diff --git a/tools/scanpy/.shed.yml b/tools/scanpy/.shed.yml
index 58706925f3c..30078db06ad 100644
--- a/tools/scanpy/.shed.yml
+++ b/tools/scanpy/.shed.yml
@@ -7,8 +7,9 @@ long_description: |
 remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/scanpy/
 type: unrestricted
 categories:
-- Transcriptomics
-- Sequence Analysis
+  - Single Cell
+  - Spatial Omics
+  - Transcriptomics
 auto_tool_repositories:
   name_template: "{{ tool_id }}"
   description_template: "Wrapper for the scanpy tool suite: {{ tool_name }}"
diff --git a/tools/scanpy/README.md b/tools/scanpy/README.md
index 10a3a036f7d..9aae2fa1557 100644
--- a/tools/scanpy/README.md
+++ b/tools/scanpy/README.md
@@ -25,6 +25,7 @@ Scanpy
     `pp.highly_variable_genes` | Extract highly variable genes
     `pp.subsample` | Subsample to a fraction of the number of observations
     `pp.downsample_counts` | Downsample counts so that each cell has no more than target_counts
+    `pp.scrublet` | Predict doublets
 
 3. Normalize (`normalize.xml`)
 
@@ -34,14 +35,18 @@ Scanpy
     `pp.recipe_zheng17` | Normalization and filtering as of [Zheng17]
     `pp.recipe_weinreb17` | Normalization and filtering as of [Weinreb17]
     `pp.recipe_seurat` | Normalization and filtering as of Seurat [Satija15]
+    `external.pp.magic` | Denoising using Markov Affinity-based Graph Imputation of Cells (MAGIC) API
 
 4. Remove confounders (`remove_confounder.xml`)
 
     Methods | Description
     --- | ---
    `pp.regress_out` | Regress out unwanted sources of variation
-   `pp.mnn_correct` | Correct batch effects by matching mutual nearest neighbors
+   <!-- `pp.mnn_correct` | Correct batch effects by matching mutual nearest neighbors -->
    `pp.combat` | ComBat function for batch effect correction
+    `external.pp.bbknn` | Batch effect removal with Batch balanced KNN (BBKNN)
+    `external.pp.harmony_integrate` | Integrate multiple single-cell experiments with Harmony
+    `external.pp.scanorama_integrate` | Integrate multiple single-cell experiments with Scanorama
 
 5. Clustering, embedding and trajectory inference (`cluster_reduce_dimension.xml`)
 
@@ -49,14 +54,14 @@ Scanpy
     --- | ---
     `tl.louvain` | Cluster cells into subgroups
     `tl.leiden` | Cluster cells into subgroups
-    `tl.pca` | Principal component analysis
-    `pp.pca` | Principal component analysis (appears to be the same func...)
+    `pp.pca` | Principal component analysis
     `tl.diffmap` | Diffusion Maps
     `tl.tsne` | t-SNE
     `tl.umap` | Embed the neighborhood graph using UMAP
     `tl.draw_graph` | Force-directed graph drawing
     `tl.dpt` | Infer progression of cells through geodesic distance along the graph
     `tl.paga` | Mapping out the coarse-grained connectivity structures of complex manifolds
+    `tl.embedding_density` | Calculate the density of cells in an embedding (per condition)
 
 6. Plot (`plot.xml`)
 
@@ -66,18 +71,20 @@ Scanpy
         --- | ---
         `pl.scatter` | Scatter plot along observations or variables axes
         `pl.heatmap` | Heatmap of the expression values of set of genes
+        `pl.tracksplot` | Tracks plot of the expression values per cell
         `pl.dotplot` | Makes a dot plot of the expression values
         `pl.violin` | Violin plot
         `pl.stacked_violin` | Stacked violin plots
         `pl.matrixplot` | Heatmap of the mean expression values per cluster
         `pl.clustermap` | Hierarchically-clustered heatmap
-    
+
     2. Preprocessing
 
         Methods | Description
         --- | ---
         `pl.highest_expr_genes` | Plot the fraction of counts assigned to each gene over all cells
         `pl.highly_variable_genes` | Plot dispersions versus means for genes
+        `pl.scrublet_score_distribution` | Histogram of doublet scores
 
     3. PCA
 
@@ -96,12 +103,13 @@ Scanpy
         `pl.umap` | Scatter plot in UMAP basis
         `pl.diffmap` | Scatter plot in Diffusion Map basis
         `pl.draw_graph` | Scatter plot in graph-drawing basis
+        `pl.embedding_density` | Density of cells in an embedding (per condition)
 
     5. Branching trajectories and pseudotime, clustering
 
         Methods | Description
         --- | ---
-        `pl.dpt_groups_pseudotime` | Plot groups and pseudotime
+        <!-- `pl.dpt_groups_pseudotime` | Plot groups and pseudotime -->
         `pl.dpt_timeseries` | Heatmap of pseudotime series
         `pl.paga` | Plot the abstracted graph through thresholding low-connectivity edges
         `pl.paga_compare` | Scatter and PAGA graph side-by-side
@@ -113,3 +121,8 @@ Scanpy
         --- | ---
         `pl.rank_genes_groups` | Plot ranking of genes using dotplot plot
         `pl.rank_genes_groups_violin` | Plot ranking of genes for all tested comparisons
+        `pl.rank_genes_groups_stacked_violin` | Plot ranking of genes as stacked violin plot
+        `pl.rank_genes_groups_heatmap` | Plot ranking of genes as heatmap plot
+        `pl.rank_genes_groups_dotplot` | Plot ranking of genes as dotplot plot
+        `pl.rank_genes_groups_matrixplot` | Plot ranking of genes as matrixplot plot
+        `pl.rank_genes_groups_tracksplot` | Plot ranking of genes as tracksplot plot
diff --git a/tools/scanpy/cluster_reduce_dimension.xml b/tools/scanpy/cluster_reduce_dimension.xml
index d8c7472563f..5e5a96c3b98 100644
--- a/tools/scanpy/cluster_reduce_dimension.xml
+++ b/tools/scanpy/cluster_reduce_dimension.xml
@@ -1,37 +1,44 @@
-<tool id="scanpy_cluster_reduce_dimension" name="Cluster, infer trajectories and embed" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
-    <description>with scanpy</description>
+<tool id="scanpy_cluster_reduce_dimension" name="Scanpy cluster, embed" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>and infer trajectories</description>
     <macros>
         <import>macros.xml</import>
         <xml name="pca_inputs">
             <param argument="n_comps" type="integer" min="0" value="50" label="Number of principal components to compute" help="If the value is larger than the number of observations the number of observations is used instead"/>
-            <param argument="dtype" type="text" value="float32" label="Numpy data type string to which to convert the result" help="">
-                <expand macro="sanitize_query" />
+            <param argument="layer" type="text" value="" optional="true" label="If provided, which element of layers to use for PCA">
+                <expand macro="sanitize_query"/>
+            </param>
+            <param argument="dtype" type="select" label="Numpy data type string to which to convert the result">
+                <option value="float32" selected="true">float32</option>
+                <option value="int32">int32</option>
+                <option value="int64">int64</option>
+                <option value="uint32">uint32</option>
+                <option value="uint64">uint64</option>
+                <option value="float16">float16</option>
+                <option value="float64">float64</option>
             </param>
             <conditional name="pca">
                 <param argument="chunked" type="select" label="Type of PCA?">
-                    <option value="True">Incremental PCA on segments (incremental PCA automatically zero centers and ignores settings of 'random_seed' and 'svd_solver')</option>
                     <option value="False" selected="true">Full PCA</option>
+                    <option value="True">Incremental PCA on segments (incremental PCA automatically zero centers and ignores settings of 'random_seed' and 'svd_solver')</option>
                 </param>
                 <when value="True">
                     <param argument="chunk_size" type="integer" min="0" value="" label="chunk_size" help="Number of observations to include in each chunk"/>
                 </when>
                 <when value="False">
-                    <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true"
-                        label="Compute standard PCA from covariance matrix?"
-                        help="If not, it omits zero-centering variables (uses *TruncatedSVD* from scikit-learn), which allows to handle sparse input efficiently."/>
+                    <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Compute standard PCA from covariance matrix?" help="If not, it omits zero-centering variables (uses *TruncatedSVD* from scikit-learn), which allows to handle sparse input efficiently."/>
                     <expand macro="svd_solver"/>
-                    <param argument="random_state" type="integer" value="0" label="Initial states for the optimization" help=""/>
+                    <param argument="random_state" type="integer" value="0" label="Change to use different initial states for the optimization"/>
                 </when>
             </conditional>
-            <param argument="use_highly_variable" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use highly variable genes only?" help="They should be use if they have been determined beforehand."/>
+            <param argument="mask_var" type="text" value="" optional="true" label="To run only on a certain set of genes given by a string referring to an array in" help="By default, uses .var['highly_variable'] if available, else everything"/>
         </xml>
         <xml name="param_random_state">
             <param argument="random_state" type="integer" value="0" label="Random state" help="Change the initialization of the optimization."/>
         </xml>
-        <xml name="param_use_weights">
-            <param argument="use_weights" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use weights from knn graph?"/>
+        <xml name="param_use_weights" token_checked="">
+            <param argument="use_weights" type="boolean" truevalue="True" falsevalue="False" checked="@CHECKED@" label="Use weights from knn graph?"/>
         </xml>
-        <token name="@CMD_pca_help@"><![CDATA[
+        <token name="@CMD_PCA_HELP@"><![CDATA[
 The PCA is computed using the implementation of *scikit-learn*.
 
 The returned AnnData object contains:
@@ -43,34 +50,25 @@ The returned AnnData object contains:
     - Explained variance, equivalent to the eigenvalues of the covariance matrix
 
 This data is accessible using the inspect tool for AnnData
-]]></token>
-        <token name="@CMD_pca_params@"><![CDATA[
-    data=adata,
-    n_comps=min($method.n_comps, adata.n_vars),
-    dtype='$method.dtype',
-    copy=False,
-    chunked=$method.pca.chunked,
-#if $method.pca.chunked == 'True'
-    chunk_size=$method.pca.chunk_size,
-#else
-    zero_center=$method.pca.zero_center,
-    svd_solver='$method.pca.svd_solver',
-    random_state=$method.pca.random_state,
-#end if
-    use_highly_variable=$method.use_highly_variable
-]]></token>
+        ]]>
+        </token>
     </macros>
     <expand macro="bio_tools"/>
     <expand macro="requirements">
+        <requirement type="package" version="0.5.6">umap-learn</requirement>
+        <requirement type="package" version="0.10.2">leidenalg</requirement>
+        <requirement type="package" version="0.8.2">louvain</requirement>
+        <requirement type="package" version="1.5.1">scikit-learn</requirement>
     </expand>
     <expand macro="version_command"/>
     <command detect_errors="exit_code"><![CDATA[
 @CMD@
-      ]]></command>
+    ]]>
+    </command>
     <configfiles>
         <configfile name="script_file"><![CDATA[
-@CMD_imports@
-@CMD_read_inputs@
+@CMD_IMPORTS@
+@CMD_READ_INPUTS@
 
 #if $method.method == 'tl.louvain'
 sc.tl.louvain(
@@ -83,6 +81,7 @@ sc.tl.louvain(
     key_added='$method.key_added',
     directed=$method.directed,
     use_weights=$method.use_weights,
+    @CMD_PARAM_NEIGHBORS_KEY@
     copy=False)
 
 #else if $method.method == 'tl.leiden'
@@ -91,33 +90,60 @@ sc.tl.leiden(
     resolution=$method.resolution,
     random_state=$method.random_state,
     key_added='$method.key_added',
+    directed=$method.directed,
     use_weights=$method.use_weights,
     n_iterations=$method.n_iterations,
+    @CMD_PARAM_NEIGHBORS_KEY@
+    flavor='$method.flavor',
     copy=False)
 
 #else if $method.method == 'pp.pca'
-sc.pp.pca(@CMD_pca_params@)
-
-#else if $method.method == 'tl.pca'
-sc.tl.pca(@CMD_pca_params@)
+sc.pp.pca(
+    data=adata,
+    n_comps=min($method.n_comps, adata.n_vars-1),
+    #if $method.layer != ''
+    layer='$method.layer',
+    #end if
+    dtype='$method.dtype',
+    chunked=$method.pca.chunked,
+    #if $method.pca.chunked == 'True'
+    chunk_size=$method.pca.chunk_size,
+    #else
+    zero_center=$method.pca.zero_center,
+    #if $method.pca.svd_solver != ''
+    svd_solver='$method.pca.svd_solver',
+    #end if
+    random_state=$method.pca.random_state,
+    #end if
+    #if $method.mask_var != ''
+    mask_var='$method.mask_var',
+    #end if
+    copy=False)
 
 #else if $method.method == 'tl.diffmap'
 sc.tl.diffmap(
     adata=adata,
-    n_comps=min($method.n_comps, adata.n_vars),
+    n_comps=min($method.n_comps, adata.n_vars-1),
+    random_state=$method.random_state,
+    @CMD_PARAM_NEIGHBORS_KEY@
     copy =False)
 
 #else if $method.method == 'tl.tsne'
+import os
 sc.tl.tsne(
     adata=adata,
     #if str($method.n_pcs) != ''
     n_pcs=$method.n_pcs,
     #end if
+    #if $method.use_rep != ''
+    use_rep='$method.use_rep',
+    #end if
     perplexity=$method.perplexity,
+    metric='$method.metric',
     early_exaggeration=$method.early_exaggeration,
     learning_rate=$method.learning_rate,
     random_state=$method.random_state,
-    use_fast_tsne=$method.use_fast_tsne,
+    n_jobs = int(os.getenv("GALAXY_SLOTS", 4)),
     copy=False)
 
 #else if $method.method == 'tl.umap'
@@ -134,6 +160,7 @@ sc.tl.umap(
     negative_sample_rate=$method.negative_sample_rate,
     init_pos='$method.init_pos',
     random_state=$method.random_state,
+    @CMD_PARAM_NEIGHBORS_KEY@
     copy=False)
 
 #else if $method.method == 'tl.draw_graph'
@@ -145,28 +172,20 @@ adjacency = io.mmread('$method.adjacency')
 sc.tl.draw_graph(
     adata=adata,
     layout='$method.layout',
-#if $method.root
-    #set $root=([int(x.strip()) for x in str($method.root).split(',')])
-    root=$root,
-#end if
-    random_state=$method.random_state,
-    #if $method.init_pos
-    init_pos='$method.init_pos',
+    #if str($method.root)
+    root=$method.root,
     #end if
+    random_state=$method.random_state,
     #if str($method.adjacency) != 'None'
     adjacency=adjacency,
     #end if
-    #if $method.key_ext
-    key_ext='$method.key_ext',
+    #if $method.key_added_ext != ''
+    key_added_ext='$method.key_added_ext',
     #end if
-    copy=False)
-
-#else if $method.method == "tl.paga"
-sc.tl.paga(
-    adata=adata,
-    groups='$method.groups',
-    use_rna_velocity=$method.use_rna_velocity,
-    model='$method.model',
+    #if $method.init_pos != ''
+    init_pos='$method.init_pos',
+    #end if
+    @CMD_PARAM_NEIGHBORS_KEY@
     copy=False)
 
 #else if $method.method == "tl.dpt"
@@ -176,24 +195,37 @@ sc.tl.dpt(
     n_branchings=$method.n_branchings,
     min_group_size=$method.min_group_size,
     allow_kendall_tau_shift=$method.allow_kendall_tau_shift,
+    @CMD_PARAM_NEIGHBORS_KEY@
+    copy=False)
+
+#else if $method.method == "tl.paga"
+sc.tl.paga(
+    adata=adata,
+    #if $method.groups != '':
+    groups='$method.groups',
+    #end if
+    use_rna_velocity=$method.use_rna_velocity,
+    model='$method.model',
+    @CMD_PARAM_NEIGHBORS_KEY@
     copy=False)
 
 #else if $method.method == "tl.embedding_density"
 sc.tl.embedding_density(
     adata=adata,
     basis='$method.basis',
-#if $method.groupby
+    #if $method.groupby != ''
     groupby='$method.groupby',
-#end if
-#if $method.key_added
+    #end if
+    #if $method.key_added != ''
     key_added='$method.key_added',
-#end if
+    #end if
     )
 
 #end if
 
-@CMD_anndata_write_outputs@
-]]></configfile>
+@CMD_ANNDATA_WRITE_OUTPUTS@
+        ]]>     
+        </configfile>
     </configfiles>
     <inputs>
         <expand macro="inputs_anndata"/>
@@ -202,113 +234,123 @@ sc.tl.embedding_density(
                 <option value="tl.louvain">Cluster cells into subgroups, using 'tl.louvain'</option>
                 <option value="tl.leiden">Cluster cells into subgroups, using 'tl.leiden'</option>
                 <option value="pp.pca">Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using 'pp.pca'</option>
-                <option value="tl.pca">Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using 'tl.pca'</option>
                 <option value="tl.diffmap">Diffusion Maps, using 'tl.diffmap'</option>
                 <option value="tl.tsne">t-distributed stochastic neighborhood embedding (tSNE), using 'tl.tsne'</option>
                 <option value="tl.umap">Embed the neighborhood graph using UMAP, using 'tl.umap'</option>
                 <option value="tl.draw_graph">Force-directed graph drawing, using 'tl.draw_graph'</option>
                 <option value="tl.dpt">Infer progression of cells through geodesic distance along the graph, using 'tl.dpt'</option>
                 <option value="tl.paga">Generate cellular maps of differentiation manifolds with complex topologies, using 'tl.paga'</option>
-                <option value="tl.embedding_density">Calculate the density of cells in an embedding (per condition)</option>
+                <option value="tl.embedding_density">Calculate the density of cells in an embedding (per condition), using 'tl.embedding_density'</option>
             </param>
             <when value="tl.louvain">
                 <conditional name="flavor">
-                    <param argument="flavor" type="select" label="Flavor for the clustering" help="">
-                        <option value="vtraag">vtraag (much more powerful)</option>
-                        <option value="igraph">igraph</option>
+                    <param argument="flavor" type="select" label="Flavor for the clustering">
+                        <option value="vtraag" selected="true">vtraag (much more powerful than igraph)</option>
+                        <option value="igraph">Built in igraph method</option>
                     </param>
                     <when value="vtraag">
-                        <param argument="resolution" type="float" value="1.0"
-                            label="Resolution"
-                            help="Higher resolution means finding more and smaller clusters, which defaults to 1.0. See “Time as a resolution parameter” in Lambiotte et al, 2009"/>
+                        <param argument="resolution" type="float" value="1.0" label="Resolution" help="Higher resolution means finding more and smaller clusters, which defaults to 1.0. See “Time as a resolution parameter” in Lambiotte et al, 2014"/>
                     </when>
                     <when value="igraph"/>
                 </conditional>
                 <expand macro="param_random_state"/>
-                <param argument="key_added" type="text" value="louvain" optional="true" label="Key under which to add the cluster labels" help="">
-                    <expand macro="sanitize_query" />
+                <param argument="key_added" type="text" value="louvain" optional="true" label="Key under which to add the cluster labels">
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="directed" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Interpret the adjacency matrix as directed graph?"/>
-                <expand macro="param_use_weights"/>
+                <expand macro="param_use_weights" checked="false"/>
+                <expand macro="param_neighbors_key"/>
             </when>
             <when value="tl.leiden">
                 <param argument="resolution" type="float" value="1" label="Coarseness of the clusterin" help="Higher values lead to more clusters"/>
                 <expand macro="param_random_state"/>
-                <param argument="key_added" type="text" value="leiden" label="Key under which to add the cluster labels" help="">
-                    <expand macro="sanitize_query" />
+                <param argument="key_added" type="text" value="leiden" label="Key under which to add the cluster labels">
+                    <expand macro="sanitize_query"/>
                 </param>
-                <expand macro="param_use_weights"/>
+                <param argument="directed" type="boolean" truevalue="True" falsevalue="None" checked="false" label="Treat the graph as directed or undirected?"/>
+                <expand macro="param_use_weights" checked="true"/>
                 <param argument="n_iterations" type="integer" value="-1" label="How many iterations of the Leiden clustering algorithm to perform." help="Positive values above 2 define the total number of iterations to perform, -1 has the algorithm run until it reaches its optimal clustering."/>
+                <expand macro="param_neighbors_key"/>
+                <param argument="flavor" type="select" label="Flavor for the clustering">
+                    <option value="leidenalg" selected="true">leidenalg</option>
+                    <option value="igraph">Built in igraph method</option>
+                </param>
             </when>
             <when value="pp.pca">
                 <expand macro="pca_inputs"/>
             </when>
-            <when value="tl.pca">
-                <expand macro="pca_inputs"/>
-            </when>
             <when value="tl.diffmap">
-                <param argument="n_comps" type="integer" min="0" value="15" optional="true" label="Number of dimensions of the representation" help=""/>
+                <param argument="n_comps" type="integer" min="0" value="15" optional="true" label="Number of dimensions of the representation"/>
+                <param argument="random_state" type="integer" value="0" label="Seed used by the random number generator"/>
+                <expand macro="param_neighbors_key"/>
             </when>
             <when value="tl.tsne">
-                <param name="n_pcs" type="integer" min="0" value="" optional="true" label="Number of PCs to use" help=""/>
-                <param name="perplexity" type="float" value="30" label="Perplexity" help="The perplexity is related to the number of nearest neighbors that is used in other manifold learning algorithms. Larger datasets usually require a larger perplexity. Consider selecting a value between 5 and 50. The choice is not extremely critical since t-SNE is quite insensitive to this parameter."/>
-                <param name="early_exaggeration" type="float" value="12.0" label="Early exaggeration" help="Controls how tight natural clusters in the original space are in the embedded space and how much space will be between them. For larger values, the space between natural clusters will be larger in the embedded space. Again, the choice of this parameter is not very critical. If the cost function increases during initial optimization, the early exaggeration factor or the learning rate might be too high."/>
-                <param name="learning_rate" type="float" value="1000" label="Learning rate" help="The learning rate can be a critical parameter. It should be between 100 and 1000. If the cost function increases during initial optimization, the early exaggeration factor or the learning rate might be too high. If the cost function gets stuck in a bad local minimum increasing the learning rate helps sometimes."/>
-                <param name="random_state" type="integer" value="0" label="Random state" help="Change this to use different intial states for the optimization"/>
-                <param argument="use_fast_tsne" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Use the MulticoreTSNE package if possible?"/>
+                <param argument="n_pcs" type="integer" min="0" value="" optional="true" label="Number of PCs to use"/>
+                <expand macro="param_use_rep"/>
+                <param argument="perplexity" type="float" value="30" label="Perplexity" help="The perplexity is related to the number of nearest neighbors that is used in other manifold learning algorithms. Larger datasets usually require a larger perplexity. Consider selecting a value between 5 and 50. The choice is not extremely critical since t-SNE is quite insensitive to this parameter."/>
+                <param argument="metric" type="select">
+                    <expand macro="distance_metric_options"/>
+                </param>
+                <param argument="early_exaggeration" type="float" value="12.0" label="Early exaggeration" help="Controls how tight natural clusters in the original space are in the embedded space and how much space will be between them. For larger values, the space between natural clusters will be larger in the embedded space. Again, the choice of this parameter is not very critical. If the cost function increases during initial optimization, the early exaggeration factor or the learning rate might be too high."/>
+                <param argument="learning_rate" type="float" value="1000" label="Learning rate" help="The learning rate can be a critical parameter. It should be between 100 and 1000. If the cost function increases during initial optimization, the early exaggeration factor or the learning rate might be too high. If the cost function gets stuck in a bad local minimum increasing the learning rate helps sometimes."/>
+                <param argument="random_state" type="integer" value="0" label="Random state" help="Change this to use different intial states for the optimization"/>
             </when>
             <when value="tl.umap">
                 <param argument="min_dist" type="float" value="0.5" label="Effective minimum distance between embedded points" help="Smaller values will result in a more clustered/clumped embedding where nearby points on the manifold are drawn closer together, while larger values will result on a more even dispersal of points. The value should be set relative to the 'spread' value, which determines the scale at which embedded points will be spread out. The default of in the 'umap-learn' package is 0.1."/>
                 <param argument="spread" type="float" value="1.0" label="Effective scale of embedded points" help="In combination with 'min_dist' this determines how clustered/clumped the embedded points are."/>
-                <param argument="n_components" type="integer" min="0" value="2" label="Number of dimensions of the embedding" help=""/>
+                <param argument="n_components" type="integer" min="0" value="2" label="Number of dimensions of the embedding"/>
                 <param argument="maxiter" type="integer" min="0" value="" optional="true" label="Number of iterations (epochs) of the optimization" help="Called 'n_epochs' in the original UMAP."/>
-                <param argument="alpha" type="float" value="1.0" label="Initial learning rate for the embedding optimization" help=""/>
+                <param argument="alpha" type="float" value="1.0" label="Initial learning rate for the embedding optimization"/>
                 <param argument="gamma" type="float" value="1.0" label="Weighting applied to negative samples in low dimensional embedding optimization" help="Values higher than one will result in greater weight being given to negative samples."/>
-                <param argument="negative_sample_rate" type="integer" min="0" value="5" label="The number of negative edge/1-simplex samples to use per positive edge/1-simplex sample in optimizing the low dimensional embedding" help=""/>
+                <param argument="negative_sample_rate" type="integer" min="0" value="5" label="The number of negative edge/1-simplex samples to use per positive edge/1-simplex sample in optimizing the low dimensional embedding"/>
                 <param argument="init_pos" type="select" label="How to initialize the low dimensional embedding" help="Called 'init' in the original UMAP">
-                    <option value="paga">Position from paga</option>
                     <option value="spectral" selected="true">Spectral embedding of the graph</option>
+                    <option value="paga">Position from paga</option>
                     <option value="random">Initial embedding positions at random</option>
                 </param>
-                <expand macro="param_random_state"/>
+                <param argument="random_state" type="integer" value="0" label="Seed used by the random number generator"/>
+                <expand macro="param_neighbors_key"/>
             </when>
             <when value="tl.draw_graph">
                 <expand macro="param_layout"/>
-                <expand macro="param_root"/>
-                <expand macro="param_random_state"/>
-                <param argument="init_pos" type="text" optional="true" value="" label="Precomputed coordinates for initialization" help="It should be a valid 2d observation (e.g. paga)">
-                    <expand macro="sanitize_query" />
-                </param>
+                <param argument="root" type="integer" value="" optional="true" label="Root for tree layouts"/>
+                <param argument="random_state" type="integer" value="0" optional="true" label="Random state" help="For layouts with random initialization like 'fr', change this to use different intial states for the optimization."/>
                 <param argument="adjacency" type="data" format="mtx" optional="true" label="Sparse adjacency matrix of the graph" help="If not set, it uses the unstructured annotation (uns) / neighbors / connectivities"/>
-                <param argument="key_ext" type="text" optional="true" value="" label="External key" help="If not set, it appends 'layout'">
-                    <expand macro="sanitize_query" />
+                <param argument="key_added_ext" type="text" optional="true" value="" label="External key" help="If not set, it appends 'layout'">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="init_pos" type="text" optional="true" value="" label="Precomputed coordinates for initialization" help="It should be a valid 2d observation (e.g. paga)">
+                    <expand macro="sanitize_query"/>
                 </param>
+                <expand macro="param_neighbors_key"/>
             </when>
             <when value="tl.dpt">
-                <param argument="n_dcs" type="integer" min="0" value="10" label="Number of diffusion components to use" help=""/>
-                <param argument="n_branchings" type="integer" min="0" value="0" label="Number of branchings to detect" help=""/>
+                <param argument="n_dcs" type="integer" min="0" value="10" label="Number of diffusion components to use"/>
+                <param argument="n_branchings" type="integer" min="0" value="0" label="Number of branchings to detect"/>
                 <param argument="min_group_size" type="float" min="0" value="0.01" label="Min group size" help="During recursive splitting of branches ('dpt groups') for 'n_branchings' &gt; 1, do not consider groups that contain less than 'min_group_size' data points. If a float, 'min_group_size' refers to a fraction of the total number of data points."/>
                 <param argument="allow_kendall_tau_shift" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Allow Kendal tau shift?" help="If a very small branch is detected upon splitting, shift away from maximum correlation in Kendall tau criterion of Haghverdi et al (2016) to stabilize the splitting."/>
+                <expand macro="param_neighbors_key"/>
             </when>
             <when value="tl.paga">
-                <param argument="groups" type="text" value="louvain" label="Key for categorical in the input" help="You can pass your predefined groups by choosing any categorical annotation of observations ('adata.obs').">
-                    <expand macro="sanitize_query" />
+                <param argument="groups" type="text" optional="true" value="" label="Key for categorical in the input" help="You can pass your predefined groups by choosing any categorical annotation of observations ('adata.obs').">
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="use_rna_velocity" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use RNA velocity to orient edges in the abstracted graph and estimate transitions?" help="Requires that 'adata.uns' contains a directed single-cell graph with key '['velocyto_transitions']'. This feature might be subject to change in the future."/>
-                <param argument="model" type="select" label="PAGA connectivity model" help="">
-                    <option value="v1.2">v1.2</option>
+                <param argument="model" type="select" label="PAGA connectivity model">
+                    <option value="v1.2" selected="true">v1.2</option>
                     <option value="v1.0">v1.0</option>
                 </param>
+                <expand macro="param_neighbors_key"/>
             </when>
             <when value="tl.embedding_density">
                 <param argument="basis" type="text" value="umap" label="The embedding over which the density will be calculated." help="This embedded representation should be found in adata.obsm['X_[basis]']">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="groupby" type="text" optional="true" value="" label="Key for categorical observation/cell annotation for which densities are calculated per category." >
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="key_added" type="text" optional="true" value="" label="Name of the .obs covariate that will be added with the density estimates.">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
             </when>
         </conditional>
@@ -318,22 +360,16 @@ sc.tl.embedding_density(
         <expand macro="anndata_outputs"/>
     </outputs>
     <tests>
+
+        <!-- test 1 -->
         <test expect_num_outputs="2">
-            <!-- test 1 -->
-            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.louvain"/>
-                <conditional name="flavor">
-                    <param name="flavor" value="vtraag"/>
-                    <param name="resolution" value="1.0"/>
-                </conditional>
                 <param name="random_state" value="10"/>
-                <param name="key_added" value="louvain"/>
-                <param name="directed" value="true"/>
-                <param name="use_weights" value="false"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -347,21 +383,23 @@ sc.tl.embedding_density(
                     <has_text_matching expression="use_weights=False"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/louvain"/>
+                    <has_h5_keys keys="uns/louvain"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 2 -->
         <test expect_num_outputs="2">
-            <!-- test 2 -->
-            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.leiden"/>
-                <param name="random_state" value="1"/>
                 <param name="random_state" value="10"/>
-                <param name="key_added" value="leiden"/>
-                <param name="use_weights" value="false"/>
-                <param name="n_iterations" value="-1"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -369,29 +407,26 @@ sc.tl.embedding_density(
                     <has_text_matching expression="resolution=1"/>
                     <has_text_matching expression="random_state=10"/>
                     <has_text_matching expression="key_added='leiden'"/>
-                    <has_text_matching expression="use_weights=False"/>
+                    <has_text_matching expression="use_weights=True"/>
                     <has_text_matching expression="n_iterations=-1"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/leiden"/>
+                    <has_h5_keys keys="uns/leiden"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 3 -->
         <test expect_num_outputs="2">
-            <!-- test 3 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.pca"/>
-                <param name="n_comps" value="50"/>
-                <param name="dtype" value="float32"/>
-                <conditional name="pca">
-                    <param name="chunked" value="False"/>
-                    <param name="zero_center" value="true"/>
-                    <param name="svd_solver" value="auto"/>
-                    <param name="random_state" value="0"/>
-                </conditional>
-                <param name="use_highly_variable" value="false"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -400,28 +435,31 @@ sc.tl.embedding_density(
                     <has_text_matching expression="copy=False"/>
                     <has_text_matching expression="chunked=False"/>
                     <has_text_matching expression="zero_center=True"/>
-                    <has_text_matching expression="svd_solver='auto'"/>
                     <has_text_matching expression="random_state=0"/>
-                    <has_text_matching expression="use_highly_variable=False"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/pca"/>
+                    <has_h5_keys keys="obsm/X_pca"/>
+                    <has_h5_keys keys="varm/PCs"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 4 -->
         <test expect_num_outputs="2">
-            <!-- test 4 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.pca"/>
                 <param name="n_comps" value="20"/>
-                <param name="dtype" value="float32"/>
                 <conditional name="pca">
                     <param name="chunked" value="True"/>
                     <param name="chunk_size" value="50"/>
                 </conditional>
-                <param name="use_highly_variable" value="false"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -431,73 +469,48 @@ sc.tl.embedding_density(
                     <has_text_matching expression="copy=False"/>
                     <has_text_matching expression="chunked=True"/>
                     <has_text_matching expression="chunk_size=50"/>
-                    <has_text_matching expression="use_highly_variable=False"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.pca.krumsiek11_chunk.h5ad" ftype="h5ad" compare="sim_size"/>
-        </test>
-        <test expect_num_outputs="2">
-            <!-- test 5 -->
-            <param name="adata" value="krumsiek11.h5ad" />
-            <conditional name="method">
-                <param name="method" value="tl.pca"/>
-                <param name="n_comps" value="50"/>
-                <param name="dtype" value="float32"/>
-                <conditional name="pca">
-                    <param name="chunked" value="False"/>
-                    <param name="zero_center" value="True"/>
-                    <param name="svd_solver" value="auto"/>
-                    <param name="random_state" value="0"/>
-                </conditional>
-                <param name="use_highly_variable" value="false"/>
-            </conditional>
-            <section name="advanced_common">
-                <param name="show_log" value="true" />
-            </section>
-            <output name="hidden_output">
+            <output name="anndata_out" ftype="h5ad">
                 <assert_contents>
-                    <has_text_matching expression="sc.tl.pca"/>
-                    <has_text_matching expression="dtype='float32'"/>
-                    <has_text_matching expression="copy=False"/>
-                    <has_text_matching expression="chunked=False"/>
-                    <has_text_matching expression="zero_center=True"/>
-                    <has_text_matching expression="svd_solver='auto'"/>
-                    <has_text_matching expression="use_highly_variable=False"/>
+                    <has_h5_keys keys="uns/pca"/>
+                    <has_h5_keys keys="obsm/X_pca"/>
+                    <has_h5_keys keys="varm/PCs"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.pca.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.15"/>
         </test>
+        
+        <!-- test 5 -->
         <test expect_num_outputs="2">
-            <!-- test 6 -->
-            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.diffmap"/>
-                <param name="n_comps" value="15"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.tl.diffmap"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obsm/X_diffmap"/>
+                    <has_h5_keys keys="uns/diffmap_evals"/>
+                </assert_contents>
+            </output>
         </test>
+        
+        <!-- test 6 -->
         <test expect_num_outputs="2">
-            <!-- test 7 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.tsne"/>
                 <param name="n_pcs" value="10"/>
-                <param name="perplexity" value="30"/>
-                <param name="early_exaggeration" value="12.0"/>
-                <param name="learning_rate" value="1000"/>
-                <param name="random_state" value="0"/>
-                <param name="use_fast_tsne" value="true"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -507,28 +520,25 @@ sc.tl.embedding_density(
                     <has_text_matching expression="early_exaggeration=12.0"/>
                     <has_text_matching expression="learning_rate=1000.0"/>
                     <has_text_matching expression="random_state=0"/>
-                    <has_text_matching expression="use_fast_tsne=True"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.tsne.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/tsne"/>
+                    <has_h5_keys keys="obsm/X_tsne"/>
+                </assert_contents>
+            </output>
         </test>
+        
+        <!-- test 7 -->
         <test expect_num_outputs="2">
-            <!-- test 8 -->
-            <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.umap"/>
-                <param name="min_dist" value="0.5"/>
-                <param name="spread" value="1.0"/>
-                <param name="n_components" value="2"/>
                 <param name="maxiter" value="2"/>
-                <param name="alpha" value="1.0"/>
-                <param name="gamma" value="1.0"/>
-                <param name="negative_sample_rate" value="5"/>
-                <param name="init_pos" value="spectral"/>
-                <param name="random_state" value="0"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -544,22 +554,22 @@ sc.tl.embedding_density(
                     <has_text_matching expression="random_state=0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size">
+            <output name="anndata_out" ftype="h5ad">
                 <assert_contents>
-                    <has_h5_keys keys="X, obs, obsm, uns, var" />
+                    <has_h5_keys keys="uns/umap"/>
+                    <has_h5_keys keys="obsm/X_umap"/>
                 </assert_contents>
             </output>
         </test>
+
+        <!-- test 8 -->
         <test expect_num_outputs="2">
-            <!-- test 9 -->
             <param name="adata" value="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.draw_graph"/>
-                <param name="layout" value="fa"/>
-                <param name="random_state" value="0"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -568,42 +578,24 @@ sc.tl.embedding_density(
                     <has_text_matching expression="random_state=0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.draw_graph.pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
-        </test>
-        <test expect_num_outputs="2">
-            <!-- test 10 -->
-            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
-            <conditional name="method">
-                <param name="method" value="tl.paga"/>
-                <param name="groups" value="paul15_clusters"/>
-                <param name="use_rna_velocity" value="False"/>
-                <param name="model" value="v1.2"/>
-            </conditional>
-            <section name="advanced_common">
-                <param name="show_log" value="true" />
-            </section>
-            <output name="hidden_output">
+            <output name="anndata_out" ftype="h5ad">
                 <assert_contents>
-                    <has_text_matching expression="sc.tl.paga"/>
-                    <has_text_matching expression="groups='paul15_clusters'"/>
-                    <has_text_matching expression="use_rna_velocity=False"/>
-                    <has_text_matching expression="model='v1.2'"/>
+                    <has_h5_keys keys="uns/draw_graph"/>
+                    <has_h5_keys keys="obsm/X_draw_graph_fr"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
+
+        <!-- test 9 -->
         <test expect_num_outputs="2">
-            <!-- test 11 -->
-            <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.dpt"/>
                 <param name="n_dcs" value="15"/>
                 <param name="n_branchings" value="1"/>
-                <param name="min_group_size" value="0.01"/>
-                <param name="allow_kendall_tau_shift" value="True"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -614,18 +606,48 @@ sc.tl.embedding_density(
                     <has_text_matching expression="allow_kendall_tau_shift=True"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/dpt_groups,obs/dpt_order,obs/dpt_order_indices"/>
+                    <has_h5_keys keys="uns/dpt_changepoints,uns/dpt_grouptips"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 10 -->
+        <test expect_num_outputs="2">    
+            <param name="adata" value="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
+            <conditional name="method">
+                <param name="method" value="tl.paga"/>
+                <param name="groups" value="paul15_clusters"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.tl.paga"/>
+                    <has_text_matching expression="groups='paul15_clusters'"/>
+                    <has_text_matching expression="use_rna_velocity=False"/>
+                    <has_text_matching expression="model='v1.2'"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/paga,uns/paul15_clusters_sizes"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 11 -->
         <test expect_num_outputs="2">
-            <!-- test 12 -->
-            <param name="adata" value="tl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="tl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.embedding_density"/>
-                <param name="basis" value="umap"/>
                 <param name="key_added" value="umap_density"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -634,10 +656,16 @@ sc.tl.embedding_density(
                     <has_text_matching expression="key_added='umap_density'"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.embedding_density.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/umap_density"/>
+                    <has_h5_keys keys="uns/umap_density_params"/>
+                </assert_contents>
+            </output>
         </test>
     </tests>
     <help><![CDATA[
+        
 Cluster cells into subgroups (`tl.louvain`)
 ===========================================
 
@@ -650,6 +678,7 @@ This requires to run `pp.neighbors`, first.
 More details on the `tl.louvain scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.louvain.html>`_
 
+
 Cluster cells into subgroups (`tl.leiden`)
 ==========================================
 
@@ -660,21 +689,13 @@ The Louvain algorithm has been proposed for single-cell analysis by Levine et al
 More details on the `tl.leiden scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.leiden.html>`_
 
+
 Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `pp.pca`
 ============================================================================================================
 
-@CMD_pca_outputs@
-
 More details on the `pp.pca scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.pca.html>`__
 
-Computes PCA (principal component analysis) coordinates, loadings and variance decomposition, using `tl.pca`
-============================================================================================================
-
-@CMD_pca_outputs@
-
-More details on the `tl.pca scanpy documentation
-<https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.pca.html>`__
 
 Diffusion Maps, using `tl.diffmap`
 ==================================
@@ -698,6 +719,7 @@ as colum. It can be accessed using the inspect tool for AnnData
 More details on the `tl.diffmap scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.diffmap.html>`__
 
+
 t-distributed stochastic neighborhood embedding (tSNE), using `tl.tsne`
 =======================================================================
 
@@ -710,6 +732,7 @@ It returns `X_tsne`, tSNE coordinates of data.
 More details on the `tl.tsne scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.tsne.html>`__
 
+
 Embed the neighborhood graph using UMAP, using `tl.umap`
 ========================================================
 
@@ -721,8 +744,8 @@ neighborhood graph. tSNE, by contrast, optimizes the distribution of
 nearest-neighbor distances in the embedding such that these best match the
 distribution of distances in the high-dimensional space.  We use the
 implementation of `umap-learn <https://github.com/lmcinnes/umap>`__
-(McInnes et al, 2018). For a few comparisons of UMAP with tSNE, see this `preprint
-<https://doi.org/10.1101/298430>`__.
+(McInnes et al, 2018). For a few comparisons of UMAP with tSNE, see this `paper
+<https://www.nature.com/articles/nbt.4314>`__.
 
 The UMAP coordinates of data are added to the return AnnData in the multi-dimensional
 observations annotation (obsm). This data is accessible using the inspect tool for AnnData
@@ -730,6 +753,7 @@ observations annotation (obsm). This data is accessible using the inspect tool f
 More details on the `tl.umap scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.umap.html>`__
 
+
 Force-directed graph drawing, using `tl.draw_graph`
 ===================================================
 
@@ -749,6 +773,7 @@ observations annotation (obsm). This data is accessible using the inspect tool f
 More details on the `tl.draw_graph scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.draw_graph.html>`__
 
+
 Infer progression of cells through geodesic distance along the graph (`tl.dpt`)
 ===============================================================================
 
@@ -808,6 +833,18 @@ These datasets are stored in the unstructured annotation (uns) and can be access
 
 More details on the `tl.paga scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.tl.paga.html>`_
-    ]]></help>
+
+
+Calculates the density of cells in an embedding (per condition). (`tl.embedding_density`)
+=========================================================================================
+
+Gaussian kernel density estimation is used to calculate the density of cells in an embedded space. This can be performed per category over a categorical cell annotation.
+
+Note that density values are scaled to be between 0 and 1. Thus, the density value at each cell is only comparable to densities in the same category.
+
+More details on the `tl.embedding_density scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/generated/scanpy.tl.embedding_density.html>`_
+    ]]>
+    </help>
     <expand macro="citations"/>
 </tool>
diff --git a/tools/scanpy/filter.xml b/tools/scanpy/filter.xml
index 1dffa8b9d6a..2624f584aac 100644
--- a/tools/scanpy/filter.xml
+++ b/tools/scanpy/filter.xml
@@ -1,18 +1,21 @@
-<tool id="scanpy_filter" name="Filter" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
-    <description>with scanpy</description>
+<tool id="scanpy_filter" name="Scanpy filter" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>mark and subsample</description>
     <macros>
         <import>macros.xml</import>
     </macros>
     <expand macro="bio_tools"/>
-    <expand macro="requirements"/>
+    <expand macro="requirements">
+        <requirement type="package" version="0.2.3">scrublet</requirement>
+        <requirement type="package" version="0.1.4">scikit-misc</requirement>
+    </expand>
     <expand macro="version_command"/>
     <command detect_errors="exit_code"><![CDATA[
 @CMD@
       ]]></command>
     <configfiles>
         <configfile name="script_file"><![CDATA[
-@CMD_imports@
-@CMD_read_inputs@
+@CMD_IMPORTS@
+@CMD_READ_INPUTS@
 
 #if $method.method == 'pp.filter_cells'
 sc.pp.filter_cells(
@@ -28,6 +31,8 @@ sc.pp.filter_cells(
     #end if
     copy=False)
 
+@CMD_ANNDATA_WRITE_OUTPUTS@
+
 #else if $method.method == 'pp.filter_genes'
 sc.pp.filter_genes(
     adata,
@@ -42,6 +47,8 @@ sc.pp.filter_genes(
     #end if
     copy=False)
 
+@CMD_ANNDATA_WRITE_OUTPUTS@
+
 #else if $method.method == 'tl.filter_rank_genes_groups'
 sc.tl.filter_rank_genes_groups(
     adata,
@@ -55,26 +62,49 @@ sc.tl.filter_rank_genes_groups(
     key_added='$method.key_added',
     min_in_group_fraction=$method.min_in_group_fraction,
     max_out_group_fraction=$method.max_out_group_fraction,
-    min_fold_change=$method.min_fold_change)
+    min_fold_change=$method.min_fold_change,
+    compare_abs=$method.compare_abs)
+
+# Temporary fix for Issue reported here: https://github.com/scverse/anndata/issues/726
+# Check and convert elements in 'rank_genes_groups_filtered' to strings
+if 'rank_genes_groups_filtered' in adata.uns:
+    for key, value in adata.uns['rank_genes_groups_filtered'].items():
+        if not isinstance(value, str):
+            adata.uns['rank_genes_groups_filtered'][key] = str(value)
+
+@CMD_ANNDATA_WRITE_OUTPUTS@
 
 #else if $method.method == "pp.highly_variable_genes"
 sc.pp.highly_variable_genes(
     adata=adata,
     flavor='$method.flavor.flavor',
-    #if $method.flavor.flavor == 'seurat'
-        min_mean=$method.flavor.min_mean,
-        max_mean=$method.flavor.max_mean,
-        min_disp=$method.flavor.min_disp,
+    #if $method.flavor.flavor == 'seurat':
+    min_mean=$method.flavor.min_mean,
+    max_mean=$method.flavor.max_mean,
+    min_disp=$method.flavor.min_disp,
         #if str($method.flavor.max_disp) != ''
-        max_disp=$method.flavor.max_disp,
+    max_disp=$method.flavor.max_disp,
         #end if
-    #else if $method.flavor.flavor == 'cell_ranger'
+    #else if $method.flavor.flavor == 'cell_ranger':
+    n_top_genes=$method.flavor.n_top_genes,
+    #else if $method.flavor.flavor == 'seurat_v3':
+    n_top_genes=$method.flavor.n_top_genes,
+    span=$method.flavor.span,
+    #else if $method.flavor.flavor == 'seurat_v3_paper':
     n_top_genes=$method.flavor.n_top_genes,
     #end if
     n_bins=$method.n_bins,
     subset=$method.subset,
+    #if $method.layer != ''
+    layer='$method.layer',
+    #end if
+    #if $method.batch_key != ''
+    layer='$method.batch_key',
+    #end if
     inplace=True)
 
+@CMD_ANNDATA_WRITE_OUTPUTS@
+
 #else if $method.method == 'pp.subsample'
 sc.pp.subsample(
     data=adata,
@@ -86,7 +116,16 @@ sc.pp.subsample(
     random_state=$method.random_state,
     copy=False)
 
+@CMD_ANNDATA_WRITE_OUTPUTS@
+
 #else if $method.method == "pp.downsample_counts"
+    #if str($method.counts_per_cell) != ''
+print("Sum of counts for the first cell before:", adata.X[0, :].sum())
+print("Sum of counts for the last cell before:", adata.X[adata.X.shape[0]-1, :].sum())
+    #else if str($method.total_counts) != ''
+print("Sum of total counts before:", adata.X.sum())
+    #end if
+
 sc.pp.downsample_counts(
     adata=adata,
     #if str($method.counts_per_cell) != ''
@@ -99,11 +138,20 @@ sc.pp.downsample_counts(
     replace=$method.replace,
     copy=False)
 
+    #if str($method.counts_per_cell) != ''
+print("Sum of counts for the first cell after:", adata.X[0, :].sum())
+print("Sum of counts for the last cell after:", adata.X[adata.X.shape[0]-1, :].sum())
+    #else if str($method.total_counts) != ''
+print("Sum of total counts after:", adata.X.sum())
+    #end if
+
+@CMD_ANNDATA_WRITE_OUTPUTS@
+
 #else if $method.method == "filter_marker"
 
-#if $method.layer_selection.use_raw == 'False':
-    adata.X = adata.layers['$method.layer_selection.layer']
-#end if
+    #if $method.layer_selection.use_raw == 'False':
+adata.X = adata.layers['$method.layer_selection.layer']
+    #end if
 
 def check_marker(adata, group, gene, thresh_mean, thresh_frac, groupby):
     filtered_data = adata[adata.obs[groupby] == group, adata.var_names == gene]
@@ -115,9 +163,9 @@ def check_marker(adata, group, gene, thresh_mean, thresh_frac, groupby):
 
 header='infer'
 
-#if $method.header == 'not_included':
-    header=None
-#end if
+    #if $method.header == 'not_included':
+header=None
+    #end if
 
 marker_list={key: list(value.values()) for key, value in pd.read_csv('$method.markerfile', sep='\t', index_col=0, header=header).to_dict(orient='index').items()}
 
@@ -133,10 +181,36 @@ for key, value in marker_list.items():
 
 df = pd.DataFrame(marker_list).T
 df.to_csv('marker.tsv', sep='\t', index=True)
-#end if
 
-@CMD_anndata_write_outputs@
-]]></configfile>
+#else if $method.method == "pp.scrublet"
+sc.pp.scrublet(
+    adata,
+    #if $method.batch_key != ''
+    batch_key='$method.batch_key',
+    #end if
+    sim_doublet_ratio=$method.sim_doublet_ratio,
+    expected_doublet_rate=$method.expected_doublet_rate,
+    stdev_doublet_rate=$method.stdev_doublet_rate,
+    synthetic_doublet_umi_subsampling=$method.synthetic_doublet_umi_subsampling,
+    knn_dist_metric='$method.knn_dist_metric',
+    normalize_variance=$method.normalize_variance,
+    log_transform=$method.log_transform,
+    mean_center=$method.mean_center,
+    n_prin_comps=$method.n_prin_comps,
+    use_approx_neighbors=$method.use_approx_neighbors,
+    get_doublet_neighbor_parents=$method.get_doublet_neighbor_parents,
+    #if str($method.n_neighbors) != ''
+    n_neighbors=$method.n_neighbors,
+    #end if
+    #if str($method.threshold) != ''
+    threshold=$method.threshold,
+    #end if
+    random_state=$method.random_state)
+
+@CMD_ANNDATA_WRITE_OUTPUTS@
+#end if
+        ]]>
+        </configfile>
     </configfiles>
     <inputs>
         <expand macro="inputs_anndata"/>
@@ -149,33 +223,34 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                 <option value="pp.subsample">Subsample to a fraction of the number of observations, using 'pp.subsample'</option>
                 <option value="pp.downsample_counts">Downsample counts from count matrix, using 'pp.downsample_counts'</option>
                 <option value="filter_marker">Filter markers from count matrix and marker list</option>
+                <option value="pp.scrublet">Predict doublets using 'pp.scrublet'</option>
             </param>
             <when value="pp.filter_cells">
                 <conditional name="filter">
                     <param argument="filter" type="select" label="Filter">
-                        <option value="min_counts">Minimum number of counts</option>
+                        <option value="min_counts" selected="true">Minimum number of counts</option>
                         <option value="max_counts">Maximum number of counts</option>
                         <option value="min_genes">Minimum number of genes expressed</option>
                         <option value="max_genes">Maximum number of genes expressed</option>
                     </param>
                     <when value="min_counts">
-                        <param argument="min_counts" type="integer" min="0" value="" label="Minimum number of counts required for a cell to pass filtering" help=""/>
+                        <param argument="min_counts" type="integer" min="0" value="" label="Minimum number of counts required for a cell to pass filtering"/>
                     </when>
                     <when value="max_counts">
-                        <param argument="max_counts" type="integer" min="0" value="" label="Maximum number of counts required for a cell to pass filtering" help=""/>
+                        <param argument="max_counts" type="integer" min="0" value="" label="Maximum number of counts required for a cell to pass filtering"/>
                     </when>
                     <when value="min_genes">
-                        <param argument="min_genes" type="integer" min="0" value="" label="Minimum number of genes expressed required for a cell to pass filtering" help=""/>
-                    </when>    
+                        <param argument="min_genes" type="integer" min="0" value="" label="Minimum number of genes expressed required for a cell to pass filtering"/>
+                    </when>
                     <when value="max_genes">
-                        <param argument="max_genes" type="integer" min="0" value="" label="Maximum number of genes expressed required for a cell to pass filtering" help=""/>
+                        <param argument="max_genes" type="integer" min="0" value="" label="Maximum number of genes expressed required for a cell to pass filtering"/>
                     </when>
                 </conditional>
             </when>
             <when value="pp.filter_genes">
                 <conditional name="filter">
                     <param argument="filter" type="select" label="Filter">
-                        <option value="min_counts">Minimum number of counts</option>
+                        <option value="min_counts" selected="true">Minimum number of counts</option>
                         <option value="max_counts">Maximum number of counts</option>
                         <option value="min_cells">Minimum number of cells expressed</option>
                         <option value="max_cells">Maximum number of cells expressed</option>
@@ -188,7 +263,7 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     </when>
                     <when value="min_cells">
                         <param argument="min_cells" type="integer" min="0" value="" label="Minimum number of cells expressed required for a gene to pass filtering"/>
-                    </when>    
+                    </when>
                     <when value="max_cells">
                         <param argument="max_cells" type="integer" min="0" value="" label="Maximum number of cells expressed required for a gene to pass filtering"/>
                     </when>
@@ -196,24 +271,27 @@ df.to_csv('marker.tsv', sep='\t', index=True)
             </when>
             <when value="tl.filter_rank_genes_groups">
                 <param argument="key" type="text" optional="true" label="Key in adata.uns where the rank_genes_groups output is stored">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="groupby" type="text" optional="true" label="The key of the observations grouping to consider">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <expand macro="param_use_raw"/>
                 <param argument="key_added" type="text" value="rank_genes_groups_filtered" label="Key that will contain new values">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="min_in_group_fraction" type="float" min="0" max="1" value="0.25" label="Minimum fraction of genes expressing the gene within the categories"/>
                 <param argument="max_out_group_fraction" type="float" min="0" max="1" value="0.5" label="Maximum fraction of genes expressing the gene outside the categories"/>
-                <param argument="min_fold_change" type="integer" value="2" label="Minimum fold change"/>
+                <param argument="min_fold_change" type="integer" value="1" label="Minimum fold change"/>
+                <param argument="compare_abs" type="boolean" truevalue="True" falsevalue="False" checked="false" label="If selected, compare absolute values of log fold change with min_fold_change"/>
             </when>
             <when value="pp.highly_variable_genes">
                 <conditional name='flavor'>
-                    <param argument="flavor" type="select" label="Flavor for computing normalized dispersion">
-                        <option value="seurat">Seurat</option>
+                    <param argument="flavor" type="select" label="Choose the flavor for identifying highly variable genes" help="Expects logarithmized data, except when flavor='seurat_v3'/'seurat_v3_paper', in which count">
+                        <option value="seurat" selected="true">Seurat</option>
                         <option value="cell_ranger">Cell Ranger</option>
+                        <option value="seurat_v3">Seurat v3</option>
+                        <option value="seurat_v3_paper">Seurat v3 (paper)</option>
                     </param>
                     <when value="seurat">
                         <param argument="min_mean" type="float" value="0.0125" label="Minimal mean cutoff"/>
@@ -224,18 +302,29 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     <when value="cell_ranger">
                         <param argument="n_top_genes" type="integer" value="" label="Number of highly-variable genes to keep"/>
                     </when>
+                    <when value="seurat_v3">
+                        <param argument="n_top_genes" type="integer" value="" optional="false" label="Number of highly-variable genes to keep"/>
+                        <param argument="span" type="float" value="0.3" label="The fraction of the data (cells) used when estimating the variance in the loess model fit"/>
+                    </when>
+                    <when value="seurat_v3_paper">
+                        <param argument="n_top_genes" type="integer" value="" optional="false" label="Number of highly-variable genes to keep"/>
+                    </when>
                 </conditional>
                 <param argument="n_bins" type="integer" value="20" label="Number of bins for binning the mean gene expression" help="Normalization is done with respect to each bin. If just a single gene falls into a bin, the normalized dispersion is artificially set to 1"/>
                 <param argument="subset" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Inplace subset to highly-variable genes?" help="Otherwise it merely indicates highly variable genes."/>
+                <expand macro="param_layer"/>
+                <param argument="batch_key" type="text" value="" label="Specify the batch key" help="If specified, highly-variable genes are selected within each batch separately and merged.">
+                    <expand macro="sanitize_query"/>
+                </param>
             </when>
             <when value="pp.subsample">
                 <conditional name="type">
                     <param name="type" type="select" label="Type of subsampling">
-                        <option value="fraction">By fraction</option>
+                        <option value="fraction" selected="true">By fraction</option>
                         <option value="n_obs">By number of observation</option>
                     </param>
                     <when value="fraction">
-                        <param argument="fraction" type="float" value="" label="Subsample to this 'fraction' of the number of observations"/>
+                        <param argument="fraction" type="float" min="0" value="" label="Subsample to this 'fraction' of the number of observations"/>
                     </when>
                     <when value="n_obs">
                         <param argument="n_obs" type="integer" min="0" value="" label="Subsample to this number of observations"/>
@@ -251,15 +340,12 @@ df.to_csv('marker.tsv', sep='\t', index=True)
             </when>
             <when value="filter_marker">
                 <param argument="markerfile" type="data" format="tabular" label="List of markers" help="This should be a tsv where row = group (e.g. celltypes) and columns = markers."></param>
-                <param name="header" type="select" label="Header in the list of markers?">
-                    <option value="included">Header incldued</option>
-                    <option value="not_included">Header not included</option>
-                </param>
+                <param name="header" type="boolean" truevalue="included" falsevalue="not_included" checked="true" label="Header is included in the list of markers?"/>
                 <param argument="thresh_mean" type="float" min="0.0" value="1.0" label="Minimal average count of all cells of a group (e.g., celltype) for a particular marker" help="Increasing the threshold will result in a smaller marker set."/>
                 <param argument="thresh_frac" type="float" min="0.0" max="1.0" value="0.1" label="Minimal fractions of cells that has a higher count than the average count of all cells of the group for the marker" help="Increasing this threshold might remove marker outliers."/>
                 <conditional name="layer_selection">
-                    <param name="use_raw" type="select" label="Use .X of adata to perform the filtering" help="">
-                        <option value="True">Yes</option>
+                    <param name="use_raw" type="select" label="Use .X of adata to perform the filtering">
+                        <option value="True" selected="true">Yes</option>
                         <option value="False">No</option>
                     </param>
                     <when value="False">
@@ -267,23 +353,46 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     </when>
                     <when value="True"/>
                 </conditional>
-                <param argument="groupby" type="text" value="" label="The key of the observation grouping to consider (e.g., celltype)" help="">
+                <param argument="groupby" type="text" value="" label="The key of the observation grouping to consider (e.g., celltype)">
+                    <expand macro="sanitize_query"/>
+                </param>
+            </when>
+            <when value="pp.scrublet">
+                <param argument="batch_key" type="text" value="" optional="true" label="Batch key for the concatenate">
                     <expand macro="sanitize_query" />
                 </param>
+                <param argument="sim_doublet_ratio" type="float" value="2.0" label="Number of doublets to simulate relative to the number of observed transcriptomes"/>
+                <param argument="expected_doublet_rate" type="float" value="0.05" label="The estimated doublet rate for the experiment"/>
+                <param argument="stdev_doublet_rate" type="float" value="0.02" label="Uncertainty in the expected doublet rate"/>
+                <param argument="synthetic_doublet_umi_subsampling" type="float" value="1.0" label="Rate for sampling UMIs when creating synthetic doublets" help="f 1.0, each doublet is created by simply adding the UMI counts from two randomly sampled observed transcriptomes. For values less than 1, the UMI counts are added and then randomly sampled at the specified rate."/>
+                <param name="knn_dist_metric" type="select" label="Distance metric used when finding nearest neighbors">
+                    <expand macro="distance_metric_options"/>
+                </param>
+                <param argument="normalize_variance" type="boolean" truevalue="True" falsevalue="False" checked="true" label="normalize the data such that each gene has a variance of 1"/>
+                <param argument="log_transform" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Whether to use log1p() to log-transform the data prior to PCA"/>
+                <param argument="mean_center" type="boolean" truevalue="True" falsevalue="False" checked="true" label="If True, center the data such that each gene has a mean of 0"/>
+                <param argument="n_prin_comps" type="integer" value="30" label="Number of principal components used to embed the transcriptomes prior to k-nearest-neighbor graph construction"/>
+                <param argument="use_approx_neighbors" type="boolean" truevalue="True" falsevalue="None" checked="false" label="Use approximate nearest neighbor method (annoy) for the KNN classifier"/>
+                <param argument="get_doublet_neighbor_parents" type="boolean" truevalue="True" falsevalue="False" checked="false" label="If True, return (in .uns) the parent transcriptomes that generated the doublet neighbors of each observed transcriptome" help="This information can be used to infer the cell states that generated a given doublet state."/>
+                <param argument="n_neighbors" type="integer" value="" optional="true" label="Number of neighbors used to construct the KNN graph of observed transcriptomes and simulated doublets"/>
+                <param argument="threshold" type="float" value="" optional="true" label="Doublet score threshold for calling a transcriptome a doublet" help="If None, this is set automatically"/>
+                <param name="random_state" type="integer" value="0" label="Initial state for doublet simulation and nearest neighbors"/>
             </when>
         </conditional>
         <expand macro="inputs_common_advanced"/>
     </inputs>
     <outputs>
-        <expand macro="anndata_outputs"/>
+        <expand macro="anndata_outputs">
+            <filter>method['method'] != 'filter_marker'</filter>
+        </expand>
         <data name="marker_out" format="tabular" from_work_dir="marker.tsv" label="${tool.name} on ${on_string}: Markers">
             <filter>method['method'] == 'filter_marker'</filter>
         </data>
     </outputs>
     <tests>
+        <!-- test 1 -->
         <test expect_num_outputs="2">
-            <!-- test 1 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.filter_cells"/>
                 <conditional name="filter">
@@ -291,112 +400,125 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     <param name="min_counts" value="3"/>
                 </conditional>
             </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
             <assert_stdout>
                 <has_text_matching expression="336 × 11"/>
             </assert_stdout>
-            <section name="advanced_common">
-                <param name="show_log" value="true" />
-            </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.filter_cells"/>
                     <has_text_matching expression="min_counts=3"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.filter_cells.krumsiek11-min_counts.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/cell_type"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 2 -->
         <test expect_num_outputs="2">
-            <!-- test 2 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.filter_cells"/>
                 <conditional name="filter">
                     <param name="filter" value="max_genes"/>
-                    <param name="max_genes" value="100"/>
+                    <param name="max_genes" value="10"/>
                 </conditional>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
+            <assert_stdout>
+                <has_text_matching expression="354 × 11"/>
+            </assert_stdout>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.filter_cells"/>
                     <has_text_matching expression="adata"/>
-                    <has_text_matching expression="max_genes=100"/>
+                    <has_text_matching expression="max_genes=10"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/cell_type"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.filter_cells.krumsiek11-max_genes.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
+
+        <!-- test 3 -->
         <test expect_num_outputs="2">
-            <!-- test 3 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.filter_genes"/>
                 <conditional name="filter">
                     <param name="filter" value="min_counts"/>
-                    <param name="min_counts" value="3"/>
+                    <param name="min_counts" value="100"/>
                 </conditional>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
+            <assert_stdout>
+                <has_text_matching expression="640 × 8"/>
+            </assert_stdout>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.filter_genes"/>
-                    <has_text_matching expression="min_counts=3"/>
+                    <has_text_matching expression="min_counts=100"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/cell_type"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.filter_genes.krumsiek11-min_counts.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
 
         <!--  test 4 -->
         <!-- Fails to write to anndata after tl.filter_rank_genes_groups
              Issue has been reported here: https://github.com/scverse/anndata/issues/726
              The current fix is: del adata.uns['rank_genes_groups_filtered']  -->
-        <!--<test expect_num_outputs="2">
-            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad" />
+        <!-- The issue is fixed in the script here -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.filter_rank_genes_groups"/>
                 <param name="key" value="rank_genes_groups"/>
-                <param name="use_raw" value="False"/>
-                <param name="key_added" value="rank_genes_groups_filtered"/>
-                <param name="min_in_group_fraction" value="0.25"/>
-                <param name="max_out_group_fraction" value="0.5"/>
                 <param name="min_fold_change" value="3"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="tl.filter_rank_genes_groups"/>
                     <has_text_matching expression="key='rank_genes_groups'"/>
                     <has_text_matching expression="use_raw=False"/>
-                    <has_text_matching expression="log=False"/>
                     <has_text_matching expression="key_added='rank_genes_groups_filtered'"/>
                     <has_text_matching expression="min_in_group_fraction=0.25"/>
                     <has_text_matching expression="max_out_group_fraction=0.5"/>
                     <has_text_matching expression="min_fold_change=3"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.filter_rank_genes_groups.h5ad" ftype="h5ad" compare="sim_size"/>
-        </test>-->
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/rank_genes_groups_filtered"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 5 -->
         <test expect_num_outputs="2">
-            <!-- test 5 -->
             <param name="adata" value="blobs.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.highly_variable_genes"/>
-                <conditional name="flavor">
-                    <param name="flavor" value="seurat"/>
-                    <param name="min_mean" value="0.0125"/>
-                    <param name="max_mean" value="3"/>
-                    <param name="min_disp" value="0.5"/>
-                </conditional>
-                <param name="n_bins" value="20"/>
-                <param name="subset" value="false"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -409,22 +531,27 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     <has_text_matching expression="subset=False"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.highly_variable_genes.seurat.blobs.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.2"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="var/highly_variable,var/means,var/dispersions,var/dispersions_norm"/>
+                    <has_h5_keys keys="uns/hvg"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 6 -->
         <test expect_num_outputs="2">
-            <!-- test 6 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.highly_variable_genes"/>
                 <conditional name="flavor">
                     <param name="flavor" value="cell_ranger"/>
                     <param name="n_top_genes" value="2"/>
                 </conditional>
-                <param name="n_bins" value="20"/>
                 <param name="subset" value="true"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -435,22 +562,30 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     <has_text_matching expression="subset=True"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.highly_variable_genes.krumsiek11-cell_ranger.h5ad" ftype="h5ad" compare="sim_size" delta="100000" delta_frac="0.9"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="var/highly_variable,var/means,var/dispersions,var/dispersions_norm"/>
+                    <has_h5_keys keys="uns/hvg"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 7 -->
         <test expect_num_outputs="2">
-            <!-- test 7 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.subsample"/>
                 <conditional name="type">
-                    <param name="type" value="fraction" />
+                    <param name="type" value="fraction"/>
                     <param name="fraction" value="0.5"/>
                 </conditional>
-                <param name="random_state" value="0"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
+            <assert_stdout>
+                <has_text_matching expression="320 × 11"/>
+            </assert_stdout>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.subsample"/>
@@ -458,22 +593,29 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     <has_text_matching expression="random_state=0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.subsample.krumsiek11_fraction.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/cell_type"/>
+                </assert_contents>
+            </output>
         </test>
-        <test expect_num_outputs="2">
-            <!-- test 8 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+
+        <!-- test 8 -->
+        <test expect_num_outputs="2">    
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.subsample"/>
                 <conditional name="type">
-                    <param name="type" value="n_obs" />
+                    <param name="type" value="n_obs"/>
                     <param name="n_obs" value="10"/>
                 </conditional>
-                <param name="random_state" value="0"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
+            <assert_stdout>
+                <has_text_matching expression="10 × 11"/>
+            </assert_stdout>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.subsample"/>
@@ -481,19 +623,22 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     <has_text_matching expression="random_state=0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.subsample.krumsiek11_n_obs.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/cell_type"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 9 -->
         <test expect_num_outputs="2">
-            <!-- test 9 -->
-            <param name="adata" value="random-randint.h5ad" />
+            <param name="adata" value="random-randint.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.downsample_counts"/>
                 <param name="total_counts" value="20000"/>
-                <param name="random_state" value="0"/>
-                <param name="replace" value="false"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -501,35 +646,100 @@ df.to_csv('marker.tsv', sep='\t', index=True)
                     <has_text_matching expression="total_counts=20000"/>
                     <has_text_matching expression="random_state=0"/>
                     <has_text_matching expression="replace=False"/>
+                    <has_text_matching expression="Sum of total counts before: 49983776.0"/>
+                    <has_text_matching expression="Sum of total counts after: 20000"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="var/index"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.downsample_counts.random-randint.h5ad" ftype="h5ad" compare="sim_size" delta="10000000" delta_frac="0.5"/>
         </test>
-        <test expect_num_outputs="3">
-            <!-- test 10 -->
-            <param name="adata" value="cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad" />
+
+        <!-- test 10 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="random-randint.h5ad"/>
+            <conditional name="method">
+                <param name="method" value="pp.downsample_counts"/>
+                <param name="counts_per_cell" value="20000"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pp.downsample_counts"/>
+                    <has_text_matching expression="counts_per_cell=20000"/>
+                    <has_text_matching expression="random_state=0"/>
+                    <has_text_matching expression="replace=False"/>
+                    <has_text_matching expression="Sum of counts for the first cell before: 489934.0"/>
+                    <has_text_matching expression="Sum of counts for the last cell before: 503669.0"/>
+                    <has_text_matching expression="Sum of counts for the first cell after: 20000.0"/>
+                    <has_text_matching expression="Sum of counts for the last cell after: 20000.0"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="var/index"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 10 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad"/>
             <conditional name="method">
                 <param name="method" value="filter_marker"/>
                 <param name="markerfile" value="tl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.tsv"/>
-                <param name="thresh_mean" value="1.0"/>
                 <param name="thresh_frac" value="0.2"/>
-                <param name="layer_selection" value="True"/>
+                <conditional name="layer_selection">
+                    <param name="use_raw" value="True"/>
+                </conditional>
                 <param name="groupby" value="bulk_labels"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="adata, key, x, 1.0, 0.2, 'bulk_labels'"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1_out.h5ad" ftype="h5ad">
+            <output name="marker_out" ftype="tabular">
                 <assert_contents>
-                    <has_h5_keys keys="obs, var, uns" />
+                    <has_text text="CD14+ Monocyte"/>
+                    <has_text text="C9orf142"/>
+                    <has_text text="EGR1"/>
+                    <has_text text="GZMB"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 11 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="krumsiek11.h5ad"/>
+            <conditional name="method">
+            <param name="method" value="pp.scrublet"/>
+                <param name="n_prin_comps" value="5"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pp.scrublet"/>
+                    <has_text_matching expression="sim_doublet_ratio=2.0"/>
+                    <has_text_matching expression="expected_doublet_rate=0.05"/>
+                    <has_text_matching expression="n_prin_comps=5"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/doublet_score,obs/predicted_doublet"/>
+                    <has_h5_keys keys="uns/scrublet"/>
                 </assert_contents>
             </output>
-            <output name="marker_out" file="tl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.tsv" ftype="tabular" compare="sim_size"/>
         </test>
     </tests>
     <help><![CDATA[
@@ -589,9 +799,11 @@ Downsample counts (`pp.downsample_counts`)
 Downsample counts so that each cell has no more than `target_counts`. Cells with fewer counts than `target_counts` are unaffected by this. This
 has been implemented by M. D. Luecken.
 
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/generated/scanpy.pp.downsample_counts.html>`__
 
 Filter marker genes (`filter_marker`)
-======================================================================
+=====================================
 
 This option is specific for celltype marker gene detection. You can generate a celltype marker gene file (tsv) with **COSG** provided at Galaxy.
 
@@ -603,6 +815,14 @@ More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.downsample_counts.html>`__
 
 
+Predict cell doublets using a nearest-neighbor classifier of observed transcriptomes and simulated doublets. (`pp.scrublet`)
+============================================================================================================================
+
+Works best if the input is a raw (unnormalized) counts matrix from a single sample or a collection of similar samples from the same experiment. This function is a wrapper around functions that pre-process using Scanpy and directly call functions of Scrublet().
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pp.scrublet.html>`__
+
     ]]></help>
     <expand macro="citations"/>
 </tool>
diff --git a/tools/scanpy/inspect.xml b/tools/scanpy/inspect.xml
index fe65373723c..2957ca6db43 100644
--- a/tools/scanpy/inspect.xml
+++ b/tools/scanpy/inspect.xml
@@ -1,102 +1,121 @@
-<tool id="scanpy_inspect" name="Inspect and manipulate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
-    <description> with scanpy</description>
+<tool id="scanpy_inspect" name="Scanpy Inspect and manipulate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
     <macros>
         <import>macros.xml</import>
-        <xml name="score_genes_params">
-            <param argument="n_bins" type="integer" value="25" label="Number of expression level bins for sampling" help=""/>
-            <param argument="random_state" type="integer" value="0" label="Random seed for sampling" help=""/>
+        <xml name="params_score_genes">
+            <param argument="n_bins" type="integer" value="25" label="Number of expression level bins for sampling"/>
+            <param argument="random_state" type="integer" value="0" label="Random seed for sampling"/>
             <expand macro="param_use_raw"/>
         </xml>
-        <token name="@CMD_score_genes_inputs@"><![CDATA[
+        <token name="@CMD_PARAMS_SCORE_GENES@"><![CDATA[
     n_bins=$method.n_bins,
     random_state=$method.random_state,
     use_raw=$method.use_raw,
     copy=False
-        ]]></token>
+        ]]>
+        </token>
         <xml name="corr_method">
             <param argument="corr_method" type="select" label="P-value correction method">
-                <option value="benjamini-hochberg">Benjamini-Hochberg</option>
+                <option value="benjamini-hochberg" selected="true">Benjamini-Hochberg</option>
                 <option value="bonferroni">Bonferroni</option>
             </param>
         </xml>
         <xml name="fit_intercept">
-            <param argument="fit_intercept" type="boolean" truevalue="True" falsevalue="False" checked="true"
-                label="Should a constant (a.k.a. bias or intercept) be added to the decision function?" help=""/>
+            <param argument="fit_intercept" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Should a constant (a.k.a. bias or intercept) be added to the decision function?"/>
         </xml>
         <xml name="max_iter">
-            <param argument="max_iter" type="integer" min="0" value="100" label="Maximum number of iterations taken for the solvers to converge" help=""/>
+            <param argument="max_iter" type="integer" min="0" value="100" label="Maximum number of iterations taken for the solvers to converge"/>
         </xml>
         <xml name="multi_class">
-            <param argument="multi_class" type="select" label="Multi class" help="">
+            <param argument="multi_class" type="select" label="Multi class">
+                <option value="auto" selected="true">auto: selects ‘ovr’ if the data is binary and otherwise selects ‘multinomial’</option>
                 <option value="ovr">ovr: a binary problem is fit for each label</option>
                 <option value="multinomial">multinomial: the multinomial loss fit across the entire probability distribution, even when the data is binary</option>
-                <option value="auto">auto: selects ‘ovr’ if the data is binary and otherwise selects ‘multinomial’</option>
             </param>
         </xml>
         <xml name="penalty">
-            <param argument="penalty" type="select" label="Norm used in the penalization" help="">
+            <param argument="penalty" type="select" label="Norm used in the penalization">
+                <option value="l2" selected="true">l2</option>
                 <option value="l1">l1</option>
-                <option value="l2">l2</option>
-                <option value="customized">customized</option>
-            </param>
-        </xml>
-        <xml name="custom_penalty">
-            <param argument="pen" type="text" value="" label="Norm used in the penalization" help="">
-                <expand macro="sanitize_query" />
+                <yield/>
             </param>
         </xml>
         <xml name="random_state">
-            <param argument="random_state" type="integer" value="" optional="true"
-                label="The seed of the pseudo random number generator to use when shuffling the data" help=""/>
+            <param argument="random_state" type="integer" value="" optional="true" label="The seed of the pseudo random number generator to use when shuffling the data"/>
         </xml>
     </macros>
     <expand macro="bio_tools"/>
-    <expand macro="requirements"/>
+    <expand macro="requirements">
+        <requirement type="package" version="1.5.1">scikit-learn</requirement>
+    </expand>
     <expand macro="version_command"/>
     <command detect_errors="exit_code"><![CDATA[
 @CMD@
       ]]></command>
     <configfiles>
         <configfile name="script_file"><![CDATA[
-@CMD_imports@
-@CMD_read_inputs@
+@CMD_IMPORTS@
+@CMD_READ_INPUTS@
 
-#if $method.method == "pp.calculate_qc_metrics"
+#if str($method.method) == 'pp.calculate_qc_metrics':
 sc.pp.calculate_qc_metrics(
     adata=adata,
     expr_type='$method.expr_type',
     var_type='$method.var_type',
-    #if $method.qc_vars
+    #if str($method.qc_vars) != '':
         #set $qc_vars = [str(x.strip()) for x in str($method.qc_vars).split(',')]
     qc_vars=$qc_vars,
     #end if
-    #if $method.percent_top
+    #if str($method.percent_top) != '':
         #set $percent_top = [int(x.strip()) for x in str($method.percent_top).split(',')]
-        percent_top=$percent_top,
+    percent_top=$percent_top,
     #end if
+    #if str($method.layer) != '':
+    layer='$method.layer',
+    #end if
+    use_raw=$method.use_raw,
+    log1p=$method.log1p,
     inplace=True)
 
-#else if $method.method == "tl.score_genes"
+#else if str($method.method) == 'pp.neighbors':
+sc.pp.neighbors(
+    adata=adata,
+    n_neighbors=$method.n_neighbors,
+    #if str($method.n_pcs) != '':
+    n_pcs=$method.n_pcs,
+    #end if
+    #if str($method.use_rep) != '':
+    use_rep='$method.use_rep',
+    #end if
+    knn=$method.knn,
+    method='$method.pp_neighbors_method',
+    metric='$method.metric',
+    random_state=$method.random_state,
+    #if str($method.key_added) != '':
+    key_added='$method.key_added',
+    #end if
+    copy=False)
+
+#else if str($method.method) == 'tl.score_genes':
 sc.tl.score_genes(
     adata=adata,
     #set $gene_list = [str(x.strip()) for x in str($method.gene_list).split(',')]
     gene_list=$gene_list,
     ctrl_size=$method.ctrl_size,
-    score_name='$method.score_name',
-    #if $method.gene_pool
-        #set $gene_pool = [str(x.strip()) for x in $method.gene_pool.split(',')]
+    #if str($method.gene_pool) != '':
+        #set $gene_pool = [str(x.strip()) for x in str($method.gene_pool).split(',')]
     gene_pool=$gene_pool,
     #end if
-    @CMD_score_genes_inputs@)
+    score_name='$method.score_name',
+    @CMD_PARAMS_SCORE_GENES@)
 
-#else if $method.method == "tl.score_genes_cell_cycle"
-    #if str($method.s_genes.format) == 'file'
+#else if str($method.method) == 'tl.score_genes_cell_cycle':
+    #if str($method.s_genes.format) == 'file':
 with open('$method.s_genes.file', 'r') as s_genes_f:
     s_genes = [str(x.strip()) for x in s_genes_f.readlines()]
 print(s_genes)
     #end if
 
-    #if str($method.g2m_genes.format) == 'file'
+    #if str($method.g2m_genes.format) == 'file':
 with open('$method.g2m_genes.file', 'r') as g2m_genes_f:
     g2m_genes = [str(x.strip()) for x in g2m_genes_f.readlines()]
 print(g2m_genes)
@@ -104,155 +123,182 @@ print(g2m_genes)
 
 sc.tl.score_genes_cell_cycle(
     adata=adata,
-    #if str($method.s_genes.format) == 'text'
-        #set $s_genes = [str(x.strip()) for x in $method.s_genes.text.split(',')]
+    #if str($method.s_genes.format) == 'text':
+        #set $s_genes = [str(x.strip()) for x in str($method.s_genes.text).split(',')]
     s_genes=$s_genes,
-    #else if str($method.s_genes.format) == 'file'
+    #else if str($method.s_genes.format) == 'file':
     s_genes=s_genes,
     #end if
-    #if str($method.g2m_genes.format) == 'text'
-        #set $g2m_genes = [str(x.strip()) for x in $method.g2m_genes.text.split(',')]
+    #if str($method.g2m_genes.format) == 'text':
+        #set $g2m_genes = [str(x.strip()) for x in str($method.g2m_genes.text).split(',')]
     g2m_genes=$g2m_genes,
-    #else if str($method.g2m_genes.format) == 'file'
+    #else if str($method.g2m_genes.format) == 'file':
     g2m_genes=g2m_genes,
     #end if
-    @CMD_score_genes_inputs@)
-
-#else if $method.method == 'pp.neighbors'
-sc.pp.neighbors(
-    adata=adata,
-    n_neighbors=$method.n_neighbors,
-    #if str($method.n_pcs) != ''
-    n_pcs=$method.n_pcs,
-    #end if
-    #if $method.use_rep
-    use_rep='$method.use_rep',
-    #end if
-    knn=$method.knn,
-    random_state=$method.random_state,
-    method='$method.pp_neighbors_method',
-    metric='$method.metric',
-    copy=False)
+    @CMD_PARAMS_SCORE_GENES@)
 
-#else if $method.method == 'tl.rank_genes_groups'
+#else if str($method.method) == 'tl.rank_genes_groups':
 sc.tl.rank_genes_groups(
     adata=adata,
+    #if str($method.groupby) != '':
     groupby='$method.groupby',
-    #if $method.groups
+    #end if
+    use_raw=$method.use_raw,
+    #if str($method.groups) != '':
     #set $group=[x.strip() for x in str($method.groups).split(',')]
-    groups=$group,
+    groups='$group',
+    #end if
+    #if str($method.layer) != '':
+    layer='$method.layer',
     #end if
-    #if $method.ref.rest == 'rest'
+    #if str($method.ref.rest) == 'rest':
     reference='$method.ref.rest',
     #else
     reference='$method.ref.reference',
     #end if
+    #if str($method.n_genes) != '':
     n_genes=$method.n_genes,
+    #end if
     method='$method.tl_rank_genes_groups_method.method',
-    #if $method.tl_rank_genes_groups_method.method != 'logreg'
+    #if str($method.tl_rank_genes_groups_method.method) != 'logreg':
     corr_method='$method.tl_rank_genes_groups_method.corr_method',
-    #else
+    #end if
+    #if str($method.tl_rank_genes_groups_method.method) == 'wilcoxon':
+    tie_correct=$method.tl_rank_genes_groups_method.tie_correct,
+    #end if
+    #if str($method.tl_rank_genes_groups_method.method) == 'logreg':
     solver='$method.tl_rank_genes_groups_method.solver.solver',
-        #if $method.tl_rank_genes_groups_method.solver.solver == 'newton-cg'
-    penalty='l2',
+        #if str($method.tl_rank_genes_groups_method.solver.solver) == 'lbfgs':
+    penalty='$method.tl_rank_genes_groups_method.solver.penalty',
     fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
     max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
     multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
-        #else if $method.tl_rank_genes_groups_method.solver.solver == 'lbfgs'
-    penalty='l2',
+        #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'newton-cg':
+    penalty='$method.tl_rank_genes_groups_method.solver.penalty',
     fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
     max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
     multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
-        #else if $method.tl_rank_genes_groups_method.solver.solver == 'liblinear'
-            #if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l1'
+        #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'liblinear':
+            #if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'l1':
     penalty='l1',
-            #else if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l2'
+            #else:
     penalty='l2',
     dual=$method.tl_rank_genes_groups_method.solver.penalty.dual,
-            #else
-    penalty='$method.tl_rank_genes_groups_method.solver.penalty.pen',
             #end if
     fit_intercept=$method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept,
-            #if $method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept == 'True'
+            #if str($method.tl_rank_genes_groups_method.solver.intercept_scaling.fit_intercept) == 'True':
     intercept_scaling=$method.tl_rank_genes_groups_method.solver.intercept_scaling.intercept_scaling,
             #end if
-            #if str($method.tl_rank_genes_groups_method.solver.random_state) != ''
+            #if str($method.tl_rank_genes_groups_method.solver.random_state) != '':
     random_state=$method.tl_rank_genes_groups_method.solver.random_state,
             #end if
-        #else if $method.tl_rank_genes_groups_method.solver.solver == 'sag'
-    penalty='l2',
+        #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'sag':
+    penalty='$method.tl_rank_genes_groups_method.solver.penalty.penalty',
     fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
-            #if str($method.tl_rank_genes_groups_method.solver.random_state) != ''
+            #if str($method.tl_rank_genes_groups_method.solver.random_state) != '':
     random_state=$method.tl_rank_genes_groups_method.solver.random_state,
             #end if
     max_iter=$method.tl_rank_genes_groups_method.solver.max_iter,
-    multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
-        #else if $method.tl_rank_genes_groups_method.solver.solver == 'saga'
-            #if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l1'
+    multi_class=$method.tl_rank_genes_groups_method.solver.multi_class,
+        #else if str($method.tl_rank_genes_groups_method.solver.solver) == 'saga':
+            #if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'l1':
     penalty='l1',
-            #else if $method.tl_rank_genes_groups_method.solver.penalty.penalty == 'l2'
+            #else if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'l2':
     penalty='l2',
-            #else
-    penalty='$method.tl_rank_genes_groups_method.solver.penalty.pen',
+            #else if str($method.tl_rank_genes_groups_method.solver.penalty.penalty) == 'elasticnet':
+    penalty='elasticnet',
+            #else:
+    penalty='None',
             #end if
     fit_intercept=$method.tl_rank_genes_groups_method.solver.fit_intercept,
-    multi_class='$method.tl_rank_genes_groups_method.solver.multi_class',
+    multi_class=$method.tl_rank_genes_groups_method.solver.multi_class,
         #end if
     tol=$method.tl_rank_genes_groups_method.tol,
     C=$method.tl_rank_genes_groups_method.c,
     #end if
-    use_raw=$method.use_raw)
+    #if str($method.key_added) != '':
+    key_added='$method.key_added',
+    #end if
+    copy=False)
 
-#else if $method.method == "tl.marker_gene_overlap"
+#else if str($method.method) == "tl.marker_gene_overlap":
 reference_markers = {}
 #for $i, $s in enumerate($method.reference_markers)
     #set $list=[x.strip() for x in str($s.values).split(',')]
 reference_markers['$s.key'] = $list
 #end for
 
-sc.tl.marker_gene_overlap(
+# Temporary fix for the issue with "inplace=True" for Pandas dataframes.
+# see here: https://github.com/scverse/scanpy/blob/b6193502e11b84fc1b4a011ee9cf08a19da22ebf/src/scanpy/tools/_marker_gene_overlap.py#L167
+marker_overlap_result = sc.tl.marker_gene_overlap(
+                            adata,
+                            reference_markers,
+                            #if str($method.key) != '':
+                            key='$method.key',
+                            #end if
+                            method='$method.overlap.method',
+                            #if str($method.overlap.method) == 'overlap_count' and str($method.overlap.normalize) != 'None':
+                            normalize='$method.overlap.normalize',
+                            #end if
+                            #if str($method.top_n_markers) != '':
+                            top_n_markers=$method.top_n_markers,
+                            #end if
+                            #if str($method.adj_pval_threshold) != '':
+                            adj_pval_threshold=$method.adj_pval_threshold,
+                            #end if
+                            #if $method.key_added:
+                            key_added='$method.key_added',
+                            #end if
+                            inplace=False)
+
+adata.uns['marker_gene_overlap'] = marker_overlap_result
+
+#else if str($method.method) == "pp.log1p":
+sc.pp.log1p(
     adata,
-    reference_markers,
-    #if $method.key
-    key='$method.key',
+    #if str($method.base) != '':
+    base=$method.base,
     #end if
-    method='$method.overlap.method',
-    #if $method.overlap.method == 'overlap_count' and str($method.overlap.normalize) != 'None'
-    normalize='$method.overlap.normalize',
+    #if str($method.layer) != '':
+    layer='$method.layer',
     #end if
-    #if str($method.top_n_markers) != ''
-    top_n_markers=$method.top_n_markers,
+    #if str($method.obsm) != '':
+    obsm='$method.obsm',
     #end if
-    #if str($method.adj_pval_threshold) != ''
-    adj_pval_threshold=$method.adj_pval_threshold,
-    #end if
-    #if $method.key_added
-    key_added='$method.key_added',
-    #end if
-    inplace=True)
-
-#else if $method.method == "pp.log1p"
-sc.pp.log1p(
-    adata,
     copy=False)
 
-#else if $method.method == "pp.scale"
+#else if str($method.method) == "pp.scale":
 sc.pp.scale(
     adata,
     zero_center=$method.zero_center,
-    #if str($method.max_value) != ''
+    #if str($method.max_value) != '':
     max_value=$method.max_value,
     #end if
+    #if str($method.layer) != '':
+    layer='$method.layer',
+    #end if
+    #if str($method.obsm) != '':
+    obsm='$method.obsm',
+    #end if
+    #if str($method.mask_obs) != '':
+    mask_obs='$method.mask_obs',
+    #end if
     copy=False)
 
-#else if $method.method == "pp.sqrt"
+#else if str($method.method) == "pp.sqrt":
+
+print("stats before sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
+
 sc.pp.sqrt(
     adata,
     copy=False)
 #end if
 
-@CMD_anndata_write_outputs@
-]]></configfile>
+print("stats after sqrt:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
+
+@CMD_ANNDATA_WRITE_OUTPUTS@
+        ]]>
+        </configfile>
     </configfiles>
     <inputs>
         <expand macro="inputs_anndata"/>
@@ -263,66 +309,66 @@ sc.pp.sqrt(
                 <option value="tl.score_genes">Score a set of genes, using 'tl.score_genes'</option>
                 <option value="tl.score_genes_cell_cycle">Score cell cycle genes, using 'tl.score_genes_cell_cycle'</option>
                 <option value="tl.rank_genes_groups">Rank genes for characterizing groups, using 'tl.rank_genes_groups'</option>
-                <!--<option value="tl.marker_gene_overlap">Calculate an overlap score between data-deriven marker genes and provided markers, using 'tl.marker_gene_overlap'</option>-->
+                <option value="tl.marker_gene_overlap">Calculate an overlap score between data-deriven marker genes and provided markers, using 'tl.marker_gene_overlap'</option>
                 <option value="pp.log1p">Logarithmize the data matrix, using 'pp.log1p'</option>
                 <option value="pp.scale">Scale data to unit variance and zero mean, using 'pp.scale'</option>
                 <option value="pp.sqrt">Square root the data matrix, using 'pp.sqrt'</option>
             </param>
             <when value="pp.calculate_qc_metrics">
                 <param argument="expr_type" type="text" value="counts" label="Name of kind of values in X">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="var_type" type="text" value="genes" label="The kind of thing the variables are">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
-                <param argument="qc_vars" type="text" value="" label="Keys for boolean columns of '.var' which identify variables you could want to control for" help="Keys separated by a comma">
-                    <expand macro="sanitize_query" />
+                <param argument="qc_vars" type="text" optional="true" value="" label="Keys for boolean columns of '.var' which identify variables you could want to control for" help="Keys separated by a comma">
+                    <expand macro="sanitize_query"/>
                 </param>
-                <param argument="percent_top" type="text" value="" label="Proportions of top genes to cover" 
+                <param argument="percent_top" type="text" value="" optional="true" label="Proportions of top genes to cover"
                     help=" Values (integers) are considered 1-indexed, '50' finds cumulative proportion to the 50th most expressed genes. Values separated by a comma. If empty don't calculate">
-                    <expand macro="sanitize_vectors" />
+                    <expand macro="sanitize_vectors"/>
                 </param>
+                <expand macro="param_layer"/>
+                <expand macro="param_use_raw"/>
+                <param argument="log1p" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Compute log1p transformed annotations"/>
             </when>
             <when value="pp.neighbors">
                 <param argument="n_neighbors" type="integer" min="0" value="15" label="The size of local neighborhood (in terms of number of neighboring data points) used for manifold approximation" help="Larger values result in more global views of the manifold, while smaller values result in more local data being preserved. In general values should be in the range 2 to 100. If 'knn' is 'True', number of nearest neighbors to be searched. If 'knn' is 'False', a Gaussian kernel width is set to the distance of the 'n_neighbors' neighbor."/>
-                <param argument="n_pcs" type="integer" min="0" value="" optional="true" label="Number of PCs to use" help=""/>
-                <param argument="use_rep" type="text" value="" optional="true" label="Indicated representation to use" help="If not set, the representation is chosen automatically: for n_vars below 50, X is used, otherwise X_pca (uns) is used. If X_pca is not present, it's computed with default parameter">
-                    <expand macro="sanitize_query" />
-                </param>
+                <param argument="n_pcs" type="integer" min="0" value="" optional="true" label="Number of PCs to use"/>
+                <expand macro="param_use_rep"/>
                 <param argument="knn" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Use a hard threshold to restrict the number of neighbors to n_neighbors?" help="If true, it considers a knn graph. Otherwise, it uses a Gaussian Kernel to assign low weights to neighbors more distant than the 'n_neighbors' nearest neighbor."/>
-                <param argument="random_state" type="integer" value="0" label="Numpy random seed" help=""/>
-                <param name="pp_neighbors_method" argument="method" type="select" label="Method for computing connectivities" help="">
-                    <option value="umap">umap (McInnes et al, 2018)</option>
+                <param name="pp_neighbors_method" argument="method" type="select" label="Method for computing connectivities">
+                    <option value="umap" selected="true">umap (McInnes et al, 2018)</option>
                     <option value="gauss">gauss: Gauss kernel following (Coifman et al 2005) with adaptive width (Haghverdi et al 2016)</option>
                 </param>
-                <param argument="metric" type="select" label="Distance metric" help="">
+                <param argument="metric" type="select" label="Distance metric">
                     <expand macro="distance_metric_options"/>
                 </param>
+                <param argument="random_state" type="integer" value="0" label="Numpy random seed"/>
+                <param argument="key_added" type="text" value="" optional="true" label="Key to store neighbors, distances and connectivities" help="If specified, the neighbors data is added to .uns[key_added], distances are stored in .obsp[key_added+'_distances'] and connectivities in .obsp[key_added+'_connectivities']"/>
             </when>
             <when value="tl.score_genes">
-                <param argument="gene_list" type="text" value="" label="The list of gene names used for score calculation" help="Genes separated by a comma">
-                    <expand macro="sanitize_query" />
+                <param argument="gene_list" type="text" value="" optional="false" label="The list of gene names used for score calculation" help="Genes separated by a comma">
+                    <expand macro="sanitize_query"/>
                 </param>
-                <param argument="ctrl_size" type="integer" value="50" label="Number of reference genes to be sampled"
-                    help="If 'len(gene_list)' is not too low, you can set 'ctrl_size=len(gene_list)'."/>
-                <param argument="gene_pool" type="text" value="" optional="true" label="Genes for sampling the reference set"
-                       help="Default is all genes. Genes separated by a comma">
-                    <expand macro="sanitize_query" />
+                <param argument="ctrl_size" type="integer" value="50" label="Number of reference genes to be sampled" help="If 'len(gene_list)' is not too low, you can set 'ctrl_size=len(gene_list)'."/>
+                <param argument="gene_pool" type="text" value="" optional="true" label="Genes for sampling the reference set" help="Default is all genes. Genes separated by a comma">
+                    <expand macro="sanitize_query"/>
                 </param>
-                <expand macro="score_genes_params"/>
-                <param argument="score_name" type="text" value="score" label="Name of the field to be added in '.obs'" help="">
-                    <expand macro="sanitize_query" />
+                <param argument="score_name" type="text" value="score" label="Name of the field to be added in '.obs'">
+                    <expand macro="sanitize_query"/>
                 </param>
+                <expand macro="params_score_genes"/>
             </when>
             <when value="tl.score_genes_cell_cycle">
                 <conditional name='s_genes'>
                     <param name="format" type="select" label="Format for the list of genes associated with S phase">
-                        <option value="file">File</option>
                         <option value="text" selected="true">Text</option>
+                        <option value="file">File</option>
                     </param>
                     <when value="text">
                         <param name="text" type="text" value="" label="List of genes associated with S phase" help="Genes separated by a comma">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                     </when>
                     <when value="file">
@@ -331,41 +377,44 @@ sc.pp.sqrt(
                 </conditional>
                 <conditional name='g2m_genes'>
                     <param name="format" type="select" label="Format for the list of genes associated with G2M phase">
-                        <option value="file">File</option>
                         <option value="text" selected="true">Text</option>
+                        <option value="file">File</option>
                     </param>
                     <when value="text">
                         <param name="text" type="text" value="" label="List of genes associated with G2M phase" help="Genes separated by a comma">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                     </when>
                     <when value="file">
                         <param name="file" type="data" format="txt" label="File with the list of genes associated with G2M phase" help="One gene per line"/>
                     </when>
                 </conditional>
-                <expand macro="score_genes_params"/>
+                <expand macro="params_score_genes"/>
             </when>
             <when value="tl.rank_genes_groups">
-                <param argument="groupby" type="text" value="" label="The key of the observations grouping to consider" help="">
-                    <expand macro="sanitize_query" />
+                <param argument="groupby" type="text" value="" label="The key of the observations grouping to consider">
+                    <expand macro="sanitize_query"/>
                 </param>
                 <expand macro="param_use_raw"/>
                 <param argument="groups" type="text" value="" label="Subset of groups to which comparison shall be restricted" help="e.g. ['g1', 'g2', 'g3']. If not passed, a ranking will be generated for all groups.">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="layer" type="text" value="" label="Key from adata.layers whose value will be used to perform tests on">
+                    <expand macro="sanitize_query"/>
                 </param>
                 <conditional name="ref">
                     <param name="rest" type="select" label="Comparison">
-                        <option value="rest">Compare each group to the union of the rest of the group</option>
+                        <option value="rest" selected="true">Compare each group to the union of the rest of the group</option>
                         <option value="group_id">Compare with respect to a specific group</option>
                     </param>
                     <when value="rest"/>
                     <when value="group_id">
                         <param argument="reference" type="text" value="" label="Group identifier with respect to which compare">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                     </when>
                 </conditional>
-                <param argument="n_genes" type="integer" min="0" value="100" label="The number of genes that appear in the returned tables" help=""/>
+                <param argument="n_genes" type="integer" min="0" value="" optional="true" label="The number of genes that appear in the returned tables" help="Defaults to all genes"/>
                 <conditional name="tl_rank_genes_groups_method">
                     <param argument="method" type="select" label="Method">
                         <option value="t-test" selected="true">t-test</option>
@@ -378,6 +427,7 @@ sc.pp.sqrt(
                     </when>
                     <when value="wilcoxon">
                         <expand macro="corr_method"/>
+                        <param argument="tie_correct" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use tie correction for 'wilcoxon' scores"/>
                     </when>
                     <when value="t-test_overestim_var">
                         <expand macro="corr_method"/>
@@ -385,18 +435,20 @@ sc.pp.sqrt(
                     <when value="logreg">
                         <conditional name="solver">
                             <param argument="solver" type="select" label="Algorithm to use in the optimization problem" help="For small datasets, ‘liblinear’ is a good choice, whereas ‘sag’ and ‘saga’ are faster for large ones. For multiclass problems, only ‘newton-cg’, ‘sag’, ‘saga’ and ‘lbfgs’ handle multinomial loss; ‘liblinear’ is limited to one-versus-rest schemes. ‘newton-cg’, ‘lbfgs’ and ‘sag’ only handle L2 penalty, whereas ‘liblinear’ and ‘saga’ handle L1 penalty.">
+                                <option value="lbfgs" selected="true">lbfgs</option>
                                 <option value="newton-cg">newton-cg</option>
-                                <option value="lbfgs">lbfgs</option>
                                 <option value="liblinear">liblinear</option>
                                 <option value="sag">sag</option>
                                 <option value="saga">saga</option>
                             </param>
-                            <when value="newton-cg">
+                            <when value="lbfgs">
+                                <param name="penalty" type="boolean" truevalue="l2" falsevalue="None" checked="true" label="use l2 penalty?"/>
                                 <expand macro="fit_intercept"/>
                                 <expand macro="max_iter"/>
                                 <expand macro="multi_class"/>
-                            </when>
-                            <when value="lbfgs">
+                            </when>                            
+                            <when value="newton-cg">
+                                <param name="penalty" type="boolean" truevalue="l2" falsevalue="None" checked="true" label="use l2 penalty?"/>
                                 <expand macro="fit_intercept"/>
                                 <expand macro="max_iter"/>
                                 <expand macro="multi_class"/>
@@ -409,26 +461,21 @@ sc.pp.sqrt(
                                         <param argument="dual" type="boolean" truevalue="True" falsevalue="False" checked="false"
                                             label="Dual (not primal) formulation?" help="Prefer primal when n_samples > n_features"/>
                                     </when>
-                                    <when value="customized">
-                                        <expand macro="custom_penalty"/>
-                                    </when>
                                 </conditional>
                                 <conditional name="intercept_scaling">
-                                    <param argument="fit_intercept" type="select"
-                                        label="Should a constant (a.k.a. bias or intercept) be added to the decision function?" help="">
-                                        <option value="True">Yes</option>
+                                    <param argument="fit_intercept" type="select" label="Should a constant (a.k.a. bias or intercept) be added to the decision function?">
+                                        <option value="True" selected="true">Yes</option>
                                         <option value="False">No</option>
                                     </param>
                                     <when value="True">
-                                        <param argument="intercept_scaling" type="float" value="1.0"
-                                            label="Intercept scaling"
-                                            help="x becomes [x, self.intercept_scaling], i.e. a 'synthetic' feature with constant value equal to intercept_scaling is appended to the instance vector. The intercept becomes intercept_scaling * synthetic_feature_weight."/>
+                                        <param argument="intercept_scaling" type="float" value="1.0" label="Intercept scaling" help="x becomes [x, self.intercept_scaling], i.e. a 'synthetic' feature with constant value equal to intercept_scaling is appended to the instance vector. The intercept becomes intercept_scaling * synthetic_feature_weight."/>
                                     </when>
                                     <when value="False"/>
                                 </conditional>
                                 <expand macro="random_state"/>
                             </when>
                             <when value="sag">
+                                <param name="penalty" type="boolean" truevalue="l2" falsevalue="None" checked="true" label="use l2 penalty?"/>
                                 <expand macro="fit_intercept"/>
                                 <expand macro="random_state"/>
                                 <expand macro="max_iter"/>
@@ -436,39 +483,42 @@ sc.pp.sqrt(
                             </when>
                             <when value="saga">
                                 <conditional name="penalty">
-                                    <expand macro="penalty"/>
+                                    <expand macro="penalty">
+                                        <option value="elasticnet">elasticnet</option>
+                                        <option value="None">None</option>
+                                    </expand>
                                     <when value="l1"/>
                                     <when value="l2"/>
-                                    <when value="customized">
-                                        <expand macro="custom_penalty"/>
-                                    </when>
+                                    <when value="elasticnet"/>
+                                    <when value="None"/>
                                 </conditional>
                                 <expand macro="fit_intercept"/>
                                 <expand macro="multi_class"/>
                             </when>
                         </conditional>
-                        <param argument="tol" type="float" value="1e-4" label="Tolerance for stopping criteria" help=""/>
-                        <param argument="c" type="float" value="1.0" label="Inverse of regularization strength"
-                            help="It must be a positive float. Like in support vector machines, smaller values specify stronger regularization."/>
+                        <param argument="tol" type="float" value="1e-4" label="Tolerance for stopping criteria"/>
+                        <param argument="c" type="float" value="1.0" label="Inverse of regularization strength" help="It must be a positive float. Like in support vector machines, smaller values specify stronger regularization."/>
                     </when>
                 </conditional>
+                <param argument="key_added" type="text" value="" optional="true" label="The key in adata.uns information is saved to"/>
             </when>
             <!-- With inplace=True, NotImplementedError: Writing Pandas dataframes to h5ad is currently under development. Please use `inplace=False`. -->
-            <!-- <when value="tl.marker_gene_overlap">
+            <!-- Issue is fixed in the script -->
+            <when value="tl.marker_gene_overlap">
                 <repeat name="reference_markers" title="Marker genes">
-                    <param name="key" type="text" value="" label="Cell identity name" help=""/>
+                    <param name="key" type="text" value="" label="Cell identity name"/>
                     <param name="values" type="text" value="" label="List of genes" help="Comma-separated names from 'var'"/>
                 </repeat>
                 <param argument="key" type="text" value="rank_genes_groups" label="Key in adata.uns where the rank_genes_groups output is stored"/>
                 <conditional name="overlap">
                     <param argument="method" type="select" label="Method to calculate marker gene overlap">
-                        <option value="overlap_count">overlap_count: Intersection of the gene set</option>
+                        <option value="overlap_count" selected="true">overlap_count: Intersection of the gene set</option>
                         <option value="overlap_coef">overlap_coef: Overlap coefficient</option>
                         <option value="jaccard">jaccard: Jaccard index</option>
                     </param>
                     <when value="overlap_count">
                         <param argument="normalize" type="select" label="Normalization option for the marker gene overlap output">
-                            <option value="None">None</option>
+                            <option value="None" selected="true">None</option>
                             <option value="reference">reference: Normalization of the data by the total number of marker genes given in the reference annotation per group</option>
                             <option value="data">data: Normalization of the data by the total number of marker genes used for each cluster</option>
                         </param>
@@ -476,16 +526,31 @@ sc.pp.sqrt(
                     <when value="overlap_coef"/>
                     <when value="jaccard"/>
                 </conditional>
-                <param argument="top_n_markers" type="integer" optional="true" label="Number of top data-derived marker genes to use" help="By default all calculated marker genes are used. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
-                <param argument="adj_pval_threshold" type="float" optional="true" label="Significance threshold on the adjusted p-values to select marker genes" help=" This can only be used when adjusted p-values are calculated by 'tl.rank_genes_groups'. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
-                <param argument="key_added" type="text" value="marker_gene_overlap" optional="true" label="Key that will contain the marker overlap scores in 'uns'"/>
-            </when>-->
-            <when value="pp.log1p"/>
+                <param argument="top_n_markers" type="integer" optional="true" value="" label="Number of top data-derived marker genes to use" help="By default all calculated marker genes are used. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
+                <param argument="adj_pval_threshold" type="float" optional="true" value="" label="Significance threshold on the adjusted p-values to select marker genes" help=" This can only be used when adjusted p-values are calculated by 'tl.rank_genes_groups'. If adj_pval_threshold is set along with top_n_markers, then adj_pval_threshold is ignored."/>
+                <param argument="key_added" type="text" optional="true" value="" label="Key that will contain the marker overlap scores in 'uns'"/>
+            </when>
+            <when value="pp.log1p">
+                <param argument="base" type="integer" value="" optional="true" label="Base of the logarithm." help="Natural logarithm is used by default."/>
+                <param argument="layer" type="text" value="" optional="true" label="Entry of layers to transform">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="obsm" type="text" value="" optional="true" label="Entry of obsm to transform">
+                    <expand macro="sanitize_query"/>
+                </param>
+            </when>
             <when value="pp.scale">
-                <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true"
-                    label="Zero center?" help="If not, it omits zero-centering variables, which allows to handle sparse input efficiently."/>
-                <param argument="max_value" type="float" value="" optional="true" label="Maximum value"
-                    help="Clip (truncate) to this value after scaling. If not set, it does not clip."/>
+                <param argument="zero_center" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Zero center?" help="If not, it omits zero-centering variables, which allows to handle sparse input efficiently."/>
+                <param argument="max_value" type="float" value="" optional="true" label="Maximum value" help="Clip (truncate) to this value after scaling. If not set, it does not clip."/>
+                <param argument="layer" type="text" value="" label="Which element of layers to scale">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="obsm" type="text" value="" label="Which element of obsm to scale">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="mask_obs" type="text" value="" label="Restrict both the derivation of scaling parameters and the scaling itself to a certain set of observations.">
+                    <expand macro="sanitize_query"/>
+                </param>
             </when>
             <when value="pp.sqrt"/>
         </conditional>
@@ -495,15 +560,40 @@ sc.pp.sqrt(
         <expand macro="anndata_outputs"/>
     </outputs>
     <tests>
+
+        <!-- test 1 -->
         <test expect_num_outputs="2">
-            <!-- test 1 -->
-            <param name="adata" value="sparce_csr_matrix.h5ad" />
+            <param name="adata" value="sparce_csr_matrix.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.calculate_qc_metrics"/>
-                <param name="expr_type" value="counts"/>
-                <param name="var_type" value="genes"/>
                 <param name="qc_vars" value="mito,negative"/>
-                <param name="percent_top" value=""/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pp.calculate_qc_metrics"/>
+                    <has_text_matching expression="expr_type='counts'"/>
+                    <has_text_matching expression="var_type='genes'"/>
+                    <has_text_matching expression="qc_vars=\['mito', 'negative'\]"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/n_genes_by_counts,obs/log1p_n_genes_by_counts,obs/total_counts,obs/log1p_total_counts,obs/pct_counts_in_top_50_genes,obs/pct_counts_in_top_100_genes,obs/pct_counts_in_top_200_genes,obs/pct_counts_in_top_500_genes,obs/total_counts_mito,obs/log1p_total_counts_mito,obs/pct_counts_mito,obs/total_counts_negative,obs/log1p_total_counts_negative,obs/pct_counts_negative"/>
+                    <has_h5_keys keys="var/n_cells_by_counts,var/mean_counts,var/log1p_mean_counts,var/pct_dropout_by_counts,var/total_counts,var/log1p_total_counts"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 2 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="sparce_csr_matrix.h5ad"/>
+            <conditional name="method">
+                <param name="method" value="pp.calculate_qc_metrics"/>
+                <param name="qc_vars" value="mito,negative"/>
+                <param name="percent_top" value="50,100,200,300"/>
             </conditional>
             <section name="advanced_common">
                 <param name="show_log" value="true" />
@@ -514,23 +604,25 @@ sc.pp.sqrt(
                     <has_text_matching expression="expr_type='counts'" />
                     <has_text_matching expression="var_type='genes'" />
                     <has_text_matching expression="qc_vars=\['mito', 'negative'\]" />
+                    <has_text_matching expression="percent_top=\[50, 100, 200, 300\]" />
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/n_genes_by_counts,obs/log1p_n_genes_by_counts,obs/total_counts,obs/log1p_total_counts,obs/pct_counts_in_top_50_genes,obs/pct_counts_in_top_100_genes,obs/pct_counts_in_top_200_genes,obs/pct_counts_in_top_300_genes,obs/total_counts_mito,obs/log1p_total_counts_mito,obs/pct_counts_mito,obs/total_counts_negative,obs/log1p_total_counts_negative,obs/pct_counts_negative"/>
+                    <has_h5_keys keys="var/mito,var/negative,var/n_cells_by_counts,var/mean_counts,var/log1p_mean_counts,var/pct_dropout_by_counts,var/total_counts,var/log1p_total_counts"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.calculate_qc_metrics.sparce_csr_matrix.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
+        
+        <!-- test 3 -->
         <test expect_num_outputs="2">
-            <!-- test 2 -->
-            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.neighbors"/>
-                <param name="n_neighbors" value="15"/>
-                <param name="knn" value="True"/>
-                <param name="random_state" value="0"/>
-                <param name="pp_neighbors_method" value="umap"/>
-                <param name="metric" value="euclidean"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -542,24 +634,24 @@ sc.pp.sqrt(
                     <has_text_matching expression="metric='euclidean'"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size">
+            <output name="anndata_out" ftype="h5ad">
                 <assert_contents>
-                    <has_h5_keys keys="X, obs, obsm, uns, var" />
+                    <has_h5_keys keys="uns/neighbors"/>
+                    <has_h5_keys keys="obsp/connectivities,obsp/distances"/>
                 </assert_contents>
             </output>
         </test>
+
+        <!-- test 4 -->
         <test expect_num_outputs="2">
-            <!-- test 3 -->
-            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="pp.recipe_weinreb17.paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.neighbors"/>
-                <param name="n_neighbors" value="15"/>
-                <param name="knn" value="True"/>
                 <param name="pp_neighbors_method" value="gauss"/>
                 <param name="metric" value="braycurtis"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -571,40 +663,48 @@ sc.pp.sqrt(
                     <has_text_matching expression="metric='braycurtis'"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obsp/connectivities,obsp/distances"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 5 -->
         <test expect_num_outputs="2">
-            <!-- test 4 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.score_genes"/>
                 <param name="gene_list" value="Gata2, Fog1"/>
                 <param name="ctrl_size" value="2"/>
                 <param name="n_bins" value="2"/>
                 <param name="random_state" value="2"/>
-                <param name="use_raw" value="False"/>
-                <param name="score_name" value="score"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
-                    <has_text_matching expression="sc.tl.score_genes" />
-                    <has_text_matching expression="gene_list=\['Gata2', 'Fog1'\]" />
-                    <has_text_matching expression="ctrl_size=2" />
-                    <has_text_matching expression="score_name='score'" />
-                    <has_text_matching expression="n_bins=2" />
-                    <has_text_matching expression="random_state=2" />
-                    <has_text_matching expression="use_raw=False" />
-                    <has_text_matching expression="copy=False" />
+                    <has_text_matching expression="sc.tl.score_genes"/>
+                    <has_text_matching expression="gene_list=\['Gata2', 'Fog1'\]"/>
+                    <has_text_matching expression="ctrl_size=2"/>
+                    <has_text_matching expression="score_name='score'"/>
+                    <has_text_matching expression="n_bins=2"/>
+                    <has_text_matching expression="random_state=2"/>
+                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="copy=False"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/score"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.score_genes.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
+
+        <!-- test 6 -->
         <test expect_num_outputs="2">
-            <!-- test 5 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.score_genes_cell_cycle"/>
                 <conditional name='s_genes'>
@@ -617,10 +717,9 @@ sc.pp.sqrt(
                 </conditional>
                 <param name="n_bins" value="2"/>
                 <param name="random_state" value="1"/>
-                <param name="use_raw" value="False"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -632,26 +731,26 @@ sc.pp.sqrt(
                     <has_text_matching expression="use_raw=False"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.score_genes_cell_cycle.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/S_score,obs/G2M_score,obs/phase"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 7 -->
         <test expect_num_outputs="2">
-            <!-- test 6 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.rank_genes_groups"/>
                 <param name="groupby" value="cell_type"/>
-                <param name="use_raw" value="False"/>
-                <conditional name="ref">
-                    <param name="rest" value="rest"/>
-                </conditional>
                 <param name="n_genes" value="100"/>
                 <conditional name="tl_rank_genes_groups_method">
                     <param name="method" value="t-test_overestim_var"/>
-                    <param name="corr_method" value="benjamini-hochberg"/>
                 </conditional>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -664,43 +763,36 @@ sc.pp.sqrt(
                     <has_text_matching expression="corr_method='benjamini-hochberg'"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.rank_genes_groups.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/rank_genes_groups"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 8 -->
         <test expect_num_outputs="2">
-            <!-- test 7 -->
-            <param name="adata" value="pbmc68k_reduced.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.rank_genes_groups"/>
-                <param name="groupby" value="louvain"/>
-                <param name="use_raw" value="True"/>
-                <conditional name="ref">
-                    <param name="rest" value="rest"/>
-                </conditional>
+                <param name="groupby" value="cell_type"/>
                 <param name="n_genes" value="100"/>
                 <conditional name="tl_rank_genes_groups_method">
                     <param name="method" value="logreg"/>
-                    <conditional name="solver">
-                        <param name="solver" value="newton-cg"/>
-                        <param name="fit_intercept" value="True"/>
-                        <param name="max_iter" value="100"/>
-                        <param name="multi_class" value="auto"/>
-                    </conditional>
-                    <param name="tol" value="1e-4"/>
-                    <param name="c" value="1.0"/>
                 </conditional>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.tl.rank_genes_groups"/>
-                    <has_text_matching expression="groupby='louvain'"/>
-                    <has_text_matching expression="use_raw=True"/>
+                    <has_text_matching expression="groupby='cell_type'"/>
+                    <has_text_matching expression="use_raw=False"/>
                     <has_text_matching expression="reference='rest'"/>
                     <has_text_matching expression="n_genes=100"/>
                     <has_text_matching expression="method='logreg'"/>
-                    <has_text_matching expression="solver='newton-cg'"/>
+                    <has_text_matching expression="solver='lbfgs'"/>
                     <has_text_matching expression="penalty='l2'"/>
                     <has_text_matching expression="fit_intercept=True"/>
                     <has_text_matching expression="max_iter=100"/>
@@ -709,22 +801,19 @@ sc.pp.sqrt(
                     <has_text_matching expression="C=1.0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.15">
+            <output name="anndata_out" ftype="h5ad">
                 <assert_contents>
-                    <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" />
+                    <has_h5_keys keys="uns/rank_genes_groups"/>
                 </assert_contents>
             </output>
         </test>
+
+        <!-- test 9 -->
         <test expect_num_outputs="2">
-            <!-- test 8 -->
-            <param name="adata" value="pbmc68k_reduced.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.rank_genes_groups"/>
-                <param name="groupby" value="louvain"/>
-                <param name="use_raw" value="True"/>
-                <conditional name="ref">
-                    <param name="rest" value="rest"/>
-                </conditional>
+                <param name="groupby" value="cell_type"/>
                 <param name="n_genes" value="100"/>
                 <conditional name="tl_rank_genes_groups_method">
                     <param name="method" value="logreg"/>
@@ -732,26 +821,19 @@ sc.pp.sqrt(
                         <param name="solver" value="liblinear"/>
                         <conditional name="penalty">
                             <param name="penalty" value="l2"/>
-                            <param name="dual" value="False"/>
-                            <conditional name="intercept_scaling">
-                                <param name="fit_intercept" value="True"/>
-                                <param name="intercept_scaling" value="1.0" />
-                            </conditional>
                             <param name="random_state" value="1"/>
                         </conditional>
                     </conditional>
-                    <param name="tol" value="1e-4"/>
-                    <param name="c" value="1.0"/>
                 </conditional>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.tl.rank_genes_groups"/>
-                    <has_text_matching expression="groupby='louvain'"/>
-                    <has_text_matching expression="use_raw=True"/>
+                    <has_text_matching expression="groupby='cell_type'"/>
+                    <has_text_matching expression="use_raw=False"/>
                     <has_text_matching expression="reference='rest'"/>
                     <has_text_matching expression="n_genes=100"/>
                     <has_text_matching expression="method='logreg'"/>
@@ -764,66 +846,78 @@ sc.pp.sqrt(
                     <has_text_matching expression="C=1.0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="tl.rank_genes_groups.liblinear.krumsiek11.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.15">
+            <output name="anndata_out" ftype="h5ad">
                 <assert_contents>
-                    <has_h5_keys keys="X, obs, obsm, raw/X, raw/var, uns, var" />
+                    <has_h5_keys keys="uns/rank_genes_groups"/>
                 </assert_contents>
             </output>
-        </test>
-        <!-- test expect_num_outputs="2">
-            < test 9  tl.marker_gene_overlap function was commented because inpace=True does not work>
-            <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" />
+        </test> 
+
+        <!-- test 10 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad"/>
             <conditional name="method">
                 <param name="method" value="tl.marker_gene_overlap"/>
                 <repeat name="reference_markers">
                     <param name="key" value="CD4 T cells"/>
-                    <param name="value" value="IL7R"/>
+                    <param name="values" value="IL7R"/>
                 </repeat>
                 <repeat name="reference_markers">
                     <param name="key" value="CD14+ Monocytes"/>
-                    <param name="value" value="CD14,LYZ"/>
+                    <param name="values" value="CD14,LYZ"/>
                 </repeat>
                 <repeat name="reference_markers">
                     <param name="key" value="B cells"/>
-                    <param name="value" value="MS4A1"/>
+                    <param name="values" value="MS4A1"/>
                 </repeat>
-                <conditional name="overlap">
-                    <param name="method" value="overlap_count"/>
-                    <param name="normalize" value="None"/>
-                </conditional>
             </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
             <assert_stdout>
-                <has_text_matching expression="tl.marker_gene_overlap"/>
-                <has_text_matching expression="key='rank_genes_groups'"/>
-                <has_text_matching expression="method='overlap_count'"/>
+                <has_text_matching expression="marker_gene_overlap"/>
             </assert_stdout>
-            <output name="anndata_out" file="tl.marker_gene_overlap.pbmc68k_reduced.h5ad" ftype="h5ad" compare="sim_size"/>
-        </test> -->
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.tl.marker_gene_overlap"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/rank_genes_groups"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 11 -->
         <test expect_num_outputs="2">
-            <!-- test 10 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.log1p"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.log1p"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.log1p.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/log1p"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 12 -->
         <test expect_num_outputs="2">
-            <!-- test 11 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.scale"/>
-                <param name="zero_center" value="true"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -831,18 +925,21 @@ sc.pp.sqrt(
                     <has_text_matching expression="zero_center=True"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.scale.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
-        </test>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="var/mean,var/std"/>
+                </assert_contents>
+            </output>        </test>
+
+        <!-- test 13 -->
         <test expect_num_outputs="2">
-            <!-- test 12 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.scale"/>
-                <param name="zero_center" value="true"/>
                 <param name="max_value" value="10"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -851,54 +948,41 @@ sc.pp.sqrt(
                     <has_text_matching expression="max_value=10.0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.scale_max_value.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="var/mean,var/std"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 14 -->
         <test expect_num_outputs="2">
-            <!-- test 13 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="random-randint.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.sqrt"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.sqrt"/>
+                    <has_text_matching expression="stats before sqrt: min= 0.0 max= 999.0 mean= 499.83777"/>
+                    <has_text_matching expression="stats after sqrt: min= 0.0 max= 31.606962 mean= 21.079018"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.sqrt.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
-        </test>
-        <test expect_num_outputs="2">
-            <!-- test 13 -->
-            <param name="adata" value="sparce_csr_matrix.h5ad" />
-            <conditional name="method">
-                <param name="method" value="pp.calculate_qc_metrics"/>
-                <param name="expr_type" value="counts"/>
-                <param name="var_type" value="genes"/>
-                <param name="qc_vars" value="mito,negative"/>
-                <param name="percent_top" value="50,100,200,300"/>
-            </conditional>
-            <section name="advanced_common">
-                <param name="show_log" value="true" />
-            </section>
-            <output name="hidden_output">
+            <output name="anndata_out" ftype="h5ad">
                 <assert_contents>
-                    <has_text_matching expression="sc.pp.calculate_qc_metrics" />
-                    <has_text_matching expression="expr_type='counts'" />
-                    <has_text_matching expression="var_type='genes'" />
-                    <has_text_matching expression="qc_vars=\['mito', 'negative'\]" />
-                    <has_text_matching expression="percent_top=\[50, 100, 200, 300\]" />
+                    <has_h5_keys keys="obs/index"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.calculate_qc_metrics.sparce_csr_matrix.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
     </tests>
     <help><![CDATA[
 Calculate quality control metrics., using `pp.calculate_qc_metrics`
 ===================================================================
 
-Calculates a number of qc metrics for an AnnData object, largely based on calculateQCMetrics from scater. 
+Calculates a number of qc metrics for an AnnData object, largely based on calculateQCMetrics from scater.
 Currently is most efficient on a sparse CSR or dense matrix.
 
 It updates the observation level metrics with
@@ -983,6 +1067,8 @@ Calculate an overlap score between data-deriven marker genes and provided marker
 
 Marker gene overlap scores can be quoted as overlap counts, overlap coefficients, or jaccard indices. The method returns a pandas dataframe which can be used to annotate clusters based on marker gene overlaps.
 
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/generated/scanpy.tl.marker_gene_overlap.html>`__
 
 Logarithmize the data matrix (`pp.log1p`)
 =========================================
diff --git a/tools/scanpy/macros.xml b/tools/scanpy/macros.xml
index 4dc0fa43b0b..137bbce8a90 100644
--- a/tools/scanpy/macros.xml
+++ b/tools/scanpy/macros.xml
@@ -1,17 +1,15 @@
 <macros>
-    <token name="@TOOL_VERSION@">1.9.6</token>
-    <token name="@VERSION_SUFFIX@">4</token>
-    <token name="@profile@">21.09</token>
+    <token name="@TOOL_VERSION@">1.10.2</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@PROFILE@">21.09</token>
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">scanpy</requirement>
-            <requirement type="package" version="3.0.6">loompy</requirement>
-            <requirement type="package" version="0.10.1">leidenalg</requirement>
-            <requirement type="package" version="0.8.1">louvain</requirement>
-            <requirement type="package" version="1.5.3">pandas</requirement>
-            <requirement type="package" version="3.7">matplotlib</requirement>
-            <requirement type="package" version="0.12.2">seaborn</requirement>
-            <requirement type="package" version="3.0.0">magic-impute</requirement>
+            <requirement type="package" version="0.10.3">anndata</requirement>
+            <requirement type="package" version="1.26.4">numpy</requirement>
+            <requirement type="package" version="2.2.2">pandas</requirement>
+            <requirement type="package" version="1.14.1">scipy</requirement>
+            <requirement type="package" version="0.14.2">statsmodels</requirement>           
             <yield />
         </requirements>
     </xml>
@@ -22,7 +20,7 @@
     </xml>
     <xml name="creators">
         <creator>
-            <organization name="European Galaxy Team" url="https://galaxyproject.org/eu/" />
+            <organization name="European Galaxy Team" url="https://galaxyproject.org/eu/"/>
         </creator>
     </xml>
     <xml name="citations">
@@ -31,28 +29,13 @@
             <citation type="doi">10.1093/gigascience/giaa102</citation>
         </citations>
     </xml>
-    <xml name="version_command">
-        <version_command><![CDATA[python -c "import scanpy as sc;print('scanpy version: %s' % sc.__version__)"]]></version_command>
-    </xml>
-    <token name="@CMD@"><![CDATA[
-cp '$adata' 'anndata.h5ad' &&
-cat '$script_file' > '$hidden_output' &&
-python '$script_file' >> '$hidden_output' &&
-ls . >> '$hidden_output' &&
-touch 'anndata_info.txt' &&
-cat 'anndata_info.txt' @CMD_prettify_stdout@
-    ]]>
-    </token>
-    <token name="@CMD_imports@"><![CDATA[
-import scanpy as sc
-import pandas as pd
-import numpy as np
-    ]]>
-    </token>
+    
+    
+    <!-- param macros -->
     <xml name="sanitize_query" token_validinitial="string.printable">
         <sanitizer>
             <valid initial="@VALIDINITIAL@">
-                <remove value="&apos;" />
+                <remove value="&apos;"/>
             </valid>
        </sanitizer>
     </xml>
@@ -62,58 +45,55 @@ import numpy as np
                 <add value=","/>
             </valid>
         </sanitizer>
-    </xml>
+    </xml>      
     <xml name="inputs_anndata">
         <param name="adata" type="data" format="h5ad" label="Annotated data matrix"/>
     </xml>
-    <token name="@CMD_read_inputs@"><![CDATA[
-adata = sc.read_h5ad('anndata.h5ad')
-]]>
-    </token>
     <xml name="inputs_common_advanced">
         <section name="advanced_common" title="Advanced Options" expanded="false">
-            <param name="show_log" type="boolean" checked="false" label="Output Log?" />
+            <param name="show_log" type="boolean" checked="false" label="Output Log?"/>
         </section>
     </xml>
     <xml name="anndata_outputs">
-        <data name="anndata_out" format="h5ad" from_work_dir="anndata.h5ad" label="${tool.name} (${method.method}) on ${on_string}: Annotated data matrix"/>
-            <data name="hidden_output" format="txt" label="Log file" >
+        <data name="anndata_out" format="h5ad" from_work_dir="anndata.h5ad" label="${tool.name} (${method.method}) on ${on_string}: Annotated data matrix">
+            <yield />
+        </data>
+        <data name="hidden_output" format="txt" label="Log file" >
             <filter>advanced_common['show_log']</filter>
         </data>
+    </xml>    
+    <xml name="param_use_rep">
+        <param argument="use_rep" type="text" value="" optional="true" label="Use the indicated representation" help="If not set, the representation is chosen automatically: for n_vars below 50, X is used, otherwise X_pca (uns) is used. If X_pca is not present, it's computed with default parameter">
+                <expand macro="sanitize_query"/>
+        </param>
     </xml>
-    <token name="@CMD_anndata_write_outputs@"><![CDATA[
-adata.write_h5ad('anndata.h5ad')
-with open('anndata_info.txt','w', encoding='utf-8') as ainfo:
-    print(adata, file=ainfo)
-]]>
-    </token>
-    <token name="@CMD_prettify_stdout@"><![CDATA[ | sed -r '1 s|AnnData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g"  | sed -r 's|^\s*(.*):\s(.*)|[\1]\n-    \2|g' | sed 's|, |\n-    |g'
-    ]]></token>
     <xml name="svd_solver">
-        <param name="svd_solver" type="select" label="SVD solver to use" help="">
+        <param name="svd_solver" type="select" optional="true" label="SVD solver to use">
             <option value="auto">Automatically chosen depending on the size of the problem</option>
             <option value="arpack">ARPACK wrapper in SciPy</option>
             <option value="randomized">Randomized algorithm due to Halko (2009)</option>
+            <option value="lobpcg">An alternative SciPy solver. Not available with dask arrays.</option>
+            <option value="tsqr">Only available with dask arrays. “tsqr” algorithm from Benson et. al. (2013).</option>
         </param>
     </xml>
     <xml name="pca_random_state">
-        <param name="random_state" type="integer" value="0" label="Initial states for the optimization" help=""/>
+        <param name="random_state" type="integer" value="0" label="Initial states for the optimization"/>
     </xml>
     <xml name="param_plot_format">
         <param name="format" type="select" label="Format for saving figures">
-            <option value="png">png</option>
+            <option value="png" selected="true">png</option>
             <option value="pdf">pdf</option>
             <option value="svg">svg</option>
         </param>
     </xml>
     <xml name="numeric_distance_metric_options">
+    	<option value="euclidean" selected="true">euclidean</option>
         <option value="braycurtis">braycurtis</option>
         <option value="canberra">canberra</option>
         <option value="chebyshev">chebyshev</option>
         <option value="cityblock">cityblock</option>
         <option value="correlation">correlation</option>
         <option value="cosine">cosine</option>
-        <option value="euclidean" selected="true">euclidean</option>
         <option value="mahalanobis">mahalanobis</option>
         <option value="matching">matching</option>
         <option value="minkowski">minkowski</option>
@@ -393,141 +373,6 @@ with open('anndata_info.txt','w', encoding='utf-8') as ainfo:
         <option value="nipy_spectral">nipy_spectral (Miscellaneous)</option>
         <option value="gist_ncar">gist_ncar (Miscellaneous)</option>
     </xml>
-    <xml name="param_groupby">
-        <param argument="groupby" type="text" value="" optional="true" label="The key of the observation grouping to consider" help="If it is given, the plot is ordered by the respective group. It is expected that to be a categorical. If it is not a categorical observation, it would be subdivided into 'num_categories'.">
-            <expand macro="sanitize_query" />
-        </param>
-    </xml>
-    <xml name="param_use_raw">
-        <param argument="use_raw" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use 'raw' attribute of input if present" help=""/>
-    </xml>
-    <xml name="param_log">
-        <param argument="log" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Use the log of the values?"/>
-    </xml>
-    <xml name="pl_figsize">
-        <conditional name="figsize">
-            <param name="test" type="select" label="Custom figure size" >
-                <option value="yes">Yes</option>
-                <option value="no" selected="true">No: the figure width is set based on the number of variable names and the height is set to 10.</option>
-            </param>
-            <when value="yes">
-                <param argument="width" type="integer" min="0" value="10" label="Figure width" help=""/>
-                <param argument="height" type="integer" min="0" value="10" label="Figure height" help=""/>
-            </when>
-            <when value="no"/>
-        </conditional>
-    </xml>
-    <token name="@CMD_params_figsize@"><![CDATA[
-
-    ]]></token>
-    <xml name="pl_var_names">
-        <conditional name="var_names">
-            <param name="type" type="select" label="Variables to plot (columns of the heatmaps)" >
-                <option value="all">All variables in 'adata.var_names'</option>
-                <option value="custom">Subset of variables in 'adata.var_names'</option>
-                <option value="customfile">Subset of variables as a tabular file</option>
-            </param>
-            <when value="all"/>
-            <when value="custom">
-                <param argument="var_names" type="text" value="" label="List of variables to plot" help="They should be a valid subset of 'adata.var_names', and separated by comma">
-                    <expand macro="sanitize_query" />
-                </param>
-            </when>
-            <when value="customfile">
-                <param argument="var_names" type="data" format="tabular" label="List of variables to plot" help="This should be a tsv where row = group (e.g. celltypes) and columns = variables."></param>
-                <param name="header" type="select" label="Header in the list of markers?">
-                    <option value="included">Header incldued</option>
-                    <option value="not_included">Header not included</option>
-                </param>
-            </when>
-        </conditional>
-    </xml>
-    <xml name="param_num_categories">
-        <param argument="num_categories" type="integer" min="0" value="7" label="Number of categories" help="It is only used if groupby observation is not categorical. This value determines the number of groups into which the groupby observation should be subdivided."/>
-    </xml>
-    <xml name="param_dendrogram">
-        <param argument="dendrogram" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Compute and plot a dendrogram?" help="groupby categories are reordered accoring to the dendrogram order. If groups of var_names are set and those groups correspond to the groupby categories, those groups are also reordered. The ‘person’ method is used to compute the pairwise correlation between categories using all var_names in raw if use_raw is None, otherwise all adata.var_names are used. The linkage method used is complete."/>
-    </xml>
-    <xml name="pl_var_group_positions">
-        <repeat name="var_group_positions" title="Group of variables to highlight" help="This will draw a 'bracket' on top of the plot between the given start and end positions. If a label is given, it will be added on top of the bracket. ">
-            <param name="start" type="integer" min="0" value="" label="Start" help=""/>
-            <param name="end" type="integer" min="0" value="" label="End" help=""/>
-            <param argument="label" type="text" value="" label="Label" help="">
-                <expand macro="sanitize_query" />
-            </param>
-        </repeat>
-    </xml>
-    <xml name="param_var_group_rotation">
-        <param argument="var_group_rotation" type="float" value="" optional="true" label="Label rotation degrees" help="By default, labels larger than 4 characters are rotated 90 degrees"/>
-    </xml>
-    <xml name="param_layer">
-        <param argument="layer" type="text" value="" label="Name of the AnnData object layer that wants to be plotted" help="By default 'adata.raw.X' is plotted. If 'use_raw=False' is set, then 'adata.X' is plotted. If layer is set to a valid layer name, then the layer is plotted. layer takes precedence over 'use_raw'.">
-            <expand macro="sanitize_query" />
-        </param>
-    </xml>
-    <token name="@CMD_param_plot_inputs@"><![CDATA[
-    adata,
-    save='.$format',
-    show=False,
-    ]]></token>
-    <xml name="params_inputs">
-        <expand macro="pl_var_names"/>
-        <expand macro="param_groupby"/>
-        <expand macro="param_num_categories"/>
-    </xml>
-    <token name="@CMD_var_names_header_check@"><![CDATA[
-header='infer'
-#if $method.var_names.type == 'customfile' and $method.var_names.header == 'not_included' :
-header=None
-#end if
-    ]]></token>
-    <token name="@CMD_params_inputs@"><![CDATA[
-    #if $method.var_names.type == 'custom'
-    #set $var_names = ([x.strip() for x in str($method.var_names.var_names).split(',')])
-    var_names=$var_names,
-    #else if $method.var_names.type == 'customfile'
-    var_names={key: [v for v in list(value.values()) if pd.notna(v)] for key, value in pd.read_csv('$var_names', sep='\t', index_col=0).to_dict(orient='index').items()},
-    #else
-    var_names=adata.var_names,
-    #end if
-    #if $method.groupby
-    groupby='$method.groupby',
-    #end if
-    num_categories=$method.num_categories,
-    ]]></token>
-    <xml name="params_plots">
-        <expand macro="param_log"/>
-        <expand macro="param_use_raw"/>
-        <expand macro="param_dendrogram"/>
-        <expand macro="pl_var_group_positions"/>
-        <expand macro="param_var_group_rotation"/>
-        <expand macro="pl_figsize"/>
-        <expand macro="param_layer"/>
-    </xml>
-    <token name="@CMD_params_plots@"><![CDATA[
-    log=$method.log,
-    use_raw=$method.use_raw,
-    dendrogram=$method.dendrogram,
-    #if len($method.var_group_positions) > 0:
-        #set $var_group_positions=[]
-        #set $var_group_labels=[]
-        #for $i, $s in enumerate($method.var_group_positions)
-            #silent $var_group_positions.append((int($s.start), int($s.end)))
-            #silent $var_group_labels.append(str($s.label))
-        #end for
-    var_group_positions=$var_group_positions,
-    var_group_labels=$var_group_labels,
-    #end if
-    #if str($method.var_group_rotation) != ''
-        var_group_rotation=$method.var_group_rotation,
-    #end if
-    #if $method.figsize.test == 'yes'
-        figsize=($method.figsize.width, $method.figsize.height),
-    #end if
-    #if $method.layer
-        layer='$method.layer',
-    #end if
-    ]]></token>
     <xml name="matplotlib_color">
         <option value="AliceBlue">AliceBlue</option>
         <option value="AntiqueWhite">AntiqueWhite</option>
@@ -679,166 +524,491 @@ header=None
         <option value="YellowGreen">YellowGreen</option>
     </xml>
     <xml name="param_matplotlib_pyplot_edgecolors">
-        <param argument="edgecolors" type="select" optional="true" label="Edge color of the marker" help="">
+        <param argument="edgecolors" type="select" optional="true" label="Edge color of the marker">
             <option value="face">The edge color will always be the same as the face color</option>
             <expand macro="matplotlib_color"/>
         </param>
     </xml>
-    <xml name="param_alpha">
-        <param argument="alpha" type="float" value="" min="0" max="1" optional="true" label="Alpha blending value" help="Between 0 (transparent) and 1 (opaque)"/>
+    <xml name="param_swap_axes">
+        <param argument="swap_axes" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Swap axes?" help="By default, the x axis contains 'var_names' (e.g. genes) and the y axis the 'groupby' categories (if any). By setting 'swap_axes' then x are the 'groupby' categories and y the 'var_names'."/>
     </xml>
-    <xml name="param_vmin">
-        <param argument="vmin" type="float" value="" optional="true" label="Minimum value to normalize luminance data" help="If not set, it is inferred from the data and other keyword arguments"/>
+    <xml name="param_cmap">
+        <param argument="cmap" type="select" optional="true" label="Colors to use for plotting categorical annotation groups">
+            <expand macro="matplotlib_pyplot_colormap"/>
+        </param>
     </xml>
-    <xml name="param_vmax">
-        <param argument="vmax" type="float" value="" optional="true" label="Maximum value to normalize luminance data" help="If not set, it is inferred from the data and other keyword arguments"/>
+    <xml name="param_sort_order">
+        <param argument="sort_order" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Sort order?" help="For continuous annotations used as color parameter, plot data points with higher values on top of others."/>
     </xml>
-    <xml name="section_matplotlib_pyplot_scatter">
-        <section name="matplotlib_pyplot_scatter" title="Parameters for matplotlib.pyplot.scatter">
-            <!--<param argument="marker" type="select" label="Marker style" help="">
-                <option value="o">o</option>
-                <option value="v">v</option>
-                <option value="^">^</option>
-                <option value="8">8</option>
-                <option value="s">s</option>
-                <option value="p">p</option>
-                <option value="*">*</option>
-                <option value="h">h</option>
-                <option value="H">H</option>
-                <option value="D">D</option>
-                <option value="d">d</option>
-                <option value="P">P</option>
-                <option value="X">X</option>
-            </param>-->
-            <expand macro="param_alpha"/>
-            <expand macro="param_vmin"/>
-            <expand macro="param_vmax"/>
-            <param argument="linewidths" type="float" value="0" label="Linewidth of the marker edges" help=""/>
-            <expand macro="param_matplotlib_pyplot_edgecolors"/>
-        </section>
+    <xml name="param_arrows">
+        <param argument="arrows" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Show arrows?" help="It requires to run 'tl.rna_velocity' before."/>
     </xml>
-    <token name="@CMD_params_matplotlib_pyplot_scatter@"><![CDATA[
-    #if str($method.matplotlib_pyplot_scatter.vmin) != ''
-    vmin=$method.matplotlib_pyplot_scatter.vmin,
-    #end if
-    #if str($method.matplotlib_pyplot_scatter.vmax) != ''
-    vmax=$method.matplotlib_pyplot_scatter.vmax,
-    #end if
-    #if str($method.matplotlib_pyplot_scatter.alpha) != ''
-    alpha=$method.matplotlib_pyplot_scatter.alpha,
-    #end if
-    lw=$method.matplotlib_pyplot_scatter.linewidths,
-    #if $method.matplotlib_pyplot_scatter.edgecolors
-    ec='$method.matplotlib_pyplot_scatter.edgecolors'
-    #end if
-    ]]></token>
-    <xml name="conditional_stripplot">
-        <conditional name="stripplot">
-            <param argument="stripplot" type="select" label="Add a stripplot on top of the violin plot" help="">
-                <option value="True">Yes</option>
-                <option value="False">No</option>
-            </param>
-            <when value="True">
-                <conditional name="jitter">
-                    <param argument="jitter" type="select" label="Add a jitter to the stripplot" help="">
-                        <option value="True">Yes</option>
-                        <option value="False">No</option>
-                    </param>
-                    <when value="True">
-                        <param argument="size" type="float" min="0" value="1" label="Size of the jitter points" help=""/>
-                    </when>
-                    <when value="False"/>
-                </conditional>
-            </when>
-            <when value="False"/>
-        </conditional>
+    <!-- param macros -->
+
+
+    
+    <!-- command macros -->
+    <xml name="version_command">
+        <version_command><![CDATA[python -c "import scanpy as sc;print('scanpy version: %s' % sc.__version__)"]]></version_command>
     </xml>
-    <token name="@CMD_conditional_stripplot@"><![CDATA[
-    stripplot=$method.violin_plot.stripplot.stripplot,
-#if $method.violin_plot.stripplot.stripplot == "True"
-    jitter=$method.violin_plot.stripplot.jitter.jitter,
-    #if $method.violin_plot.stripplot.jitter.jitter == "True"
-    size=$method.violin_plot.stripplot.jitter.size,
-    #end if
+    <token name="@CMD_PRETTIFY_STDOUT@"><![CDATA[
+| sed -r '1 s|AnnData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g"  | sed -r 's|^\s*(.*):\s(.*)|[\1]\n-    \2|g' | sed 's|, |\n-    |g'
+    ]]>
+    </token>
+    <token name="@CMD_READ_INPUTS@"><![CDATA[
+adata = sc.read_h5ad('anndata.h5ad')
+    ]]>
+    </token>
+    <!-- ln -s doesn't work here because the output is overwritten to the same file -->
+    <token name="@CMD@"><![CDATA[
+cp '$adata' 'anndata.h5ad' &&
+cat '$script_file' > '$hidden_output' &&
+python '$script_file' >> '$hidden_output' &&
+ls . >> '$hidden_output' &&
+touch 'anndata_info.txt' &&
+cat 'anndata_info.txt' @CMD_PRETTIFY_STDOUT@
+    ]]>
+    </token>
+    <token name="@CMD_IMPORTS@"><![CDATA[
+import scanpy as sc
+import pandas as pd
+import numpy as np
+    ]]>
+    </token>
+    <token name="@CMD_ANNDATA_WRITE_OUTPUTS@"><![CDATA[
+adata.write_h5ad('anndata.h5ad', compression='gzip')
+with open('anndata_info.txt','w', encoding='utf-8') as ainfo:
+    print(adata, file=ainfo)
+    ]]>
+    </token>
+    <token name="@CMD_PARAM_PLOT_INPUTS@"><![CDATA[
+    adata,
+    save='.$format',
+    ]]>
+    </token>
+    <token name="@CMD_SHOW_NONE@"><![CDATA[
+        show=None
+        ]]>
+    </token>
+    <token name="@CMD_VAR_NAMES_HEADER_CHECK@"><![CDATA[
+header='infer'
+#if $method.var_names.type == 'customfile' and $method.var_names.header == 'not_included' :
+header=None
 #end if
-    ]]></token>
-    <xml name="param_scale">
-        <param argument="scale" type="select" label="Method used to scale the width of each violin">
-            <option value="area">area: each violin will have the same area</option>
-            <option value="count">count: the width of the violins will be scaled by the number of observations in that bin</option>
-            <option value="width" selected="true">width: each violin will have the same width</option>
-        </param>
-    </xml>
-    <token name="@CMD_params_violin_plots@"><![CDATA[
-    @CMD_conditional_stripplot@
+    ]]>
+    </token>
+    <token name="@CMD_PARAMS_VIOLIN_PLOTS@"><![CDATA[
+    @CMD_CONDITIONAL_STRIPPLOT@
     multi_panel=$method.violin_plot.multi_panel.multi_panel,
 #if $method.multi_panel.violin_plot.multi_panel == "True" and str($method.violin_plot.multi_panel.width) != '' and str($method.violin_plot.multi_panel.height) != ''
     figsize=($method.violin_plot.multi_panel.width, $method.violin_plot.multi_panel.height)
 #end if
-    scale='$method.violin_plot.scale',
-    ]]></token>
-    <xml name="seaborn_violinplot">
-        <section name="seaborn_violinplot" title="Parameters for seaborn.violinplot">
-            <param argument="bw" type="select" label="Name of a reference rule when computing the kernel bandwidth">
-                <option value="scott">scott</option>
-                <option value="silverman">silverman</option>
-            </param>
-            <param argument="orient" type="select" optional="true" label="Orientation of the plot">
-                <option value="v">vertical</option>
-                <option value="h">horizontal</option>
-            </param>
-            <param argument="linewidth" type="float" value="0" label="Width of the gray lines that frame the plot elements" help=""/>
-            <param argument="color" type="select" optional="true" label="Color for all of the elements" help="">
-                <expand macro="matplotlib_color"/>
-            </param>
-            <param argument="saturation" type="float" value="0.75" min="0" max="1" label="Proportion of the original saturation to draw colors at" help=""/>
-        </section>
+    density_norm='$method.violin_plot.density_norm',
+    ]]>
+    </token>
+    <!-- command macros -->
+
+
+
+    <!-- param and cmd macros -->
+    <xml name="param_standard_scale">
+        <param argument="standard_scale" type="select" label="Standardize a dimension between 0 and 1" help="Each variable or observation is subtracted by the minimum and divided each by its maximum.">
+            <option value="None" selected="true">No standardization</option>
+            <option value="var">Standardization on variable</option>
+            <option value="obs">Standardization on observation</option>
+        </param>
     </xml>
-    <token name="@CMD_params_seaborn_violinplot@"><![CDATA[
-    bw='$method.seaborn_violinplot.bw',
-#if $method.seaborn_violinplot.orient
-    orient='$method.seaborn_violinplot.orient',
-#end if
-    linewidth=$method.seaborn_violinplot.linewidth,
-    #if $method.seaborn_violinplot.color
-    color='$method.seaborn_violinplot.color',
+    <token name="@CMD_STANDARD_SCALE@"><![CDATA[
+    #if str($method.standard_scale) != 'None':
+    standard_scale='$method.standard_scale',
     #end if
-    saturation=$method.seaborn_violinplot.saturation
-    ]]></token>
-    <xml name="param_color">
-        <param argument="color" type="text" value="" optional="true" label="Keys for annotations of observations/cells or variables/genes" help="One or a list of comma-separated index or key from either '.obs' or '.var'">
-            <expand macro="sanitize_query" />
+    ]]>
+    </token>
+
+    <xml name="param_layer" token_optional="true" token_label="If provided, use adata.layers[layer] for expression values instead of adata.X." token_help="">
+        <param argument="layer" type="text" value="" optional="@OPTIONAL@" label="@LABEL@">
+            <expand macro="sanitize_query"/>
         </param>
     </xml>
-    <token name="@CMD_param_color@"><![CDATA[
-#if $method.color
-    #set $color = ([x.strip() for x in str($method.color).split(',')])
-    color=$color,
-#end if
-    ]]></token>
-    <xml name="param_groups">
-        <param argument="groups" type="text" value="" optional="true" label="Categorical observation annotations to plot" help="Comma-separated">
-            <expand macro="sanitize_query" />
+    <token name="@CMD_PARAM_LAYER@"><![CDATA[
+    #if str($method.layer) != '':
+    layer='$method.layer',
+    #end if
+    ]]>
+    </token>
+
+    <xml name="param_neighbors_key">
+        <param argument="neighbors_key" type="text" value="" label="Key to look for neighbors settings and connectivities" help="If not specified, looks .uns[‘neighbors’] for neighbors settings and .obsp[‘connectivities’] for connectivities (default storage places for pp.neighbors).">
+            <expand macro="sanitize_query"/>
         </param>
     </xml>
-    <token name="@CMD_params_groups@"><![CDATA[
-#if $method.groups
-    #set $groups=([x.strip() for x in str($method.groups).split(',')])
-    groups=$groups,
-#end if
-    ]]></token>
-    <xml name="pl_components">
+    <token name="@CMD_PARAM_NEIGHBORS_KEY@"><![CDATA[
+    #if $method.neighbors_key != ''
+    neighbors_key='$method.neighbors_key',
+    #end if
+    ]]>
+    </token>
+
+    <xml name="pl_var_names">
+        <conditional name="var_names">
+            <param name="type" type="select" label="Variables to plot (columns of the heatmaps)" >
+                <option value="all" selected="true">All variables in 'adata.var_names'</option>
+                <option value="custom">Subset of variables in 'adata.var_names'</option>
+                <option value="customfile">Subset of variables as a tabular file</option>
+            </param>
+            <when value="all"/>
+            <when value="custom">
+                <param argument="var_names" type="text" value="" label="List of variables to plot" help="They should be a valid subset of 'adata.var_names', and separated by comma">
+                    <expand macro="sanitize_query"/>
+                </param>
+            </when>
+            <when value="customfile">
+                <param argument="var_names" type="data" format="tabular" label="List of variables to plot" help="This should be a tsv where row = group (e.g. celltypes) and columns = variables."></param>
+                <param name="header" type="boolean" truevalue="included" falsevalue="not_included" checked="true" label="Header is included in the list of markers?"/>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="param_groupby">
+        <param argument="groupby" type="text" value="" optional="true" label="The key of the observation grouping to consider" help="If it is given, the plot is ordered by the respective group. It is expected that to be a categorical. If it is not a categorical observation, it would be subdivided into 'num_categories'.">
+            <expand macro="sanitize_query"/>
+        </param>
+    </xml>
+    <xml name="param_num_categories">
+        <param argument="num_categories" type="integer" min="0" value="7" label="Number of categories" help="It is only used if groupby observation is not categorical. This value determines the number of groups into which the groupby observation should be subdivided."/>
+    </xml>
+
+    <xml name="params_inputs">
+        <expand macro="pl_var_names"/>
+        <expand macro="param_groupby"/>
+        <expand macro="param_num_categories"/>
+    </xml>
+    <token name="@CMD_PARAMS_INPUTS@"><![CDATA[
+    #if str($method.var_names.type) == 'custom':
+    #set $var_names = ([x.strip() for x in str($method.var_names.var_names).split(',')])
+    var_names=$var_names,
+    #else if str($method.var_names.type) == 'customfile':
+    var_names={key: [v for v in list(value.values()) if pd.notna(v)] for key, value in pd.read_csv('$var_names', sep='\t', index_col=0, header=header).to_dict(orient='index').items()},
+    #else
+    var_names=adata.var_names,
+    #end if
+    #if str($method.groupby) != '':
+    groupby='$method.groupby',
+    #end if
+    num_categories=$method.num_categories,
+    ]]>
+    </token>
+
+    <xml name="pl_figsize">
+        <conditional name="figsize">
+            <param name="custom" type="select" label="Custom figure size" >
+                <option value="no" selected="true">No: the figure width is set based on the number of variable names and the height is set to 10.</option>
+                <option value="yes">Yes</option>
+            </param>
+            <when value="yes">
+                <param argument="width" type="integer" min="0" value="10" label="Figure width"/>
+                <param argument="height" type="integer" min="0" value="10" label="Figure height"/>
+            </when>
+            <when value="no"/>
+        </conditional>
+    </xml>
+    <token name="@CMD_PARAMS_FIGSIZE@"><![CDATA[
+    #if $method.figsize.custom == 'yes':
+        figsize=($method.figsize.width, $method.figsize.height),
+    #end if
+    ]]>
+    </token>
+
+    <xml name="param_log" token_checked="false">
+        <param argument="log" type="boolean" truevalue="True" falsevalue="False" checked="@CHECKED@" label="Use the log of the values?"/>
+    </xml>
+    <xml name="param_use_raw" token_falsevalue="False">
+        <param argument="use_raw" type="boolean" truevalue="True" falsevalue="@FALSEVALUE@" checked="false" label="Use 'raw' attribute of input if present"/>
+    </xml>
+    <xml name="param_dendrogram">
+        <param argument="dendrogram" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Compute and plot a dendrogram?" help="groupby categories are reordered accoring to the dendrogram order. If groups of var_names are set and those groups correspond to the groupby categories, those groups are also reordered. The ‘person’ method is used to compute the pairwise correlation between categories using all var_names in raw if use_raw is None, otherwise all adata.var_names are used. The linkage method used is complete."/>
+    </xml>
+    <xml name="pl_var_group_positions">
+        <repeat name="var_group_positions" title="Group of variables to highlight" help="This will draw a 'bracket' on top of the plot between the given start and end positions. If a label is given, it will be added on top of the bracket. ">
+            <param name="start" type="integer" min="0" value="" label="Start"/>
+            <param name="end" type="integer" min="0" value="" label="End"/>
+            <param argument="label" type="text" value="" label="Label">
+                <expand macro="sanitize_query"/>
+            </param>
+        </repeat>
+    </xml>
+    <xml name="param_var_group_rotation">
+        <param argument="var_group_rotation" type="float" value="" optional="true" label="Label rotation degrees" help="By default, labels larger than 4 characters are rotated 90 degrees"/>
+    </xml>
+    <xml name="params_plots">
+        <expand macro="param_log"/>
+        <expand macro="param_use_raw" falsevalue="None"/>
+        <expand macro="param_dendrogram"/>
+        <expand macro="pl_var_group_positions"/>
+        <expand macro="param_var_group_rotation"/>
+        <expand macro="pl_figsize"/>
+        <expand macro="param_layer" optional="true" label="Name of the AnnData object layer that wants to be plotted" help="By default 'adata.raw.X' is plotted. If 'use_raw=False' is set, then 'adata.X' is plotted. If layer is set to a valid layer name, then the layer is plotted. layer takes precedence over 'use_raw'."/>
+    </xml>
+    <token name="@CMD_PARAMS_PLOTS@"><![CDATA[
+    log=$method.log,
+    use_raw=$method.use_raw,
+    dendrogram=$method.dendrogram,
+    #if len($method.var_group_positions) > 0:
+        #set $var_group_positions=[]
+        #set $var_group_labels=[]
+        #for $i, $s in enumerate($method.var_group_positions)
+            #silent $var_group_positions.append((int($s.start), int($s.end)))
+            #silent $var_group_labels.append(str($s.label))
+        #end for
+    var_group_positions=$var_group_positions,
+    var_group_labels=$var_group_labels,
+    #end if
+    #if str($method.var_group_rotation) != '':
+        var_group_rotation=$method.var_group_rotation,
+    #end if
+    @CMD_PARAMS_FIGSIZE@
+    @CMD_PARAM_LAYER@
+    ]]>
+    </token>
+
+    <xml name="param_alpha">
+        <param argument="alpha" type="float" value="" min="0" max="1" optional="true" label="Alpha blending value" help="Between 0 (transparent) and 1 (opaque)"/>
+    </xml>
+    <xml name="param_vmin" token_label="Minimum value to normalize luminance data" token_help="If not set, it is inferred from the data and other keyword arguments">
+        <param argument="vmin" type="float" value="" optional="true" label="@LABEL@" help="@HELP@"/>
+    </xml>
+    <xml name="param_vmax" token_label="Maximum value to normalize luminance data" token_help="If not set, it is inferred from the data and other keyword arguments">
+        <param argument="vmax" type="float" value="" optional="true" label="@LABEL@" help="@HELP@"/>
+    </xml>
+    <xml name="param_vcenter">
+        <param argument="vcenter" type="float" value="" optional="true" label="The value representing the center of the color scale" help="Useful for diverging colormaps."/>
+    </xml>
+    <xml name="section_matplotlib_pyplot_scatter">
+        <section name="matplotlib_pyplot_scatter" title="Parameters for matplotlib.pyplot.scatter">
+            <expand macro="param_alpha"/>
+            <expand macro="param_vmin"/>
+            <expand macro="param_vmax"/>
+            <param argument="linewidths" type="float" value="0" label="Linewidth of the marker edges"/>
+            <expand macro="param_matplotlib_pyplot_edgecolors"/>
+        </section>
+    </xml>
+    <token name="@CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@"><![CDATA[
+    #if str($method.matplotlib_pyplot_scatter.vmin) != '':
+    vmin=$method.matplotlib_pyplot_scatter.vmin,
+    #end if
+    #if str($method.matplotlib_pyplot_scatter.vmax) != '':
+    vmax=$method.matplotlib_pyplot_scatter.vmax,
+    #end if
+    #if str($method.matplotlib_pyplot_scatter.alpha) != '':
+    alpha=$method.matplotlib_pyplot_scatter.alpha,
+    #end if
+    linewidth=$method.matplotlib_pyplot_scatter.linewidths,
+    #if $method.matplotlib_pyplot_scatter.edgecolors:
+    edgecolor='$method.matplotlib_pyplot_scatter.edgecolors',
+    #end if
+    ]]>
+    </token>
+
+    <xml name="params_pl_heatmap">
+        <expand macro="param_swap_axes"/>
+        <param argument="show_gene_labels" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Show gene labels?" help="By default gene labels are shown when there are 50 or less genes. Otherwise the labels are removed."/>
+        <expand macro="param_standard_scale"/>
+        <section name="matplotlib_pyplot_imshow" title="Parameters for matplotlib.pyplot.imshow">
+            <expand macro="param_cmap"/>
+            <param name="interpolation" type="select" label="Interpolation method">
+                <option value="None" selected="true">none</option>
+                <option value="nearest">nearest</option>
+                <option value="bilinear">bilinear</option>
+                <option value="bicubic">bicubic</option>
+                <option value="spline16">spline16</option>
+                <option value="spline36">spline36</option>
+                <option value="hanning">hanning</option>
+                <option value="hamming">hamming</option>
+                <option value="hermite">hermite</option>
+                <option value="kaiser">kaiser</option>
+                <option value="quadric">quadric</option>
+                <option value="catrom">catrom</option>
+                <option value="gaussian">gaussian</option>
+                <option value="bessel">bessel</option>
+                <option value="sinc">sinc</option>
+                <option value="mitchell">mitchell</option>
+                <option value="lanczos">lanczos</option>
+            </param>
+            <expand macro="param_alpha"/>
+            <expand macro="param_vmin"/>
+            <expand macro="param_vmax"/>
+            <param name="origin" type="select" label="Place the [0,0] index of the array in the upper left or lower left corner of the axes" help=" The convention 'upper' is typically used for matrices and images.">
+                <option value="upper" selected="true">Upper</option>
+                <option value="lower">Lower</option>
+            </param>
+        </section>
+    </xml>
+    <token name="@CMD_PARAMS_PL_HEATMAP@"><![CDATA[
+    swap_axes=$method.swap_axes,
+    show_gene_labels=$method.show_gene_labels,
+    @CMD_STANDARD_SCALE@
+    #if $method.matplotlib_pyplot_imshow.cmap:
+    cmap='$method.matplotlib_pyplot_imshow.cmap',
+    #end if
+    #if str($method.matplotlib_pyplot_imshow.interpolation) != 'None':
+    interpolation='$method.matplotlib_pyplot_imshow.interpolation',
+    #end if
+    #if str($method.matplotlib_pyplot_imshow.alpha) != '':
+    alpha=$method.matplotlib_pyplot_imshow.alpha,
+    #end if
+    #if str($method.matplotlib_pyplot_imshow.vmin) != '':
+    vmin=$method.matplotlib_pyplot_imshow.vmin,
+    #end if
+    #if str($method.matplotlib_pyplot_imshow.vmax) != '':
+    vmax=$method.matplotlib_pyplot_imshow.vmax,
+    #end if
+    origin='$method.matplotlib_pyplot_imshow.origin',
+    ]]>
+    </token>
+
+    <xml name="params_pl_matrixplot">
+        <expand macro="param_swap_axes"/>
+        <section name="matplotlib_pyplot_pcolor" title="Parameters for matplotlib.pyplot.pcolor">
+            <param argument="cmap" type="select" optional="true" label="Color palette">
+                <expand macro="seaborn_color_palette_options"/>
+            </param>
+            <expand macro="param_matplotlib_pyplot_edgecolors"/>
+            <expand macro="param_alpha"/>
+            <param argument="snap" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Snap the mesh to pixel boundaries?"/>
+        </section>
+        <expand macro="param_standard_scale"/>
+        <expand macro="param_vmin" label="The value representing the lower limit of the color scale" help="Values smaller than vmin are plotted with the same color as vmin."/>
+        <expand macro="param_vmax" label="The value representing the upper limit of the color scale" help="Values larger than vmax are plotted with the same color as vmax."/>
+        <expand macro="param_vcenter"/>
+    </xml>
+    <token name="@CMD_PARAMS_PL_MATRIXPLOT@"><![CDATA[
+    swap_axes=$method.swap_axes,
+    #if $method.matplotlib_pyplot_pcolor.cmap:
+    cmap='$method.matplotlib_pyplot_pcolor.cmap',
+    #end if
+    #if $method.matplotlib_pyplot_pcolor.edgecolors:
+    edgecolor='$method.matplotlib_pyplot_pcolor.edgecolors',
+    #end if
+    #if str($method.matplotlib_pyplot_pcolor.alpha) != '':
+    alpha=$method.matplotlib_pyplot_pcolor.alpha,
+    #end if
+    snap=$method.matplotlib_pyplot_pcolor.snap,
+    #if str($method.vmin) != '':
+    vmin=$method.vmin,
+    #end if
+    #if str($method.vmax) != '':
+    vmax=$method.vmax,
+    #end if
+    #if str($method.vcenter) != '':
+    vcenter=$method.vcenter,
+    #end if
+    @CMD_STANDARD_SCALE@
+    ]]>
+    </token>
+
+    <xml name="conditional_stripplot">
+        <conditional name="stripplot">
+            <param argument="stripplot" type="select" label="Add a stripplot on top of the violin plot">
+                <option value="True" selected="true">Yes</option>
+                <option value="False">No</option>
+            </param>
+            <when value="True">
+                <conditional name="jitter">
+                    <param argument="jitter" type="select" label="Add a jitter to the stripplot">
+                        <option value="True" selected="true">Yes</option>
+                        <option value="False">No</option>
+                    </param>
+                    <when value="True">
+                        <param argument="size" type="float" min="0" value="1" label="Size of the jitter points"/>
+                    </when>
+                    <when value="False"/>
+                </conditional>
+            </when>
+            <when value="False"/>
+        </conditional>
+    </xml>
+    <token name="@CMD_CONDITIONAL_STRIPPLOT@"><![CDATA[
+    stripplot=$method.violin_plot.stripplot.stripplot,
+#if str($method.violin_plot.stripplot.stripplot) == 'True':
+    jitter=$method.violin_plot.stripplot.jitter.jitter,
+    #if str($method.violin_plot.stripplot.jitter.jitter) == 'True':
+    size=$method.violin_plot.stripplot.jitter.size,
+    #end if
+#end if
+    ]]>
+    </token>
+    
+    <xml name="params_seaborn_violinplot">
+        <section name="seaborn_violinplot" title="Parameters for seaborn.violinplot">
+            <param argument="bw_method" type="select" label="Name of a reference rule when computing the kernel bandwidth">
+                <option value="scott" selected="true">scott</option>
+                <option value="silverman">silverman</option>
+            </param>
+            <param argument="bw_adjust" type="float" value="1" label="Factor that scales the bandwidth to use more or less smoothing."/>
+            <param argument="orient" type="select" optional="true" label="Orientation of the plot">
+                <option value="v">vertical</option>
+                <option value="h">horizontal</option>
+            </param>
+            <param argument="linewidth" type="float" value="" optional="true" label="Width of the gray lines that frame the plot elements"/>
+            <param argument="color" type="select" optional="true" label="Color for all of the elements">
+                <expand macro="matplotlib_color"/>
+            </param>
+            <param argument="saturation" type="float" value="0.75" min="0" max="1" label="Proportion of the original saturation to draw colors at"/>
+        </section>
+    </xml>
+    <token name="@CMD_PARAMS_SEABORN_VIOLINPLOT@"><![CDATA[
+    bw_method='$method.seaborn_violinplot.bw_method',
+    bw_adjust=$method.seaborn_violinplot.bw_adjust,
+    #if $method.seaborn_violinplot.orient:
+    orient='$method.seaborn_violinplot.orient',
+    #end if
+    #if str($method.seaborn_violinplot.linewidth) != '':
+    linewidth=$method.seaborn_violinplot.linewidth,
+    #end if
+    #if $method.seaborn_violinplot.color:
+    color='$method.seaborn_violinplot.color',
+    #end if
+    saturation=$method.seaborn_violinplot.saturation,
+    ]]></token>
+   
+    <xml name="param_color">
+        <param argument="color" type="text" value="" optional="true" label="Keys for annotations of observations/cells or variables/genes" help="One or a list of comma-separated index or key from either '.obs' or '.var'">
+            <expand macro="sanitize_query"/>
+        </param>
+    </xml>
+    <token name="@CMD_PARAM_COLOR@"><![CDATA[
+#if str($method.color) != '':
+    #set $color = ([x.strip() for x in str($method.color).split(',')])
+    color=$color,
+#end if
+    ]]>
+    </token>
+
+    <xml name="param_groups">
+        <param argument="groups" type="text" value="" optional="true" label="Categorical observation annotations to plot" help="Comma-separated">
+            <expand macro="sanitize_query"/>
+        </param>
+    </xml>
+    <token name="@CMD_PARAM_GROUPS@"><![CDATA[
+#if str($method.groups) != '':
+    #set $groups=([x.strip() for x in str($method.groups).split(',')])
+    groups=$groups,
+#end if
+    ]]>
+    </token>
+
+
+    <xml name="param_pl_components">
         <repeat name="components" title="Component">
-            <param argument="axis1" type="text" value="1" label="X-Axis" help="">
-                <expand macro="sanitize_query" />
+            <param argument="axis1" type="text" value="1" label="X-Axis">
+                <expand macro="sanitize_query"/>
             </param>
-            <param argument="axis2" type="text" value="2" label="Y-Axis" help="">
-                <expand macro="sanitize_query" />
+            <param argument="axis2" type="text" value="2" label="Y-Axis">
+                <expand macro="sanitize_query"/>
             </param>
         </repeat>
     </xml>
-    <token name="@CMD_params_pl_components@"><![CDATA[
-#if len($method.plot.components) > 0
+    <token name="@CMD_PARAM_PL_COMPONENTS@"><![CDATA[
+#if len($method.plot.components) > 0:
     #set $components=[]
     #for $i, $s in enumerate($method.plot.components)
         #silent $components.append(str($s.axis1) + ',' + str($s.axis2))
@@ -847,23 +1017,56 @@ header=None
 #end if
     ]]>
     </token>
+    
+    <xml name="param_legend_fontsize">
+        <param argument="legend_fontsize" type="integer" optional="true" value="" label="Legend font size"/>
+    </xml>
+    <token name="@CMD_PARAM_LEGEND_FONTSIZE@"><![CDATA[
+    #if str($method.plot.legend_fontsize) != '':
+    legend_fontsize=$method.plot.legend_fontsize,
+    #end if
+    ]]>
+    </token>
+
+    <xml name="param_size">
+        <param argument="size" type="float" optional="true" value="" label="Point size"/>
+    </xml>
+    <token name="@CMD_PARAM_SIZE@"><![CDATA[
+    #if str($method.plot.size) != '':
+    size=$method.plot.size,
+    #end if
+    ]]>
+    </token>
+
+    <xml name="param_title">
+        <param argument="title" type="text" value="" optional="true" label="Title for panels" help="Titles must be separated by a comma">
+            <expand macro="sanitize_query"/>
+        </param>
+    </xml>
+    <token name="@CMD_PARAM_TITLE@"><![CDATA[
+    #if str($method.plot.title) != '':
+    title='$method.plot.title',
+    #end if
+    ]]>
+    </token>
+
     <xml name="param_projection">
-        <param argument="projection" type="select" label="Projection of plot" help="">
-            <option value="2d">2d</option>
+        <param argument="projection" type="select" label="Projection of plot">
+            <option value="2d" selected="true">2d</option>
             <option value="3d">3d</option>
         </param>
     </xml>
     <xml name="param_legend_loc">
-        <param argument="legend_loc" type="select" label="Location of legend" help="">
+        <param argument="legend_loc" type="select" label="Location of legend">
+            <yield />
             <option value="none">none</option>
-            <option value="right margin" selected="true">right margin</option>
-            <option value="on data">on data</option>
             <option value="on data export">on data export</option>
             <option value="best">best</option>
             <option value="upper right">upper right</option>
             <option value="upper left">upper left</option>
             <option value="lower left">lower left</option>
             <option value="lower right">lower right</option>
+            <option value="right">right</option>
             <option value="center left">center left</option>
             <option value="center right">center right</option>
             <option value="lower center">lower center</option>
@@ -871,120 +1074,48 @@ header=None
             <option value="center">center</option>
         </param>
     </xml>
-    <xml name="param_legend_fontsize">
-        <param argument="legend_fontsize" type="integer" optional="true" value="" label="Legend font size" help=""/>
-    </xml>
-    <token name="@CMD_param_legend_fontsize@"><![CDATA[
-    #if str($method.plot.legend_fontsize) != ''
-    legend_fontsize=$method.plot.legend_fontsize,
-    #end if
-    ]]>
-    </token>
     <xml name="param_legend_fontweight">
-        <param argument="legend_fontweight" type="select" label="Legend font weight" help="">
+        <param argument="legend_fontweight" type="select" label="Legend font weight">
+            <option value="bold" selected="true">bold</option>
+            <option value="normal">normal</option>
             <option value="light">light</option>
-            <option value="normal" selected="true">normal</option>
             <option value="medium">medium</option>
             <option value="semibold">semibold</option>
-            <option value="bold">bold</option>
             <option value="heavy">heavy</option>
             <option value="black">black</option>
         </param>
     </xml>
-    <xml name="param_palette">
-        <param argument="palette" type="select" optional="true" label="Colors to use for plotting categorical annotation groups" help="">
+    <xml name="param_color_map">
+        <param argument="color_map" type="select" optional="true" label="Color map to use for continous variables">
             <expand macro="matplotlib_pyplot_colormap"/>
         </param>
     </xml>
-    <xml name="param_color_map">
-        <param argument="color_map" type="select" optional="true" label="Color map to use for continous variables" help="">
+    <xml name="param_palette">
+        <param argument="palette" type="select" optional="true" label="Colors to use for plotting categorical annotation groups">
             <expand macro="matplotlib_pyplot_colormap"/>
         </param>
     </xml>
     <xml name="param_frameon">
-        <param argument="frameon" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Draw a frame around the scatter plot?" help=""/>
-    </xml>
-    <xml name="param_right_margin">
-        <param argument="right_margin" type="float" value="1" label="Width of the space right of each plotting panel" help=""/>
-    </xml>
-    <xml name="param_left_margin">
-        <param argument="left_margin" type="float" value="1" label="Width of the space left of each plotting panel" help=""/>
-    </xml>
-    <xml name="param_size">
-        <param argument="size" type="float" optional="true" value="" label="Point size" help=""/>
-    </xml>
-    <token name="@CMD_param_size@"><![CDATA[
-    #if str($method.plot.size) != ''
-    size=$method.plot.size,
-    #end if
-    ]]>
-    </token>
-    <xml name="param_title">
-        <param argument="title" type="text" value="" optional="true" label="Title for panels" help="Titles must be separated by a comma">
-            <expand macro="sanitize_query" />
-        </param>
-    </xml>
-    <token name="@CMD_param_title@"><![CDATA[
-    #if $method.plot.title
-    title='$method.plot.title',
-    #end if
-    ]]>
-    </token>
-    <xml name="param_sort_order">
-        <param argument="sort_order" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Sort order?" help="For continuous annotations used as color parameter, plot data points with higher values on top of others."/>
-    </xml>
-    <xml name="param_sort_order">
-        <param argument="sort_order" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Sort order?" help="For continuous annotations used as color parameter, plot data points with higher values on top of others."/>
+        <param argument="frameon" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Draw a frame around the scatter plot?"/>
     </xml>
     <xml name="param_ncols">
-        <param argument="ncols" type="integer" min="0" value="4" label="Number of panels per row" help=""/>
+        <param argument="ncols" type="integer" min="0" value="4" label="Number of panels per row"/>
     </xml>
     <xml name="param_wspace">
-        <param argument="wspace" type="float" min="0" value="0.1" label="Width of the space between multiple panels" help=""/>
+        <param argument="wspace" type="float" min="0" value="0.1" label="Width of the space between multiple panels"/>
     </xml>
     <xml name="param_hspace">
-        <param argument="hspace" type="float" min="0" value="0.25" label="Height of the space between multiple panels" help=""/>
-    </xml>
-    <xml name="pl_edges">
-        <conditional name="edges">
-            <param argument="edges" type="select" label="Show edges?">
-                <option value="True">Yes</option>
-                <option value="False" selected="true">No</option>
-            </param>
-            <when value="True">
-                <param argument="edges_width" type="float" min="0" value="0.1" label="Width of edges"/>
-                <param argument="edges_color" type="select" optional="true" label="Color of edges">
-                    <expand macro="matplotlib_color"/>
-                </param>
-            </when>
-            <when value="False"/>
-        </conditional>
+        <param argument="hspace" type="float" min="0" value="0.25" label="Height of the space between multiple panels"/>
     </xml>
-    <token name="@CMD_pl_edges@"><![CDATA[
-#if str($method.edges.edges) == 'True'
-    edges=True,
-    edges_width=$method.edges.edges_width,
-    #if $method.edges.edges_color
-    edges_color='$method.edges.edges_color',
-    #end if
-#else
-    edges=False,
-#end if
-    ]]>
-    </token>
-    <xml name="param_arrows">
-        <param argument="arrows" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Show arrows?" help="It requires to run 'tl.rna_velocity' before."/>
-    </xml>
-    <xml name="param_cmap">
-        <param argument="cmap" type="select" optional="true" label="Colors to use for plotting categorical annotation groups" help="">
-            <expand macro="matplotlib_pyplot_colormap"/>
-        </param>
-    </xml>
-    <xml name="pl_attribute_section">
+
+    <xml name="params_pl_attribute_section">
         <section name="plot" title="Plot attributes">
-            <expand macro="pl_components"/>
+            <expand macro="param_pl_components"/>
             <expand macro="param_projection"/>
-            <expand macro="param_legend_loc"/>
+            <expand macro="param_legend_loc">
+                <option value="right margin">right margin</option>
+                <option value="on data">on data</option>
+            </expand>
             <expand macro="param_legend_fontsize"/>
             <expand macro="param_legend_fontweight"/>
             <expand macro="param_size"/>
@@ -997,303 +1128,336 @@ header=None
             <expand macro="param_title"/>
         </section>
     </xml>
-    <token name="@CMD_pl_attribute_section@"><![CDATA[
+    <token name="@CMD_PARAMS_PL_ATTRIBUTE_SECTION@"><![CDATA[
+    @CMD_PARAM_PL_COMPONENTS@
     projection='$method.plot.projection',
+    #if str($method.plot.legend_loc) != '':
     legend_loc='$method.plot.legend_loc',
-    @CMD_param_legend_fontsize@
+    #end if
+    @CMD_PARAM_LEGEND_FONTSIZE@
     legend_fontweight='$method.plot.legend_fontweight',
-    @CMD_param_size@
-    #if $method.plot.color_map
+    @CMD_PARAM_SIZE@
+    #if $method.plot.color_map:
     color_map='$method.plot.color_map',
     #end if
-    #if $method.plot.palette
+    #if $method.plot.palette:
     palette='$method.plot.palette',
     #end if
     frameon=$method.plot.frameon,
     ncols=$method.plot.ncols,
     wspace=$method.plot.wspace,
     hspace=$method.plot.hspace,
-    @CMD_param_title@
+    @CMD_PARAM_TITLE@
     ]]>
     </token>
+
+    <xml name="pl_edges">
+        <conditional name="edges">
+            <param argument="edges" type="select" label="Show edges?">
+            	<option value="False" selected="true">No</option>
+                <option value="True">Yes</option>
+            </param>
+            <when value="True">
+                <param argument="edges_width" type="float" min="0" value="0.1" label="Width of edges"/>
+                <param argument="edges_color" type="select" optional="true" label="Color of edges">
+                    <expand macro="matplotlib_color"/>
+                </param>
+            </when>
+            <when value="False"/>
+        </conditional>
+    </xml>
+    <token name="@CMD_PL_EDGES@"><![CDATA[
+#if str($method.edges.edges) == 'True':
+    edges=True,
+    edges_width=$method.edges.edges_width,
+    #if $method.edges.edges_color:
+    edges_color='$method.edges.edges_color',
+    #end if
+#else
+    edges=False,
+#end if
+    ]]>
+    </token>
+
+
     <xml name="options_layout">
-        <option value="fa">fa: ForceAtlas2</option>
+    	<option value="fa" selected="true">fa: ForceAtlas2</option>
+        <option value="drl">drl: Distributed Recursive Layout, pretty fast</option>
         <option value="fr">fr: Fruchterman-Reingold</option>
         <option value="grid_fr">grid_fr: Grid Fruchterman Reingold, faster than "fr"</option>
         <option value="kk">kk: Kamadi Kawai’, slower than "fr"</option>
-        <option value="drl">drl: Distributed Recursive Layout, pretty fast</option>
+        <option value="lgl">Large Graph, very fast</option>
         <option value="rt">rt: Reingold Tilford tree layout</option>
-        <option value="eq_tree">eq_tree: Equally spaced tree</option>
+        <option value="rt_circular">rt_circular: Reingold Tilford tree circular</option>
     </xml>
     <xml name="param_layout">
-        <param argument="layout" type="select" label="Plotting layout" optional="false" help="">
+        <param argument="layout" type="select" label="Plotting layout" optional="false">
             <expand macro="options_layout"/>
         </param>
     </xml>
-    <xml name="param_root">
-        <param argument="root" type="text" value="" label="Comma-separated roots" help="If choosing a tree layout, this is the index of the root node or a list of root node indices. If this is a non-empty vector then the supplied node IDs are used as the roots of the trees (or a single tree if the graph is connected). If this is 'None' or an empty list, the root vertices are automatically calculated based on topological sorting.">
-            <expand macro="sanitize_query" />
-        </param>
-    </xml>
-    <xml name="param_random_state">
-        <param argument="random_state" type="integer" value="0" label="Random state" help="For layouts with random initialization like 'fr', change this to use different intial states for the optimization. If 'None', the initial state is not reproducible."/>
-    </xml>
-    <xml name="inputs_paga">
-        <param argument="threshold" type="float" min="0" value="0.01" label="Threshold to draw edges" help="Do not draw edges for weights below this threshold. Set to 0 if you want all edges. Discarding low-connectivity edges helps in getting a much clearer picture of the graph."/>
+    <xml name="params_pl_paga">
+        <param argument="threshold" type="float" min="0" value="" optional="true" label="Threshold to draw edges" help="Do not draw edges for weights below this threshold. Set to 0 if you want all edges. Discarding low-connectivity edges helps in getting a much clearer picture of the graph."/>
         <expand macro="param_groups"/>
         <param argument="color" type="text" value="" label="The node colors" help="Gene name or obs. annotation, and also plots the degree of the abstracted graph when passing 'degree_dashed', 'degree_solid'.">
-            <expand macro="sanitize_query" />
+            <expand macro="sanitize_query"/>
         </param>
-        <param argument="pos" type="data" format="tabular,csv,tsv" optional="true" label="Two-column tabular file storing the x and y coordinates for drawing" help=""/>
+        <param argument="pos" type="data" format="tabular,csv,tsv" optional="true" label="Two-column tabular file storing the x and y coordinates for drawing"/>
         <param argument="labels" type="text" value="" label="Comma-separated node labels" help="If none is provided, this defaults to the group labels stored in the categorical for which 'tl.paga' has been computed.">
-            <expand macro="sanitize_query" />
+            <expand macro="sanitize_query"/>
         </param>
         <expand macro="param_layout"/>
-        <param argument="init_pos" type="data" format="tabular,csv,tsv" optional="true" label="Two-column tabular file storing the x and y coordinates for initializing the layout" help=""/>
-        <expand macro="param_random_state"/>
-        <expand macro="param_root"/>
+        <param argument="init_pos" type="data" format="tabular,csv,tsv" optional="true" label="Two-column tabular file storing the x and y coordinates for initializing the layout"/>
+        <param argument="random_state" type="integer" value="0" label="For layouts with random initialization like 'fr', change this to use different intial states for the optimization. If 'None', the initial state is not reproducible."/>
+        <param argument="root" type="text" value="0" label="Comma-separated roots" help="If choosing a tree layout, this is the index of the root node or a list of root node indices. If this is a non-empty vector then the supplied node IDs are used as the roots of the trees (or a single tree if the graph is connected). If this is 'None' or an empty list, the root vertices are automatically calculated based on topological sorting.">
+            <expand macro="sanitize_query"/>
+        </param>
         <param argument="transitions" type="text" value="" label="Key corresponding to the matrix storing the arrows" help="Key for '.uns['paga']', e.g. 'transistions_confidence'">
-            <expand macro="sanitize_query" />
+            <expand macro="sanitize_query"/>
         </param>
         <param argument="solid_edges" type="text" value="connectivities" label="Key corresponding to the matrix storing the edges to be drawn solid black" help="Key for uns/paga">
-            <expand macro="sanitize_query" />
+            <expand macro="sanitize_query"/>
         </param>
         <param argument="dashed_edges" type="text" value="" optional="true" label="Key corresponding to the matrix storing the edges to be drawn dashed grey" help="Key for uns/paga. If not set, no dashed edges are drawn.">
-            <expand macro="sanitize_query" />
+            <expand macro="sanitize_query"/>
         </param>
-        <param argument="single_component" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Restrict to largest connected component?" help=""/>
-        <param argument="fontsize" type="integer" min="0" value="1" label="Font size for node labels" help=""/>
-        <param argument="node_size_scale" type="float" min="0" value="1.0" label="Size of the nodes" help=""/>
-        <param argument="node_size_power" type="float" min="0" value="0.5" label="Power with which groups sizes influence the radius of the nodes" help=""/>
-        <param argument="edge_width_scale" type="float" min="0" value="5" label="Scale for edge width" help=""/>
-        <param argument="min_edge_width" type="float" min="0" value="" optional="true" label="Min width of solid edges" help=""/>
-        <param argument="max_edge_width" type="float" min="0" value="" optional="true" label="Max width of solid and dashed edges" help=""/>
+        <param argument="single_component" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Restrict to largest connected component?"/>
+        <param argument="fontsize" type="integer" min="0" value="" optional="true" label="Font size for node labels"/>
+        <param argument="node_size_scale" type="float" min="0" value="1.0" label="Size of the nodes"/>
+        <param argument="node_size_power" type="float" min="0" value="0.5" label="Power with which groups sizes influence the radius of the nodes"/>
+        <param argument="edge_width_scale" type="float" min="0" value="1.0" label="Scale for edge width"/>
+        <param argument="min_edge_width" type="float" min="0" value="" optional="true" label="Min width of solid edges"/>
+        <param argument="max_edge_width" type="float" min="0" value="" optional="true" label="Max width of solid and dashed edges"/>
         <param argument="arrowsize" type="integer" min="0" value="30" label="Arrow size" help="For directed graphs, choose the size of the arrow head head's length and width."/>
-        <param argument="normalize_to_color" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Normalize categorical plots to color or the underlying grouping?" help=""/>
+        <param argument="normalize_to_color" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Normalize categorical plots to color or the underlying grouping?"/>
         <expand macro="param_cmap"/>
         <expand macro="param_title"/>
         <expand macro="param_frameon"/>
     </xml>
-    <token name="@CMD_params_pl_paga@"><![CDATA[
+    <token name="@CMD_PARAMS_PL_PAGA@"><![CDATA[
+        #if str($method.threshold) != '':
     threshold=$method.threshold,
-#if $method.groups
-    #set $groups=([x.strip() for x in str($method.groups).split(',')])
+        #end if
+        #if str($method.groups) != '':
+            #set $groups=([x.strip() for x in str($method.groups).split(',')])
     groups=$groups,
-#end if
-#if $method.color
-    #set $color=([x.strip() for x in str($method.color).split(',')])
+        #end if
+        #if str($method.color) != '':
+            #set $color=([x.strip() for x in str($method.color).split(',')])
     color=$color,
-#end if
-#if $method.pos
+        #end if
+        #if $method.pos:
     pos=np.fromfile($method.pos, dtype=dt),
-#end if
-#if $method.labels
-    #set $labels=([x.strip() for x in str($method.labels).split(',')])
+        #end if
+        #if str($method.labels) != '':
+            #set $labels=([x.strip() for x in str($method.labels).split(',')])
     labels=$labels,
-#end if
+        #end if
     layout='$method.layout',
-#if $method.init_pos
+        #if $method.init_pos:
     init_pos=np.fromfile($method.init_pos, dtype=dt),
-#end if
+        #end if
     random_state=$method.random_state,
-#if $method.root
-    #set $root=([int(x.strip()) for x in str($method.root).split(',')])
+        #if str($method.root) != '':
+            #set $root=([int(x.strip()) for x in str($method.root).split(',')])
     root=$root,
-#end if
-#if $method.transitions
+        #end if
+        #if str($method.transitions) != '':
     transitions='$method.transitions',
-#end if
+        #end if
     solid_edges='$method.solid_edges',
-#if $method.dashed_edges
+        #if str($method.dashed_edges) != '':
     dashed_edges='$method.dashed_edges',
-#end if
+        #end if
     single_component=$method.single_component,
     fontsize=$method.fontsize,
     node_size_scale=$method.node_size_scale,
     node_size_power=$method.node_size_power,
     edge_width_scale=$method.edge_width_scale,
-#if str($method.min_edge_width) != ''
+        #if str($method.min_edge_width) != '':
     min_edge_width=$method.min_edge_width,
-#end if
-#if str($method.max_edge_width) != ''
+        #end if
+        #if str($method.max_edge_width) != '':
     max_edge_width=$method.max_edge_width,
-#end if
+        #end if
     arrowsize=$method.arrowsize,
     normalize_to_color=$method.normalize_to_color,
-    #if $method.cmap
+    #if $method.cmap:
     cmap='$method.cmap',
     #end if
-#if $method.title
+        #if str($method.title) != '':
     title='$method.title',
-#end if
+        #end if
     frameon=$method.frameon,
     ]]>
     </token>
-    <xml name="param_swap_axes">
-        <param argument="swap_axes" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Swap axes?" help="By default, the x axis contains 'var_names' (e.g. genes) and the y axis the 'groupby' categories (if any). By setting 'swap_axes' then x are the 'groupby' categories and y the 'var_names'."/>
-    </xml>
-    <xml name="gene_symbols">
-        <param argument="gene_symbols" type="text" value="" optional="true" label="Key for field in '.var' that stores gene symbols">
-            <expand macro="sanitize_query" />
+
+    <xml name="param_gene_symbols">
+        <param argument="gene_symbols" type="text" value="" optional="true" label="Key for field in '.var' that stores gene symbols" help="By default 'var_names' refer to the index column of the '.var' DataFrame">
+            <expand macro="sanitize_query"/>
         </param>
     </xml>
-    <xml name="param_n_genes">
-        <param argument="n_genes" type="integer" min="0" value="10" label="Number of genes to show" help="It is only used if you are not specifying certain variable names"/>
-    </xml>
-    <xml name="pl_dotplot">
+    <token name="@CMD_PARAM_GENE_SYMBOLS@"><![CDATA[
+    #if str($method.gene_symbols) != '':
+    gene_symbols='$method.gene_symbols',
+    #end if
+    ]]>
+    </token>
+
+    <xml name="params_pl_dotplot">
         <param argument="color_map" type="select" optional="true" label="Color palette">
             <expand macro="matplotlib_pyplot_colormap"/>
         </param>
         <param argument="dot_max" type="float" value="" min="0" max="1" optional="true" label="Maximum dot size" help="If none, the maximum dot size is set to the maximum fraction value found (e.g. 0.6). If given, the value should be a number between 0 and 1. All fractions larger than dot_max are clipped to this value."/>
         <param argument="dot_min" type="float" value="" min="0" max="1" optional="true" label="Minimum dot size" help="If none, the minimum dot size is set to 0. If given, the value should be a number between 0 and 1. All fractions smaller than dot_min are clipped to this value."/>
+        <expand macro="param_standard_scale"/>
+        <param argument="expression_cutoff" type="float" min="0.0" value="0.0" label="Expression cutoff that is used for binarizing the gene expression and determining the fraction of cells expressing given genes" help="A gene is expressed only if the expression value is greater than this threshold."/>
+        <param argument="mean_only_expressed" type="boolean" truevalue="True" falsevalue="False" checked="false" label="average the gene expression only over the cells expressing the given genes"/>
         <expand macro="section_matplotlib_pyplot_scatter"/>
     </xml>
-    <token name="@CMD_pl_dotplot@"><![CDATA[
-    #if $method.color_map
+    <token name="@CMD_PL_DOTPLOT@"><![CDATA[
+    #if $method.color_map:
     color_map='$method.color_map',
     #end if
-    #if str($method.dot_max) != ''
+    #if str($method.dot_max) != '':
     dot_max=$method.dot_max,
     #end if
-    #if str($method.dot_min) != ''
+    #if str($method.dot_min) != '':
     dot_min=$method.dot_min,
     #end if
-    @CMD_params_matplotlib_pyplot_scatter@
+    @CMD_STANDARD_SCALE@
+    expression_cutoff=$method.expression_cutoff,
+    mean_only_expressed=$method.mean_only_expressed,
+    @CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@
     ]]>
     </token>
-    <xml name="param_key">
-        <param argument="key" type="text" value="" label="Key used to store the ranking results in 'uns'">
-            <expand macro="sanitize_query" />
+
+    <xml name="values_to_plot">
+        <param argument="values_to_plot" type="select" optional="true" label="Values to plot" help="Defualt: plots mean expression. When plotting logfoldchanges a divergent colormap is recommended.">
+            <option value="scores">Scores</option>
+            <option value="logfoldchanges">Log foldchanges</option>
+            <option value="pvals">P-values</option>
+            <option value="pvals_adj">Adjusted p-values</option>
+            <option value="log10_pvals">log10 of p-values</option>
+            <option value="log10_pvals_adj">log10 of adjusted p-values</option>
         </param>
     </xml>
-    <xml name="pl_heatmap">
-        <expand macro="param_swap_axes"/>
-        <param argument="show_gene_labels" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Show gene labels?" help="By default gene labels are shown when there are 50 or less genes. Otherwise the labels are removed."/>
-        <section name="matplotlib_pyplot_imshow" title="Parameters for matplotlib.pyplot.imshow">
-            <expand macro="param_cmap"/>
-            <param name="interpolation" type="select" label="Interpolation method" help="">
-                <option value="None">none</option>
-                <option value="nearest">nearest</option>
-                <option value="bilinear">bilinear</option>
-                <option value="bicubic">bicubic</option>
-                <option value="spline16">spline16</option>
-                <option value="spline36">spline36</option>
-                <option value="hanning">hanning</option>
-                <option value="hamming">hamming</option>
-                <option value="hermite">hermite</option>
-                <option value="kaiser">kaiser</option>
-                <option value="quadric">quadric</option>
-                <option value="catrom">catrom</option>
-                <option value="gaussian">gaussian</option>
-                <option value="bessel">bessel</option>
-                <option value="sinc">sinc</option>
-                <option value="mitchell">mitchell</option>
-                <option value="lanczos">lanczos</option>
-            </param>
-            <expand macro="param_alpha"/>
-            <expand macro="param_vmin"/>
-            <expand macro="param_vmax"/>
-            <param name="origin" type="select" label="Place the [0,0] index of the array in the upper left or lower left corner of the axes" help=" The convention 'upper' is typically used for matrices and images.">
-                <option value="upper">Upper</option>
-                <option value="lower">Lower</option>
-            </param>
-        </section>
-    </xml>
-    <token name="@CMD_pl_heatmap@"><![CDATA[
-    swap_axes=$method.swap_axes,
-    show_gene_labels=$method.show_gene_labels,
-    #if $method.matplotlib_pyplot_imshow.cmap
-    cmap='$method.matplotlib_pyplot_imshow.cmap',
-    #end if
-    #if str($method.matplotlib_pyplot_imshow.interpolation) != 'None'
-    interpolation='$method.matplotlib_pyplot_imshow.interpolation',
-    #end if
-    #if str($method.matplotlib_pyplot_imshow.alpha) != ''
-    alpha=$method.matplotlib_pyplot_imshow.alpha,
-    #end if
-    #if str($method.matplotlib_pyplot_imshow.vmin) != ''
-    vmin=$method.matplotlib_pyplot_imshow.vmin,
-    #end if
-    #if str($method.matplotlib_pyplot_imshow.vmax) != ''
-    vmax=$method.matplotlib_pyplot_imshow.vmax,
+    <token name="@CMD_VALUES_TO_PLOT@"><![CDATA[
+    #if $method.values_to_plot:
+    values_to_plot='$method.values_to_plot',
+    colorbar_title='$method.values_to_plot',
     #end if
-    origin='$method.matplotlib_pyplot_imshow.origin'
     ]]>
     </token>
+
+
+    <xml name="param_n_genes" token_value="">
+        <param argument="n_genes" type="integer" min="0" value="@VALUE@" optional="true" label="Number of genes to show" help="It is only used if you are not specifying certain variable names"/>
+    </xml>
+    <xml name="param_key">
+        <param argument="key" type="text" value="" label="Key used to store the ranking results in 'uns'">
+            <expand macro="sanitize_query"/>
+        </param>
+    </xml>
+
     <xml name="pl_rank_genes_groups_ext">
+        <expand macro="pl_var_names"/>
         <expand macro="param_groups"/>
-        <expand macro="param_n_genes"/>
+        <expand macro="param_n_genes" value=""/>
         <expand macro="param_key"/>
+        <param argument="min_logfoldchange" type="integer" optional="true" value="" label="Value to filter genes in groups if their logfoldchange is less than this value"/>
     </xml>
-    <token name="@CMD_pl_rank_genes_groups_ext@"><![CDATA[
-    @CMD_params_groups@
-    n_genes=$method.n_genes,
-    #if $method.key
-    key='$method.key',
-    #end if
-    ]]>
-    </token>
-    <xml name="pl_matrixplot">
-        <expand macro="param_swap_axes"/>
-        <section name="matplotlib_pyplot_pcolor" title="Parameters for matplotlib.pyplot.pcolor">
-            <param argument="cmap" type="select" optional="true" label="Color palette">
-                <expand macro="seaborn_color_palette_options"/>
-            </param>
-            <param argument="vmin" type="float" value="" optional="true" label="Minimum value to anchor the colormap" help=""/>
-            <param argument="vmax" type="float" value="" optional="true" label="Maximum value to anchor the colormap" help=""/>
-            <expand macro="param_matplotlib_pyplot_edgecolors"/>
-            <expand macro="param_alpha"/>
-            <param argument="snap" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Snap the mesh to pixel boundaries?" help=""/>
-        </section>
-    </xml>
-    <token name="@CMD_pl_matrixplot@"><![CDATA[
-    swap_axes=$method.swap_axes,
-    #if $method.matplotlib_pyplot_pcolor.cmap
-    cmap='$method.matplotlib_pyplot_pcolor.cmap',
-    #end if
-    #if str($method.matplotlib_pyplot_pcolor.vmin) != ''
-    vmin=$method.matplotlib_pyplot_pcolor.vmin,
+    <token name="@CMD_PL_RANK_GENES_GROUPS_EXT@"><![CDATA[
+    #if str($method.var_names.type) == 'custom':
+    #set $var_names = ([x.strip() for x in str($method.var_names.var_names).split(',')])
+    var_names=$var_names,
+    #else if str($method.var_names.type) == 'customfile':
+    var_names={key: [v for v in list(value.values()) if pd.notna(v)] for key, value in pd.read_csv('$var_names', sep='\t', index_col=0, header=header).to_dict(orient='index').items()},
     #end if
-    #if str($method.matplotlib_pyplot_pcolor.vmax) != ''
-    vmax=$method.matplotlib_pyplot_pcolor.vmax,
+    @CMD_PARAM_GROUPS@
+    #if str($method.n_genes) != '':
+    n_genes=$method.n_genes,
     #end if
-    #if $method.matplotlib_pyplot_pcolor.edgecolors
-    ec='$method.matplotlib_pyplot_pcolor.edgecolors',
+    #if str($method.key) != '':
+    key='$method.key',
     #end if
-    #if str($method.matplotlib_pyplot_pcolor.alpha) != ''
-    alpha=$method.matplotlib_pyplot_pcolor.alpha,
+    #if str($method.min_logfoldchange) != '':
+    min_logfoldchange=$method.min_logfoldchange,
     #end if
-    snap=$method.matplotlib_pyplot_pcolor.snap
     ]]>
     </token>
-    <xml name="pl_stacked_violin">
+
+    <xml name="param_density_norm">
+        <param argument="density_norm" type="select" label="Method used to scale the width of each violin">
+        	<option value="area" selected="true">area: each violin will have the same area</option>
+            <option value="width">width: each violin will have the same width</option>
+            <option value="count">count: the width of the violins will be scaled by the number of observations in that bin</option>
+        </param>
+    </xml>
+    <xml name="params_pl_stacked_violin">
         <expand macro="param_swap_axes"/>
         <section name="violin_plot" title="Violin plot attributes">
             <expand macro="conditional_stripplot"/>
-            <expand macro="param_scale"/>
+            <expand macro="param_density_norm"/>
         </section>
         <param argument="row_palette" type="select" optional="true" label="Colors to use in each of the stacked violin plots">
             <option value="muted">muted</option>
             <expand macro="seaborn_color_palette_options"/>
         </param>
-        <param argument="standard_scale" type="select" label="Standardize a dimension between 0 and 1" help="Each variable or observation is subtracted by the minimum and divided each by its maximum.">
-            <option value="None">No standardization</option>
-            <option value="var">Standardization on variable</option>
-            <option value="obs">Standardization on observation</option>
-        </param>
-        <expand macro="seaborn_violinplot"/>
-    </xml>
-    <token name="@CMD_pl_stacked_violin@"><![CDATA[
+        <expand macro="param_standard_scale"/>
+        <expand macro="params_seaborn_violinplot"/>
+        <param argument="yticklabels" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Set to view the y tick labels"/>
+        <expand macro="param_vmin" label="The value representing the lower limit of the color scale" help="Values smaller than vmin are plotted with the same color as vmin."/>
+        <expand macro="param_vmax" label="The value representing the upper limit of the color scale" help="Values larger than vmax are plotted with the same color as vmax."/>
+        <expand macro="param_vcenter"/>
+    </xml>
+    <token name="@CMD_PARAMS_PL_STACKED_VIOLIN@"><![CDATA[
     swap_axes=$method.swap_axes,
-    @CMD_conditional_stripplot@
-    scale='$method.violin_plot.scale',
-    #if $method.row_palette
+    @CMD_CONDITIONAL_STRIPPLOT@
+    density_norm='$method.violin_plot.density_norm',
+    #if $method.row_palette:
     row_palette='$method.row_palette',
     #end if
-    #if str($method.standard_scale) != 'None'
-    standard_scale='$method.standard_scale',
+    @CMD_STANDARD_SCALE@
+    @CMD_PARAMS_SEABORN_VIOLINPLOT@
+    yticklabels=$method.yticklabels,
+    #if str($method.vmin) != '':
+    vmin=$method.vmin,
+    #end if
+    #if str($method.vmax) != '':
+    vmax=$method.vmax,
+    #end if
+    #if str($method.vcenter) != '':
+    vcenter=$method.vcenter,
     #end if
-    @CMD_params_seaborn_violinplot@
     ]]>
     </token>
+
+    <xml name="params_scatter_outine">
+        <param argument="add_outline" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Add a thin border around groups of dots" help="In some situations this can enhance the aesthetics of the resulting image"/>
+        <param name="outline_color_border" type="select" optional="true" label="Border color around the scatter dot" help="Default: black">
+            <expand macro="matplotlib_color"/>
+        </param>
+        <param name="outline_color_gap" type="select" optional="true" label="Gap color between the border color and the scatter dot" help="Default: white">
+            <expand macro="matplotlib_color"/>
+        </param>
+        <param argument="outline_width_border" type="float" value="0.3" optional="true" label=" width of the border color as a fraction of the scatter dot size "/>
+        <param argument="outline_width_gap" type="float" value="0.05" optional="true" label="The width of the gap color"/>
+    </xml>
+    <token name="@CMD_SCATTER_OUTINE@"><![CDATA[
+    add_outline=$method.add_outline,
+    #if $method.outline_color_border and $method.outline_color_gap:
+    outline_color=($method.outline_color_border, $method.outline_color_gap),
+    #end if
+    outline_width=($method.outline_width_border, $method.outline_width_gap),
+    ]]>
+    </token>
+
+
+    <!-- unused macros -->
+    <!-- <xml name="param_right_margin">
+        <param argument="right_margin" type="float" value="1" label="Width of the space right of each plotting panel"/>
+    </xml>
+    <xml name="param_left_margin">
+        <param argument="left_margin" type="float" value="1" label="Width of the space left of each plotting panel"/>
+    </xml> -->
 </macros>
diff --git a/tools/scanpy/normalize.xml b/tools/scanpy/normalize.xml
index 29caa1adaf9..d8c55063020 100644
--- a/tools/scanpy/normalize.xml
+++ b/tools/scanpy/normalize.xml
@@ -1,45 +1,40 @@
-<tool id="scanpy_normalize" name="Normalize" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
-    <description>and impute with scanpy</description>
+<tool id="scanpy_normalize" name="Scanpy normalize" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>and impute</description>
     <macros>
         <import>macros.xml</import>
     </macros>
     <expand macro="bio_tools"/>
-    <expand macro="requirements"/>
+    <expand macro="requirements">
+        <requirement type="package" version="3.0.0">magic-impute</requirement>
+    </expand>
     <expand macro="version_command"/>
     <command detect_errors="exit_code"><![CDATA[
 @CMD@
       ]]></command>
     <configfiles>
         <configfile name="script_file"><![CDATA[
-@CMD_imports@
-@CMD_read_inputs@
+@CMD_IMPORTS@
+@CMD_READ_INPUTS@
 
-#if $method.method == "pp.normalize_total"
+#if str($method.method) == 'pp.normalize_total':
 sc.pp.normalize_total(
     adata,
-    #if str($method.target_sum) != ''
+    #if str($method.target_sum) != '':
     target_sum=$method.target_sum,
     #end if
     exclude_highly_expressed=$method.exclude_highly_expressed.exclude_highly_expressed,
-    #if $method.exclude_highly_expressed.exclude_highly_expressed == "True"
+    #if str($method.exclude_highly_expressed.exclude_highly_expressed) == 'True':
     max_fraction=$method.exclude_highly_expressed.max_fraction,
     #end if
-    #if $method.key_added
+    #if str($method.key_added) != '':
     key_added='$method.key_added',
     #end if
-    #if $method.layers
-        #if str($method.layers) != 'all'
-    layers[str(x.strip()) for x in str($method.layers).split(',')],
-        #else
-    layers='$method.layers',
-        #end if
-    #end if
-    #if str($method.layer_norm) != "None"
-        layer_norm='$method.layer_norm',
+    #if str($method.layer) != '':
+        layer='$method.layer',
     #end if
     inplace=True)
 
-#else if $method.method == "pp.recipe_zheng17"
+#else if str($method.method) == 'pp.recipe_zheng17':
 sc.pp.recipe_zheng17(
     adata=adata,
     n_top_genes=$method.n_top_genes,
@@ -47,52 +42,62 @@ sc.pp.recipe_zheng17(
     plot=False,
     copy=False)
 
-#else if $method.method == "pp.recipe_weinreb17"
+#else if str($method.method) == 'pp.recipe_weinreb17':
 sc.pp.recipe_weinreb17(
     adata=adata,
     log=$method.log,
-    mean_threshold=$method.mean_threshold,
-    cv_threshold=$method.cv_threshold,
-    n_pcs=$method.n_pcs,
-    svd_solver='$method.svd_solver',
-    random_state=$method.random_state,
+    mean_threshold=0.01,
+    cv_threshold=2,
+    n_pcs=50,
+    svd_solver='randomized',
+    random_state=0,
     copy=False)
 
-#else if $method.method == "pp.recipe_seurat"
+#else if str($method.method) == 'pp.recipe_seurat':
 sc.pp.recipe_seurat(
     adata=adata,
     log=$method.log,
     plot=False,
     copy=False)
 
-#else if $method.method == "external.pp.magic"
+#else if str($method.method) == 'external.pp.magic':
+print("stats before magic:", "min=", f"{adata.X.min():.5f}", "max=", f"{adata.X.max():.5f}", "mean=", f"{adata.X.mean():.5f}")
+
 sc.external.pp.magic(
     adata=adata,
     name_list='$method.name_list',
     knn=$method.knn,
-    #if str($method.decay) != ''
+    #if str($method.decay) != '':
     decay=$method.decay,
     #end if
-    #if str($method.knn_max) != ''
+    #if str($method.knn_max) != '':
     knn_max=$method.knn_max,
     #end if
-    #if $method.t == -1
+    #if $method.t == -1:
     t='auto',
     #else
     t=$method.t,
     #end if
-    #if str($method.n_pca) != ''
+    #if str($method.n_pca) != '':
     n_pca=$method.n_pca,
     #end if
     solver='$method.solver',
     knn_dist='$method.knn_dist',
+    #if str($method.random_state) != '':
     random_state=$method.random_state,
+    #else
+    random_state=None,
+    #end if
     copy=False)
-#end if
 
-@CMD_anndata_write_outputs@
+    #if str($method.name_list) == 'all_genes':
+print("stats after magic:", "min=", f"{adata.X.min():.5f}", "max=", f"{adata.X.max():.5f}", "mean=", f"{adata.X.mean():.5f}")
+    #end if
+#end if
 
-]]></configfile>
+@CMD_ANNDATA_WRITE_OUTPUTS@
+        ]]>
+        </configfile>
     </configfiles>
     <inputs>
         <expand macro="inputs_anndata"/>
@@ -108,63 +113,50 @@ sc.external.pp.magic(
                 <param argument="target_sum" type="float" value="" optional="true" label="Target sum" help="If not provided, after normalization, each observation (cell) has a total count equal to the median of the total counts (cells) before normalization."/>
                 <conditional name="exclude_highly_expressed">
                     <param argument="exclude_highly_expressed" type="select" label="Exclude (very) highly expressed genes for the computation of the normalization factor (size factor) for each cell" help=" A gene is considered highly expressed, if it has more than max_fraction of the total counts in at least one cell. The not-excluded genes will sum up to target_sum">
-                        <option value="True">Yes</option>
                         <option value="False" selected="true">No</option>
+                        <option value="True">Yes</option>
                     </param>
                     <when value="True">
-                        <param argument="max_fraction" type="float" value="0.05" label="Target sum" help="If not provided, after normalization, each observation (cell) has a total count equal to the median of the total counts (cells) before normalization."/>
+                        <param argument="max_fraction" type="float" value="0.05" label="Consider cells as highly expressed that have more counts than this value of the original total counts in at least one cell."/>
                     </when>
                     <when value="False"/>
                 </conditional>
-                <param argument="key_added" type="text" value="" optional="true" label="Name of the field in 'adata.obs' where the normalization factor is stored" help="">
-                    <expand macro="sanitize_query" />
+                <param argument="key_added" type="text" value="" optional="true" label="Name of the field in 'adata.obs' where the normalization factor is stored">
+                    <expand macro="sanitize_query"/>
                 </param>
-                <param argument="layers" type="text" value="" optional="true" label="List of layers to normalize" help="'All' will normalize all layers. The list should be comma-separated.">
-                    <expand macro="sanitize_query" />
-                </param>
-                <param argument="layer_norm" type="select" label="How to normalize layers?">
-                    <option value="None">None: after normalization, for each layer in layers each cell has a total count equal to the median of the median of the total counts (cells) before normalization of the layer.</option>
-                    <option value="after">After: for each layer in layers each cell has a total count equal to target_sum.</option>
-                    <option value="X">X: for each layer in layers each cell has a total count equal to the median of total counts for observations (cells) of adata.X before normalization.</option>
+                <param argument="layer" type="text" value="" label="Layer to normalize instead of X. If not provided, X is normalized.">
+                    <expand macro="sanitize_query"/>
                 </param>
             </when>
             <when value="pp.recipe_zheng17">
-                <param argument="n_top_genes" type="integer" min="0" value="1000" label="Number of genes to keep" help=""/>
-                <expand macro="param_log"/>
+                <param argument="n_top_genes" type="integer" min="0" value="1000" label="Number of genes to keep"/>
+                <expand macro="param_log" checked="true"/>
             </when>
             <when value="pp.recipe_weinreb17">
-                <expand macro="param_log"/>
-                <param argument="mean_threshold" type="float" value="0.01" label="Mean threshold" help=""/>
-                <param argument="cv_threshold" type="float" value="2" label="CV threshold" help=""/>
-                <param argument="n_pcs" type="integer" min="0" value="50" label="Number of principal component" help=""/>
-                <expand macro="svd_solver"/>
-                <expand macro="pca_random_state"/>
+                <expand macro="param_log" checked="true"/>
             </when>
             <when value="pp.recipe_seurat">
-                <expand macro="param_log"/>
+                <expand macro="param_log" checked="true"/>
             </when>
             <when value="external.pp.magic">
                 <param name="name_list" type="select" label="Denoised genes to return" help="Selecting all genes may require a large amount of memory">
-                    <option value="all_genes">All genes</option>
+                    <option value="all_genes" selected="true">All genes</option>
                     <option value="pca_only">PCA only</option>
                 </param>
-                <param argument="knn" type="integer" min="1" value="5" label="Number of nearest neighbors on which to build kernel" help=""/>
-                <param argument="decay" type="integer" optional="true" value="1" label="Set decay rate of kernel tails" 
-                    help="If not set, alpha decaying kernel is not used" />
-                <param argument="knn_max" type="integer" min="1" optional="true" value="" label="Maximum number of nearest neighbors with nonzero connection"
-                    help="If not set, will be set to 3 * knn" />
-                <param argument="t" type="integer" min="-1" value="3" label="Power to which the diffusion operator is powered. This sets the level of diffusion"
-                    help="If ‘-1’, this parameter is selected according to the Procrustes disparity of the diffused data." />
+                <param argument="knn" type="integer" min="1" value="5" label="Number of nearest neighbors on which to build kernel"/>
+                <param argument="decay" type="integer" optional="true" value="1" label="Set decay rate of kernel tails" help="If not set, alpha decaying kernel is not used"/>
+                <param argument="knn_max" type="integer" min="1" optional="true" value="" label="Maximum number of nearest neighbors with nonzero connection" help="If not set, will be set to 3 * knn"/>
+                <param argument="t" type="integer" min="-1" value="3" label="Power to which the diffusion operator is powered. This sets the level of diffusion" help="If ‘-1’, this parameter is selected according to the Procrustes disparity of the diffused data."/>
                 <param argument="n_pca" type="integer" value="100" optional="true" label="Number of principal components to use for calculating neighborhoods"
-                    help="For extremely large datasets, using n_pca less than 20 allows neighborhoods to be calculated in roughly log(n_samples) time. If not set, no PCA is performed." />
+                    help="For extremely large datasets, using n_pca less than 20 allows neighborhoods to be calculated in roughly log(n_samples) time. If not set, no PCA is performed."/>
                 <param name="solver" type="select" label="Which solver to use" help="Selecting all genes may require a large amount of memory">
-                    <option value="exact">"exact", the implementation described in van Dijk et al. (2018) </option>
+                    <option value="exact" selected="true">"exact", the implementation described in van Dijk et al. (2018) </option>
                     <option value="approximate">"approximate", is faster that performs imputation in the PCA space and then projects back to the gene space</option>
                 </param>
                 <param name="knn_dist" type="select" label="Distance metric to use for the data" help="See scipy.spatial.distance.pdist documentation for more options https://docs.scipy.org/doc/scipy/reference/generated/scipy.spatial.distance.pdist.html">
                     <expand macro="distance_metric_options"/>
                 </param>
-                <expand macro="param_random_state"/>
+                <param argument="random_state" type="integer" optional="true" label="Random seed" help="Defaults to the global numpy random number generator."/>
             </when>
         </conditional>
         <expand macro="inputs_common_advanced"/>
@@ -173,41 +165,39 @@ sc.external.pp.magic(
         <expand macro="anndata_outputs"/>
     </outputs>
     <tests>
+
+        <!-- test 1 -->
         <test expect_num_outputs="2">
-            <!-- test 1 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.normalize_total"/>
-                <conditional name="exclude_highly_expressed">
-                    <param name="exclude_highly_expressed" value="False"/>
-                </conditional>
                 <param name="key_added" value="n_counts"/>
-                <param name="layers" value="all"/>
-                <param name="layer_norm" value="None"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.normalize_total"/>
                     <has_text_matching expression="exclude_highly_expressed=False"/>
                     <has_text_matching expression="key_added='n_counts'"/>
-                    <has_text_matching expression="layers='all'"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.normalize_total.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/n_counts"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 2 -->
         <test expect_num_outputs="2">
-            <!-- test 2 -->
             <param name="adata" value="random-randint.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.recipe_zheng17"/>
-                <param name="n_top_genes" value="1000"/>
-                <param name="log" value="True"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -216,45 +206,50 @@ sc.external.pp.magic(
                     <has_text_matching expression="log=True"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.recipe_zheng17.random-randint.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.15"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/n_counts_all"/>
+                    <has_h5_keys keys="var/n_counts,var/mean,var/std"/>
+                    <has_h5_keys keys="uns/log1p"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 3 -->
         <test expect_num_outputs="2">
-            <!-- test 3 -->
-            <param name="adata" value="paul15_subsample.h5ad" />
+            <param name="adata" value="paul15_subsample.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.recipe_weinreb17"/>
-                <param name="log" value="True"/>
-                <param name="mean_threshold" value="0.01"/>
-                <param name="cv_threshold" value="2.0"/>
-                <param name="n_pcs" value="50"/>
-                <param name="svd_solver" value="randomized"/>
-                <param name="random_state" value="0"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.recipe_weinreb17"/>
                     <has_text_matching expression="log=True"/>
                     <has_text_matching expression="mean_threshold=0.01"/>
-                    <has_text_matching expression="cv_threshold=2.0"/>
+                    <has_text_matching expression="cv_threshold=2"/>
                     <has_text_matching expression="n_pcs=50"/>
                     <has_text_matching expression="svd_solver='randomized'"/>
                     <has_text_matching expression="random_state=0"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.recipe_weinreb17.paul15_subsample.updated.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/log1p"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 4 -->
         <test expect_num_outputs="2">
-            <!-- test 4 -->
-            <param name="adata" value="pp.recipe_zheng17.random-randint.h5ad" />
+            <param name="adata" value="pp.recipe_zheng17.random-randint.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.recipe_seurat"/>
-                <param name="log" value="True"/>
-            </conditional>
+           </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -262,19 +257,25 @@ sc.external.pp.magic(
                     <has_text_matching expression="log=True"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.recipe_seurat.recipe_zheng17.h5ad" ftype="h5ad" compare="sim_size" delta="1000000" delta_frac="0.25"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/n_genes"/>
+                    <has_h5_keys keys="var/n_cells"/>
+                    <has_h5_keys keys="uns/log1p"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 5 -->
         <test expect_num_outputs="2">
-            <!-- test 5 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="external.pp.magic"/>
-                <param name="name_list" value="all_genes"/>
                 <param name="t" value="-1"/>
                 <param name="n_pca" value="5"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -282,13 +283,20 @@ sc.external.pp.magic(
                     <has_text_matching expression="name_list='all_genes'"/>
                     <has_text_matching expression="t='auto'"/>
                     <has_text_matching expression="n_pca=5"/>
+                    <has_text_matching expression="stats before magic: min= -0.01630 max= 1.01060 mean= 0.28644"/>
+                    <has_text_matching expression="stats after magic: min= -0.00857 max= 1.00546 mean= 0.28645"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obs/cell_type"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="external.pp.magic.all_genes.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
+
+        <!-- test 6 -->
         <test expect_num_outputs="2">
-            <!-- test 6 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <conditional name="method">
                 <param name="method" value="external.pp.magic"/>
                 <param name="name_list" value="pca_only"/>
@@ -296,7 +304,7 @@ sc.external.pp.magic(
                 <param name="n_pca" value="5"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -306,23 +314,26 @@ sc.external.pp.magic(
                     <has_text_matching expression="n_pca=5"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="external.pp.magic.pca_only.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obsm/X_magic"/>
+                </assert_contents>
+            </output>
             <assert_stdout>
                 <has_text text="X_magic"/>
             </assert_stdout>
         </test>
     </tests>
     <help><![CDATA[
-Normalize total counts per cell (`pp.normalize_per_cell`)
-=========================================================
+Normalize total counts per cell (`pp.normalize_total`)
+======================================================
 
-Normalize each cell by total counts over all genes, so that every cell has
-the same total count after normalization.
+Normalize each cell by total counts over all genes, so that every cell has the same total count after normalization. If choosing target_sum=1e6, this is CPM normalization.
 
 Similar functions are used, for example, by Seurat, Cell Ranger or SPRING.
 
 More details on the `scanpy documentation
-<https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.normalize_per_cell.html>`__
+<https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.normalize_total.html>`__
 
 
 Normalization and filtering as of Zheng et al. (2017), the Cell Ranger R Kit of 10x Genomics (`pp.recipe_zheng17`)
@@ -369,7 +380,7 @@ Markov Affinity-based Graph Imputation of Cells (MAGIC) as of Van Dijk D et al.
 
 MAGIC is an algorithm for denoising and transcript recover of single cells applied to single-cell sequencing data. MAGIC builds a graph from the data and uses diffusion to smooth out noise and recover the data manifold.
 
-The algorithm implemented here has changed primarily in two ways compared to the algorithm described in Van Dijk D et al. (2018). 
+The algorithm implemented here has changed primarily in two ways compared to the algorithm described in Van Dijk D et al. (2018).
 
 - Firstly, we use the adaptive kernel described in Moon et al, (2019) for improved stability.
 - Secondly, data diffusion is applied in the PCA space, rather than the data space, for speed and memory improvements.
diff --git a/tools/scanpy/plot.xml b/tools/scanpy/plot.xml
index 274e9bd3ff1..c8b9eef0683 100644
--- a/tools/scanpy/plot.xml
+++ b/tools/scanpy/plot.xml
@@ -1,10 +1,13 @@
-<tool id="scanpy_plot" name="Plot" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
-    <description> with scanpy</description>
+<tool id="scanpy_plot" name="Scanpy plot" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
     <macros>
         <import>macros.xml</import>
     </macros>
     <expand macro="bio_tools"/>
-    <expand macro="requirements"/>
+    <expand macro="requirements">
+        <requirement type="package" version="3.9.1">matplotlib</requirement>
+        <requirement type="package" version="0.13.2">seaborn</requirement>
+        <requirement type="package" version="0.11.6">python-igraph</requirement>
+    </expand>
     <stdio>
         <regex match="... storing" source="stderr" level="warning"/>
     </stdio>
@@ -14,18 +17,18 @@
       ]]></command>
     <configfiles>
         <configfile name="script_file"><![CDATA[
-@CMD_imports@
-@CMD_read_inputs@
+@CMD_IMPORTS@
+@CMD_READ_INPUTS@
 
 sc.settings.figdir = '.'
 
-#if $method.method == 'pl.scatter'
+#if str($method.method) == 'pl.scatter':
 
-#if $method.type.type == 'xy':
+    #if str($method.type.type) == 'xy':
 x_field='$method.type.x'
 y_field='$method.type.y'
 
-#if $method.type.log:
+    #if $method.type.log:
 if x_field in adata.obs or x_field in adata.var:
     if x_field in adata.obs:
         adata.obs[f"log_{x_field}"] = np.log10(adata.obs[x_field])
@@ -39,425 +42,462 @@ if y_field in adata.obs or y_field in adata.var:
     elif y_field in adata.var:
         adata.var[f"log_{y_field}"] = np.log10(adata.var[y_field])
     y_field=f"log_{y_field}"
-#end if
-#end if
+    #end if
+    #end if
 
 sc.pl.scatter(
-    @CMD_param_plot_inputs@
-    #if $method.type.type == 'xy':
+    @CMD_PARAM_PLOT_INPUTS@
+    #if str($method.type.type) == 'xy':
     x=x_field,
     y=y_field,
-    #if $method.type.color
+        #if str($method.type.color) != '':
     color='$method.type.color',
-    #end if
-    #if str('$method.type.layers.use_layers') == 'true'
+        #end if
+        #if str('$method.type.layers.use_layers') == 'true':
     layers=('$method.type.layers.layer_x', '$method.type.layers.layer_y', '$method.type.layers.layer_color'),
-    #end if
-    #else
+        #end if
+    #else if str($method.type.type) == 'basis':
     basis='$method.type.basis',
-    #if $method.type.color
-        #set $color = ([x.strip() for x in str($method.type.color).split(',')])
+        #if str($method.type.color) != '':
+            #set $color = ([x.strip() for x in str($method.type.color).split(',')])
     color=$color,
-    #end if
+        #end if
     #end if
     use_raw=$method.use_raw,
     sort_order=$method.sort_order,
-    @CMD_params_groups@
-    @CMD_params_pl_components@
+    @CMD_PARAM_GROUPS@
+    @CMD_PARAM_PL_COMPONENTS@
     projection='$method.plot.projection',
+    #if str($method.plot.legend_loc) != '':
     legend_loc='$method.plot.legend_loc',
-    #if $method.plot.palette
-    palette=['$method.plot.palette'],
     #end if
-    #if $method.plot.color_map
+    @CMD_PARAM_LEGEND_FONTSIZE@
+    legend_fontweight='$method.plot.legend_fontweight',
+    #if $method.plot.color_map:
     color_map='$method.plot.color_map',
+    #end if   
+    #if $method.plot.palette:
+    palette=['$method.plot.palette'],
     #end if
-    @CMD_param_legend_fontsize@
-    legend_fontweight='$method.plot.legend_fontweight',
-    @CMD_param_title@
-    @CMD_param_size@
-    frameon=$method.plot.frameon)
+    frameon=$method.plot.frameon,
+    @CMD_PARAM_SIZE@
+    @CMD_PARAM_TITLE@
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.heatmap'
-@CMD_var_names_header_check@
+#else if str($method.method) == 'pl.heatmap':
+@CMD_VAR_NAMES_HEADER_CHECK@
 sc.pl.heatmap(
-    @CMD_param_plot_inputs@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_params_inputs@
-    @CMD_params_plots@
-    @CMD_pl_heatmap@)
-
-#else if $method.method == 'pl.dotplot'
-@CMD_var_names_header_check@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAMS_INPUTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAMS_PL_HEATMAP@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.dotplot':
+@CMD_VAR_NAMES_HEADER_CHECK@
 sc.pl.dotplot(
-    @CMD_param_plot_inputs@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_params_inputs@
-    @CMD_params_plots@
-    @CMD_pl_dotplot@)
-
-#else if $method.method == 'pl.violin'
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAMS_INPUTS@    
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PL_DOTPLOT@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.tracksplot':
+@CMD_VAR_NAMES_HEADER_CHECK@
+sc.pl.tracksplot(
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAMS_INPUTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PLOTS@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.violin':
 sc.pl.violin(
-    @CMD_param_plot_inputs@
-    #if $method.key_variables.type == "var_names"
+    @CMD_PARAM_PLOT_INPUTS@
+    #if str($method.key_variables.type) == 'var_names':
         #set $key_list = adata.var_names
-    #else if $method.key_variables.type == "obs"
+    #else if str($method.key_variables.type) == 'obs':
         #set $key_list = adata.obs.select_dtypes(exclude=['category']).columns
-    #else if $method.key_variables.type == "custom"
+    #else if str($method.key_variables.type) == 'custom':
         #set $key_list=([x.strip() for x in str($method.key_variables.keys).split(',')])
     #end if
     keys=$key_list,
-    #if $method.groupby
+    #if str($method.groupby) != '':
     groupby='$method.groupby',
     #end if
     log=$method.log,
     use_raw=$method.use_raw,
-    @CMD_conditional_stripplot@
+    @CMD_CONDITIONAL_STRIPPLOT@
     multi_panel=$method.violin_plot.multi_panel.multi_panel,
-    #if $method.violin_plot.multi_panel.multi_panel == "True" and str($method.violin_plot.multi_panel.width) != '' and str($method.violin_plot.multi_panel.height) != ''
-    figsize=($method.violin_plot.multi_panel.width, $method.violin_plot.multi_panel.height),
-    #end if
-    scale='$method.violin_plot.scale',
-    #if $method.xlabel
+    ##if $method.violin_plot.multi_panel.multi_panel == "True" and str($method.violin_plot.multi_panel.width) != '' and str($method.violin_plot.multi_panel.height) != ''
+    ##figsize=($method.violin_plot.multi_panel.width, $method.violin_plot.multi_panel.height),
+    ##end if
+    #if str($method.xlabel) != '':
     xlabel='$method.xlabel',
     #end if
-    #if str($method.rotation) != ''
+    #if str($method.rotation) != '':
     rotation=$method.rotation,
     #end if
-    @CMD_params_seaborn_violinplot@)
+    @CMD_PARAMS_SEABORN_VIOLINPLOT@
+    @CMD_PARAM_LAYER@
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.stacked_violin'
-@CMD_var_names_header_check@
+#else if str($method.method) == 'pl.stacked_violin':
+@CMD_VAR_NAMES_HEADER_CHECK@
 sc.pl.stacked_violin(
-    @CMD_param_plot_inputs@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_params_inputs@
-    @CMD_params_plots@
-    @CMD_pl_stacked_violin@)
-
-#else if $method.method == 'pl.matrixplot'
-@CMD_var_names_header_check@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAMS_INPUTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAMS_PL_STACKED_VIOLIN@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.matrixplot':
+@CMD_VAR_NAMES_HEADER_CHECK@
 sc.pl.matrixplot(
-    @CMD_param_plot_inputs@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_params_inputs@
-    @CMD_params_plots@
-    @CMD_pl_matrixplot@)
-
-#else if $method.method == 'pl.clustermap'
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAMS_INPUTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAMS_PL_MATRIXPLOT@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.clustermap':
 sc.pl.clustermap(
-    #if str($method.use_raw) == 'True'
+    #if str($method.use_raw) == 'True':
     adata=adata.X,
     #else
     adata=adata,
     #end if
-    show=False,
-    #if $method.obs_keys
+    #if str($method.obs_keys) != '':
     obs_keys='$method.obs_keys',
     #end if
     use_raw=$method.use_raw,
     method='$method.seaborn_clustermap.method',
     metric='$method.seaborn_clustermap.metric',
-    #if str($method.seaborn_clustermap.z_score) != 'None'
+    #if str($method.seaborn_clustermap.z_score) != 'None':
     z_score=$method.seaborn_clustermap.z_score,
     #end if
-    #if str($method.seaborn_clustermap.standard_scale) != 'None'
+    #if str($method.seaborn_clustermap.standard_scale) != 'None':
     standard_scale=$method.seaborn_clustermap.standard_scale,
     #end if
     col_cluster=$method.seaborn_clustermap.col_cluster,
-    row_cluster=$method.seaborn_clustermap.row_cluster).savefig(fname="output.$format")
+    row_cluster=$method.seaborn_clustermap.row_cluster,
+    save='.$format',
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.highest_expr_genes'
+#else if str($method.method) == 'pl.highest_expr_genes':
 sc.pl.highest_expr_genes(
-    @CMD_param_plot_inputs@
+    @CMD_PARAM_PLOT_INPUTS@
     n_top=$method.n_top,
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    #if $method.setseaborn_boxplot.color
+    @CMD_PARAM_GENE_SYMBOLS@
+    #if str($method.setseaborn_boxplot.color) != '':
     color='$method.setseaborn_boxplot.color',
     #end if
-    #if $method.setseaborn_boxplot.palette
+    #if $method.setseaborn_boxplot.palette:
     palette='$method.setseaborn_boxplot.palette',
     #end if
-    saturation=$method.setseaborn_boxplot.saturation)
+    saturation=$method.setseaborn_boxplot.saturation,
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.highly_variable_genes'
+#else if str($method.method) == 'pl.highly_variable_genes':
 sc.pl.highly_variable_genes(
     adata_or_result=adata,
     log=$method.log,
     save='.$format',
-    show=False,
-    highly_variable_genes=$method.highly_variable_genes)
+    highly_variable_genes=$method.highly_variable_genes,
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.scrublet_score_distribution':
+sc.pl.scrublet_score_distribution(
+    adata=adata,
+    scale_hist_obs='$method.scale_hist_obs',
+    scale_hist_sim='$method.scale_hist_sim',
+    @CMD_PARAMS_FIGSIZE@
+    save='.$format',
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.pca'
+#else if str($method.method) == 'pl.pca':
 sc.pl.pca(
-    @CMD_param_plot_inputs@
-    @CMD_param_color@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_COLOR@
     use_raw=$method.use_raw,
     sort_order=$method.sort_order,
-    @CMD_params_groups@
-    @CMD_params_pl_components@
-    @CMD_pl_attribute_section@
-    @CMD_params_matplotlib_pyplot_scatter@)
-
-#else if $method.method == 'pl.pca_loadings'
+    @CMD_PARAM_GROUPS@
+    @CMD_PARAMS_PL_ATTRIBUTE_SECTION@
+    @CMD_SCATTER_OUTINE@
+    @CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@
+    @CMD_PARAM_LAYER@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.pca_loadings':
 sc.pl.pca_loadings(
-    @CMD_param_plot_inputs@
+    @CMD_PARAM_PLOT_INPUTS@
     #set $components = ([int(x.strip()) for x in str($method.components).split(',')])
-    components=$components)
+    components=$components,
+    include_lowest=$method.include_lowest,
+    #if str($method.n_points) != '':
+    n_points=$method.n_points,
+    #end if
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.pca_variance_ratio'
+#else if str($method.method) == 'pl.pca_variance_ratio':
 sc.pl.pca_variance_ratio(
-    @CMD_param_plot_inputs@
+    @CMD_PARAM_PLOT_INPUTS@
     n_pcs=$method.n_pcs,
-    log=$method.log)
+    log=$method.log,
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.pca_overview'
+#else if str($method.method) == 'pl.pca_overview':
 sc.pl.pca_overview(
-    @CMD_param_plot_inputs@
-    @CMD_param_color@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_COLOR@
     use_raw=$method.use_raw,
     sort_order=$method.sort_order,
-    @CMD_params_groups@
-    @CMD_params_pl_components@
-    @CMD_pl_attribute_section@
-    @CMD_params_matplotlib_pyplot_scatter@)
+    @CMD_PARAM_GROUPS@
+    @CMD_PARAMS_PL_ATTRIBUTE_SECTION@
+    @CMD_SCATTER_OUTINE@
+    @CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@    
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.tsne'
+#else if str($method.method) == 'pl.tsne':
 sc.pl.tsne(
-    @CMD_param_plot_inputs@
-    @CMD_param_color@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_COLOR@
+    @CMD_PARAM_GENE_SYMBOLS@
     use_raw=$method.use_raw,
-    @CMD_pl_edges@
+    @CMD_PL_EDGES@
     arrows=$method.arrows,
     sort_order=$method.sort_order,
-    @CMD_params_groups@
-    @CMD_params_pl_components@
-    @CMD_pl_attribute_section@
-    @CMD_params_matplotlib_pyplot_scatter@)
-
-#else if $method.method == 'pl.umap'
+    @CMD_PARAM_GROUPS@
+    @CMD_PARAMS_PL_ATTRIBUTE_SECTION@
+    @CMD_SCATTER_OUTINE@
+    @CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@    
+    @CMD_PARAM_LAYER@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.umap':
 sc.pl.umap(
-    @CMD_param_plot_inputs@
-    @CMD_param_color@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_COLOR@
     use_raw=$method.use_raw,
-    @CMD_pl_edges@
+    @CMD_PL_EDGES@
     arrows=$method.arrows,
     sort_order=$method.sort_order,
-    @CMD_params_groups@
-    @CMD_params_pl_components@
-    @CMD_pl_attribute_section@
-    @CMD_params_matplotlib_pyplot_scatter@)
-
-#else if $method.method == 'pl.diffmap'
+    @CMD_PARAM_GROUPS@
+    @CMD_PARAMS_PL_ATTRIBUTE_SECTION@
+    @CMD_SCATTER_OUTINE@
+    @CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@
+    @CMD_PARAM_LAYER@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.diffmap':
 sc.pl.diffmap(
-    @CMD_param_plot_inputs@
-    @CMD_param_color@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_COLOR@
     use_raw=$method.use_raw,
     sort_order=$method.sort_order,
-    @CMD_params_groups@
-    @CMD_params_pl_components@
-    @CMD_pl_attribute_section@
-    @CMD_params_matplotlib_pyplot_scatter@)
-
-#else if $method.method == 'pl.draw_graph'
+    @CMD_PARAM_GROUPS@
+    @CMD_PARAMS_PL_ATTRIBUTE_SECTION@
+    @CMD_SCATTER_OUTINE@
+    @CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@
+    @CMD_PARAM_LAYER@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.draw_graph':
 sc.pl.draw_graph(
-    @CMD_param_plot_inputs@
-    @CMD_param_color@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_COLOR@
+    @CMD_PARAM_GENE_SYMBOLS@
     use_raw=$method.use_raw,
     layout='$method.layout',
-    edges=$method.edges.edges,
-    #if str($method.edges.edges) == 'True'
-    edges_width=$method.edges.edges_width,
-    edges_color='$method.edges.edges_color',
-    #end if
+    @CMD_PL_EDGES@
     arrows=$method.arrows,
     sort_order=$method.sort_order,
-    @CMD_params_groups@
-    @CMD_params_pl_components@
-    @CMD_pl_attribute_section@
-    @CMD_params_matplotlib_pyplot_scatter@)
-
-#else if $method.method == 'pl.embedding_density'
+    @CMD_PARAM_GROUPS@
+    @CMD_PARAMS_PL_ATTRIBUTE_SECTION@
+    @CMD_SCATTER_OUTINE@
+    @CMD_SECTION_MATPLOTLIB_PYPLOT_SCATTER@
+    @CMD_PARAM_LAYER@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.embedding_density':
 sc.pl.embedding_density(
-    @CMD_param_plot_inputs@
+    @CMD_PARAM_PLOT_INPUTS@
     basis='$method.basis',
-    #if $method.key
+    #if str($method.key) != '':
     key='$method.key',
     #end if
-    #if $method.groupby
+    #if str($method.groupby) != '':
     groupby='$method.groupby',
     #end if
-    #if $method.group
+    #if str($method.group) != '':
     #set $group = ([x.strip() for x in str($method.group).split(',')])
     group=$group,
     #end if
-    #if $method.color_map
+    #if $method.color_map:
     color_map='$method.color_map',
     #end if
     bg_dotsize=$method.bg_dotsize,
     fg_dotsize=$method.fg_dotsize,
     ncols=$method.ncols,
     wspace=$method.wspace,
-    hspace=$method.hspace)
+    hspace=$method.hspace,
+    @CMD_SHOW_NONE@)
+
 
-#else if $method.method == 'pl.dpt_groups_pseudotime'
-sc.pl.dpt_groups_pseudotime(
-    @CMD_param_plot_inputs@
-    #if $method.color_map
-    color_map='$method.color_map'
-    #end if
-    )
 
-#else if $method.method == 'pl.dpt_timeseries'
+#else if str($method.method) == 'pl.dpt_timeseries':
 sc.pl.dpt_timeseries(
-    @CMD_param_plot_inputs@
-    #if $method.heatmap.as_heatmap == "True"
+    @CMD_PARAM_PLOT_INPUTS@
+    #if str($method.heatmap.as_heatmap) == 'True'
         #if $method.heatmap.color_map
     color_map='$method.heatmap.color_map',
         #end if
     #end if
-    as_heatmap=$method.heatmap.as_heatmap)
+    as_heatmap=$method.heatmap.as_heatmap,
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.paga'
+#else if str($method.method) == 'pl.paga':
 sc.pl.paga(
-    @CMD_param_plot_inputs@
-    @CMD_params_pl_paga@)
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAMS_PL_PAGA@
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.paga_compare'
+#else if str($method.method) == 'pl.paga_compare':
 sc.pl.paga_compare(
-    @CMD_param_plot_inputs@
-    @CMD_params_pl_paga@)
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAMS_PL_PAGA@
+    @CMD_PARAM_PL_COMPONENTS@
+    projection='$method.plot.projection',
+    #if str($method.plot.legend_loc) != '':
+    legend_loc='$method.plot.legend_loc',
+    #end if
+    @CMD_PARAM_LEGEND_FONTSIZE@
+    legend_fontweight='$method.plot.legend_fontweight',
+    #if $method.plot.color_map:
+    color_map='$method.plot.color_map',
+    #end if   
+    #if $method.plot.palette:
+    palette=['$method.plot.palette'],
+    #end if
+    @CMD_PARAM_SIZE@
+    @CMD_PARAM_TITLE@
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.paga_path'
+#else if str($method.method) == 'pl.paga_path':
 sc.pl.paga_path(
-    @CMD_param_plot_inputs@
+    @CMD_PARAM_PLOT_INPUTS@
     #set $nodes = ([int(x.strip()) for x in str($method.nodes).split(',')])
     nodes=$nodes,
     #set $keys=([x.strip() for x in str($method.keys).split(',')])
     keys=$keys,
     use_raw=$method.use_raw,
-    #if $method.annotations
+    #if str($method.annotations) != '':
         #set $annotations=([x.strip() for x in str($method.annotations).split(',')])
     annotations=$annotations,
     #end if
-    #if $method.color_map
+    #if $method.color_map:
     color_map='$method.color_map',
     #end if
     n_avg=$method.n_avg,
-    #if $method.annotations
+    #if str($method.annotations) != '':
     groups_key='$method.groups_key',
     #end if
     as_heatmap=$method.as_heatmap,
     show_node_names=$method.show_node_names,
     show_colorbar=$method.show_colorbar,
     show_yticks=$method.show_yticks,
-    normalize_to_zero_one=$method.normalize_to_zero_one)
+    normalize_to_zero_one=$method.normalize_to_zero_one,
+    @CMD_SHOW_NONE@)
 
-#else if $method.method == 'pl.rank_genes_groups'
+#else if str($method.method) == 'pl.rank_genes_groups':
 sc.pl.rank_genes_groups(
-    @CMD_param_plot_inputs@
-    @CMD_params_groups@
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_GROUPS@
     n_genes=$method.n_genes,
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
+    @CMD_PARAM_GENE_SYMBOLS@
     fontsize=$method.fontsize,
     ncols=$method.ncols,
-    sharey=$method.sharey)
+    sharey=$method.sharey,
+    @CMD_SHOW_NONE@)
 
 #else if $method.method == 'pl.rank_genes_groups_violin'
 sc.pl.rank_genes_groups_violin(
-    @CMD_param_plot_inputs@
-    @CMD_params_groups@
-    #if $method.genes.select == 'n_genes'
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PARAM_GROUPS@
+    #if str($method.genes.select) == 'n_genes':
     n_genes=$method.genes.n_genes,
     #else
         #set $gene_names = ([x.strip() for x in str($method.genes.gene_names).split(',')])
     gene_names=$gene_names,
     #end if
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
+    @CMD_PARAM_GENE_SYMBOLS@
     use_raw=$method.use_raw,
     split=$method.split,
     strip=$method.violin_plot.stripplot.stripplot,
-    #if $method.violin_plot.stripplot.stripplot == "True"
+    #if str($method.violin_plot.stripplot.stripplot) == 'True':
     jitter=$method.violin_plot.stripplot.jitter.jitter,
-        #if $method.violin_plot.stripplot.jitter.jitter == "True"
+        #if str($method.violin_plot.stripplot.jitter.jitter) == 'True':
     size=$method.violin_plot.stripplot.jitter.size,
         #end if
     #end if
-    scale='$method.violin_plot.scale')
-
-#else if $method.method == 'pl.rank_genes_groups_dotplot'
+    density_norm='$method.violin_plot.density_norm',
+    @CMD_SHOW_NONE@)
 
-@CMD_var_names_header_check@
-
-sc.pl.rank_genes_groups_dotplot(
-    @CMD_param_plot_inputs@
-    #if $method.var_names.type == 'custom'
-    #set $var_names = ([x.strip() for x in str($method.var_names.var_names).split(',')])
-    var_names=$var_names,
-    #else if $method.var_names.type == 'customfile'
-    var_names={key: [v for v in list(value.values()) if pd.notna(v)] for key, value in pd.read_csv('$var_names', sep='\t', index_col=0, header=header).to_dict(orient='index').items()},
-    #else
-    n_genes=$method.n_genes,
-    #end if
-    #if $method.groupby != ''
-    groupby='$method.groupby',
-    #end if
-    num_categories=$method.num_categories,
-    #if $method.key != ''
-    key='$method.key',
-    #end if
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_params_plots@
-    @CMD_pl_dotplot@)
-
-#else if $method.method == 'pl.rank_genes_groups_heatmap'
+#else if str($method.method) == 'pl.rank_genes_groups_stacked_violin':
+@CMD_VAR_NAMES_HEADER_CHECK@
+sc.pl.rank_genes_groups_stacked_violin(
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PL_RANK_GENES_GROUPS_EXT@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PL_STACKED_VIOLIN@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.rank_genes_groups_heatmap':
+@CMD_VAR_NAMES_HEADER_CHECK@
 sc.pl.rank_genes_groups_heatmap(
-    @CMD_param_plot_inputs@
-    @CMD_pl_rank_genes_groups_ext@
-    @CMD_params_plots@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_pl_heatmap@)
-
-#else if $method.method == 'pl.rank_genes_groups_matrixplot'
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PL_RANK_GENES_GROUPS_EXT@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PL_HEATMAP@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.rank_genes_groups_dotplot':
+@CMD_VAR_NAMES_HEADER_CHECK@
+sc.pl.rank_genes_groups_dotplot(
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PL_RANK_GENES_GROUPS_EXT@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PL_DOTPLOT@
+    @CMD_VALUES_TO_PLOT@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.rank_genes_groups_matrixplot':
+@CMD_VAR_NAMES_HEADER_CHECK@
 sc.pl.rank_genes_groups_matrixplot(
-    @CMD_param_plot_inputs@
-    @CMD_pl_rank_genes_groups_ext@
-    @CMD_params_plots@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_pl_matrixplot@)
-
-#else if $method.method == 'pl.rank_genes_groups_stacked_violin'
-sc.pl.rank_genes_groups_stacked_violin(
-    @CMD_param_plot_inputs@
-    @CMD_pl_rank_genes_groups_ext@
-    @CMD_params_plots@
-    #if $method.gene_symbols
-    gene_symbols='$method.gene_symbols',
-    #end if
-    @CMD_pl_stacked_violin@)
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PL_RANK_GENES_GROUPS_EXT@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PL_MATRIXPLOT@
+    @CMD_VALUES_TO_PLOT@
+    @CMD_SHOW_NONE@)
+
+#else if str($method.method) == 'pl.rank_genes_groups_tracksplot':
+@CMD_VAR_NAMES_HEADER_CHECK@
+sc.pl.rank_genes_groups_tracksplot(
+    @CMD_PARAM_PLOT_INPUTS@
+    @CMD_PL_RANK_GENES_GROUPS_EXT@
+    @CMD_PARAMS_PLOTS@
+    @CMD_PARAM_GENE_SYMBOLS@
+    @CMD_PARAMS_PL_HEATMAP@
+    @CMD_SHOW_NONE@)
 
 #end if
 ]]></configfile>
@@ -470,13 +510,14 @@ sc.pl.rank_genes_groups_stacked_violin(
                 <option value="pl.scatter">Generic: Scatter plot along observations or variables axes, using 'pl.scatter'</option>
                 <option value="pl.heatmap">Generic: Heatmap of the expression values of set of genes, using 'pl.heatmap'</option>
                 <option value="pl.dotplot">Generic: Makes a dot plot of the expression values, using 'pl.dotplot'</option>
+                <option value="pl.tracksplot">Generic: Makes a tracks plot of the expression values per cell, using 'pl.tracksplot'</option>
                 <option value="pl.violin">Generic: Violin plot, using 'pl.violin'</option>
                 <option value="pl.stacked_violin">Generic: Stacked violin plots, using 'pl.stacked_violin'</option>
                 <option value="pl.matrixplot">Generic: Heatmap of the mean expression values per cluster, using 'pl.matrixplot'</option>
                 <option value="pl.clustermap">Generic: Hierarchically-clustered heatmap, using 'pl.clustermap'</option>
                 <option value="pl.highest_expr_genes">Preprocessing: Plot the fraction of counts assigned to each gene over all cells, using 'pl.highest_expr_genes'</option>
-                <!--<option value="pl.filter_genes_dispersion">Preprocessing: Plot dispersions versus means for genes, using 'pl.filter_genes_dispersion'</option>-->
                 <option value="pl.highly_variable_genes">Preprocessing: Plot dispersions versus means for genes, using 'pl.highly_variable_genes'</option>
+                <option value="pl.scrublet_score_distribution">Preprocessing: Plot histogram of doublet scores, using 'pl.scrublet_score_distribution'</option>
                 <option value="pl.pca">PCA: Scatter plot in PCA coordinates, using 'pl.pca'</option>
                 <option value="pl.pca_loadings">PCA: Rank genes according to contributions to PCs, using 'pl.pca_loadings'</option>
                 <option value="pl.pca_variance_ratio">PCA: Scatter plot in PCA coordinates, using 'pl.pca_variance_ratio'</option>
@@ -486,57 +527,59 @@ sc.pl.rank_genes_groups_stacked_violin(
                 <option value="pl.diffmap">Embeddings: Scatter plot in Diffusion Map basis, using 'pl.diffmap'</option>
                 <option value="pl.draw_graph">Embeddings: Scatter plot in graph-drawing basis, using 'pl.draw_graph'</option>
                 <option value="pl.embedding_density">Embeddings: Plot the density of cells in an embedding (per condition), using 'pl.embedding_density'</option>
-                <option value="pl.dpt_groups_pseudotime">Branching trajectories and pseudotime, clustering: Plot groups and pseudotime, using 'pl.dpt_groups_pseudotime'</option>
+                <!-- This function is commented out because it is not compatible with pandas version. If the issue is not resolved in the next update, this should be removed. -->
+                <!-- <option value="pl.dpt_groups_pseudotime">Branching trajectories and pseudotime, clustering: Plot groups and pseudotime, using 'pl.dpt_groups_pseudotime'</option> -->
                 <option value="pl.dpt_timeseries">Branching trajectories and pseudotime, clustering: Heatmap of pseudotime series, using 'pl.dpt_timeseries'</option>
                 <option value="pl.paga">Branching trajectories and pseudotime, clustering: Plot the abstracted graph through thresholding low-connectivity edges, using 'pl.paga'</option>
                 <option value="pl.paga_compare">Branching trajectories and pseudotime, clustering: Scatter and PAGA graph side-by-side, using 'pl.paga_compare'</option>
                 <option value="pl.paga_path">Branching trajectories and pseudotime, clustering: Gene expression and annotation changes along paths, using 'pl.paga_path'</option>
                 <option value="pl.rank_genes_groups">Marker genes: Plot ranking of genes using dotplot plot, using 'pl.rank_genes_groups'</option>
                 <option value="pl.rank_genes_groups_violin">Marker genes: Plot ranking of genes as violin plot, using 'pl.rank_genes_groups_violin'</option>
-                <option value="pl.rank_genes_groups_dotplot">Marker genes: Plot ranking of genes as dotplot plot, using 'pl.rank_genes_groups_dotplot'</option>
+                <option value="pl.rank_genes_groups_stacked_violin">Marker genes: Plot ranking of genes as stacked violin plot, using 'pl.rank_genes_groups_stacked_violin'</option>
                 <option value="pl.rank_genes_groups_heatmap">Marker genes: Plot ranking of genes as heatmap plot, using 'pl.rank_genes_groups_heatmap'</option>
+                <option value="pl.rank_genes_groups_dotplot">Marker genes: Plot ranking of genes as dotplot plot, using 'pl.rank_genes_groups_dotplot'</option>
                 <option value="pl.rank_genes_groups_matrixplot">Marker genes: Plot ranking of genes as matrixplot plot, using 'pl.rank_genes_groups_matrixplot'</option>
-                <option value="pl.rank_genes_groups_stacked_violin">Marker genes: Plot ranking of genes as stacked violin plot, using 'pl.rank_genes_groups_stacked_violin'</option>
+                <option value="pl.rank_genes_groups_tracksplot">Marker genes: Plot ranking of genes as tracksplot plot, using 'pl.rank_genes_groups_tracksplot'</option>
             </param>
             <when value="pl.scatter">
                 <conditional name="type">
-                    <param name="type" type="select" label="Plotting tool that computed coordinates" help="">
-                        <option value="xy">Using coordinates</option>
+                    <param name="type" type="select" label="Plotting tool that computed coordinates">
+                        <option value="xy" selected="true">Using coordinates</option>
                         <option value="basis">Using tool that computes coordinates</option>
                     </param>
                     <when value="xy">
                         <param argument="x" type="text" value="" label="x coordinate" help="Index or key from either '.obs' or '.var'">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                         <param argument="y" type="text" value="" label="y coordinate" help="Index or key from either '.obs' or '.var'">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                         <expand macro="param_log"/>
                         <param argument="color" type="text" value="" label="Color by" help="Color points by single variable in `.obs` or `.var`">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                         <conditional name="layers">
                             <param argument="use_layers" type="select" label="Use the layers attribute?">
-                                <option value="true">Yes</option>
                                 <option value="false" selected="true">No</option>
+                                <option value="true">Yes</option>
                             </param>
                             <when value="true">
                                 <param argument="layer_x" type="text" value="" optional="true" label="Layers for x coordinate" help="Use the 'layers' attribute of 'adata' if present">
-                                    <expand macro="sanitize_query" />
+                                    <expand macro="sanitize_query"/>
                                 </param>
                                 <param argument="layer_y" type="text" value="" optional="true" label="Layers for y coordinate" help="Use the 'layers' attribute of 'adata' if present">
-                                    <expand macro="sanitize_query" />
+                                    <expand macro="sanitize_query"/>
                                 </param>
                                 <param argument="layer_color" type="text" value="" optional="true" label="Layers for color" help="Use the 'layers' attribute of 'adata' if present">
-                                    <expand macro="sanitize_query" />
+                                    <expand macro="sanitize_query"/>
                                 </param>
                             </when>
                             <when value="false"/>
                         </conditional>
                     </when>
                     <when value="basis">
-                        <param argument="basis" type="select" label="Plotting tool that computes coordinates" help="">
-                            <option value="pca">pca (need to run on 'tl.pca' output)</option>
+                        <param argument="basis" type="select" label="Plotting tool that computes coordinates">
+                            <option value="pca">pca (need to run on 'pl.pca' output)</option>
                             <option value="tsne">tsne (need to run on 'tl.tsne' output)</option>
                             <option value="umap">umap (need to run on 'tl.umap' output)</option>
                             <option value="diffmap">diffmap (need to run on 'tl.diffmap' output)</option>
@@ -545,11 +588,11 @@ sc.pl.rank_genes_groups_stacked_violin(
                         <expand macro="param_color"/>
                     </when>
                 </conditional>
-                <expand macro="param_use_raw"/>
+                <expand macro="param_use_raw" falsevalue="None"/>
                 <param argument="sort_order" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Plot data points with higher values on top of others?" help="For continuous annotations used as color parameter"/>
                 <expand macro="param_groups"/>
                 <section name="plot" title="Plot attributes">
-                    <expand macro="pl_components"/>
+                    <expand macro="param_pl_components"/>
                     <expand macro="param_projection"/>
                     <expand macro="param_legend_loc"/>
                     <expand macro="param_legend_fontsize"/>
@@ -563,20 +606,25 @@ sc.pl.rank_genes_groups_stacked_violin(
             </when>
             <when value="pl.heatmap">
                 <expand macro="params_inputs"/>
-                <expand macro="gene_symbols"/>
+                <expand macro="param_gene_symbols"/>
                 <expand macro="params_plots"/>
-                <expand macro="pl_heatmap"/>
+                <expand macro="params_pl_heatmap"/>
             </when>
             <when value="pl.dotplot">
                 <expand macro="params_inputs"/>
-                <expand macro="gene_symbols"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="params_plots"/>
+                <expand macro="params_pl_dotplot"/>
+            </when>
+            <when value="pl.tracksplot">
+                <expand macro="params_inputs"/>
+                <expand macro="param_gene_symbols"/>
                 <expand macro="params_plots"/>
-                <expand macro="pl_dotplot"/>
             </when>
             <when value="pl.violin">
                 <conditional name="key_variables">
                     <param name="type" type="select" label="Keys for accessing variables">
-                        <option value="var_names">All variables in '.var_names'</option>
+                        <option value="var_names" selected="true">All variables in '.var_names'</option>
                         <option value="obs">All fields in '.obs'</option>
                         <option value="custom">Subset of variables in 'adata.var_names' or fields of '.obs'</option>
                     </param>
@@ -584,56 +632,56 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <when value="obs"/>
                     <when value="custom">
                         <param argument="keys" type="text" value="" label="Keys for accessing variables" help="One or a list of comma-separated index or key from '.var_names' or fields of '.obs'">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                     </when>
                 </conditional>
                 <expand macro="param_groupby"/>
                 <expand macro="param_log"/>
-                <expand macro="param_use_raw"/>
+                <expand macro="param_use_raw" falsevalue="None"/>
                 <section name="violin_plot" title="Violin plot attributes">
                     <expand macro="conditional_stripplot"/>
                     <conditional name="multi_panel">
                         <param argument="multi_panel" type="select" label="Display keys in multiple panels" help="Also when 'groupby is not provided">
+                            <option value="None" selected="true">No</option>                            
                             <option value="True">Yes</option>
-                            <option value="False" selected="true">No</option>
                         </param>
+                        <when value="None"/>
                         <when value="True">
-                            <param argument="width" type="integer" min="0" value="" optional="true" label="Width of the figure" help=""/>
-                            <param argument="height" type="integer" min="0" value="" optional="true" label="Height of the figure" help=""/>
+                            <!-- <param argument="width" type="integer" min="0" value="" optional="true" label="Width of the figure"/>
+                            <param argument="height" type="integer" min="0" value="" optional="true" label="Height of the figure"/> -->
                         </when>
-                        <when value="False"/>
                     </conditional>
-                    <expand macro="param_scale"/>
                 </section>
                 <param argument="xlabel" type="text" value="" optional="true" label="Label of the x axis" help="Defaults to 'groupby' if 'rotation' is 'None',    otherwise, no label is shown.">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
-                <param argument="rotation" type="float" value="" optional="true" label="Rotation of xtick labels" help=""/>
-                <expand macro="seaborn_violinplot"/>
+                <param argument="rotation" type="float" value="" optional="true" label="Rotation of xtick labels"/>
+                <expand macro="params_seaborn_violinplot"/>
+                <expand macro="param_layer"/>
             </when>
             <when value="pl.stacked_violin">
                 <expand macro="params_inputs"/>
-                <expand macro="gene_symbols"/>
+                <expand macro="param_gene_symbols"/>
                 <expand macro="params_plots"/>
-                <expand macro="pl_stacked_violin"/>
+                <expand macro="params_pl_stacked_violin"/>
             </when>
             <when value="pl.matrixplot">
                 <expand macro="params_inputs"/>
-                <expand macro="gene_symbols"/>
+                <expand macro="param_gene_symbols"/>
                 <expand macro="params_plots"/>
-                <expand macro="pl_matrixplot"/>
+                <expand macro="params_pl_matrixplot"/>
             </when>
             <when value="pl.clustermap">
                 <param argument="obs_keys" type="text" value="" optional="true" label="Categorical annotation to plot with a different color map" help="Currently, only a single key is supported.">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <expand macro="param_use_raw"/>
                 <section name="seaborn_clustermap" title="Parameters for seaborn.clustermap">
                     <param name="method" type="select" label="Linkage method to use for calculating clusters" help="More details in https://docs.scipy.org/doc/scipy/reference/generated/scipy.cluster.hierarchy.linkage.html">
+                        <option value="average" selected="true">average: UPGMA algorithm</option>
                         <option value="single">single: Nearest Point Algorithm</option>
                         <option value="complete">complete: Farthest Point Algorithm or Voor Hees Algorithm</option>
-                        <option value="average">average: UPGMA algorithm</option>
                         <option value="weighted">weighted: WPGMA algorithm</option>
                         <option value="centroid">centroid: UPGMC algorithm</option>
                         <option value="median">median: WPGMC algorithm</option>
@@ -643,53 +691,71 @@ sc.pl.rank_genes_groups_stacked_violin(
                         <expand macro="distance_metric_options"/>
                     </param>
                     <param name="z_score" type="select" label="Calculate z-scores for the rows or the columns?" help="Z scores are: z = (x - mean)/std, so values in each row (column) will get the mean of the row (column) subtracted, then divided by the standard deviation of the row (column). This ensures that each row (column) has mean of 0 and variance of 1.">
-                        <option value="None">No Z-score</option>
+                        <option value="None" selected="true">No Z-score</option>
                         <option value="0">Rows</option>
                         <option value="1">Columns</option>
                     </param>
                     <param name="standard_scale" type="select" label="Standardize a dimension?" help="It means for each row or column, subtract the minimum and divide each by its maximum.">
-                        <option value="None">No standardization</option>
+                        <option value="None" selected="true">No standardization</option>
                         <option value="0">Rows</option>
                         <option value="1">Columns</option>
                     </param>
-                    <param name="col_cluster" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Cluster the columns?" help=""/>
-                    <param name="row_cluster" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Cluster the rows?" help=""/>
+                    <param name="col_cluster" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Cluster the columns?"/>
+                    <param name="row_cluster" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Cluster the rows?"/>
                 </section>
             </when>
-            <when value="pl.highly_variable_genes">
-                <expand macro="param_log"/>
-                <param argument="highly_variable_genes" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Plot highly variable genes or gene subset?"/>
-            </when>
             <when value="pl.highest_expr_genes">
-                <param argument="n_top" type="integer" min="0" value="30" label="Number of top genes" help=""/>
-                <param argument="gene_symbols" type="text" optional="true" label="Key for field in '.var' that stores gene symbols" help="Fill it if you do not want to use '.var_names'.">
-                    <expand macro="sanitize_query" />
-                </param>
+                <param argument="n_top" type="integer" min="0" value="30" label="Number of top genes"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="param_log"/>
                 <section name="setseaborn_boxplot" title="Plot settings" expanded="false">
-                    <param argument="color" type="text" value="" optional="true" label="Color for all of the elements, or seed for a gradient palette" help="">
-                        <expand macro="sanitize_query" />
+                    <param argument="color" type="text" value="" optional="true" label="Color for all of the elements, or seed for a gradient palette">
+                        <expand macro="sanitize_query"/>
                     </param>
                     <param argument="palette" type="select" optional="true" label="Colors to use for the different levels of the hue variable" help="See https://seaborn.pydata.org/tutorial/color_palettes.html for more details.">
                         <expand macro="seaborn_color_palette_options"/>
                     </param>
-                    <param argument="saturation" type="float" value="1" label="Proportion of the original saturation to draw colors at" help="Large patches often look better with slightly desaturated colors, but set this to 1 if you want the plot colors to perfectly match the input color spec."/>
+                    <param argument="saturation" type="float" value="0.75" label="Proportion of the original saturation to draw colors at" help="Large patches often look better with slightly desaturated colors, but set this to 1 if you want the plot colors to perfectly match the input color spec."/>
                 </section>
             </when>
+            <when value="pl.highly_variable_genes">
+                <expand macro="param_log"/>
+                <param argument="highly_variable_genes" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Plot highly variable genes or gene subset?"/>
+            </when>
+            <when value="pl.scrublet_score_distribution">
+                <param name="scale_hist_obs" type="select" label="Set y axis scale transformation in matplotlib for the plot of observed transcriptomes">
+                    <option value="log" selected="true">log</option>
+                    <option value="linear">linear</option>
+                    <option value="symlog">symlog</option>
+                    <option value="logit">logit</option>
+                </param>
+                <param name="scale_hist_sim" type="select" label="Set y axis scale transformation in matplotlib for the plot of simulated doublets">
+                    <option value="linear" selected="true">linear</option>
+                    <option value="log">log</option>
+                    <option value="symlog">symlog</option>
+                    <option value="logit">logit</option>
+                </param>
+                <expand macro="pl_figsize"/>
+            </when>
             <when value="pl.pca">
                 <expand macro="param_color"/>
                 <expand macro="param_use_raw"/>
                 <expand macro="param_sort_order"/>
                 <expand macro="param_groups"/>
-                <expand macro="pl_attribute_section"/>
+                <expand macro="params_pl_attribute_section"/>
+                <expand macro="params_scatter_outine"/>
                 <expand macro="section_matplotlib_pyplot_scatter"/>
+                <expand macro="param_layer"/>
             </when>
             <when value="pl.pca_loadings">
                 <param argument="components" type="text" value="1,2,3" label="List of comma-separated components" help="1, 2, 3 means first, second and third principal components">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
+                <param argument="include_lowest" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Show the variables with both highest and lowest loadings"/>
+                <param argument="n_points" type="integer" value="" optional="true" label="Number of variables to plot for each component"/>
             </when>
             <when value="pl.pca_variance_ratio">
-                <param argument="n_pcs" type="integer" min="0" value="30" label="Number of PCs to show" help=""/>
+                <param argument="n_pcs" type="integer" min="0" value="30" label="Number of PCs to show"/>
                 <expand macro="param_log"/>
             </when>
             <when value="pl.pca_overview">
@@ -697,18 +763,22 @@ sc.pl.rank_genes_groups_stacked_violin(
                 <expand macro="param_use_raw"/>
                 <expand macro="param_sort_order"/>
                 <expand macro="param_groups"/>
-                <expand macro="pl_attribute_section"/>
+                <expand macro="params_pl_attribute_section"/>
+                <expand macro="params_scatter_outine"/>
                 <expand macro="section_matplotlib_pyplot_scatter"/>
             </when>
             <when value="pl.tsne">
                 <expand macro="param_color"/>
+                <expand macro="param_gene_symbols"/>
                 <expand macro="param_use_raw"/>
                 <expand macro="pl_edges"/>
                 <expand macro="param_arrows"/>
                 <expand macro="param_sort_order"/>
                 <expand macro="param_groups"/>
-                <expand macro="pl_attribute_section"/>
+                <expand macro="params_pl_attribute_section"/>
+                <expand macro="params_scatter_outine"/>
                 <expand macro="section_matplotlib_pyplot_scatter"/>
+                <expand macro="param_layer"/>
             </when>
             <when value="pl.umap">
                 <expand macro="param_color"/>
@@ -717,44 +787,50 @@ sc.pl.rank_genes_groups_stacked_violin(
                 <expand macro="param_arrows"/>
                 <expand macro="param_sort_order"/>
                 <expand macro="param_groups"/>
-                <expand macro="pl_attribute_section"/>
+                <expand macro="params_pl_attribute_section"/>
+                <expand macro="params_scatter_outine"/>
                 <expand macro="section_matplotlib_pyplot_scatter"/>
+                <expand macro="param_layer"/>
             </when>
             <when value="pl.diffmap">
                 <expand macro="param_color"/>
                 <expand macro="param_use_raw"/>
                 <expand macro="param_sort_order"/>
                 <expand macro="param_groups"/>
-                <expand macro="pl_attribute_section"/>
+                <expand macro="params_pl_attribute_section"/>
+                <expand macro="params_scatter_outine"/>
                 <expand macro="section_matplotlib_pyplot_scatter"/>
+                <expand macro="param_layer"/>
             </when>
             <when value="pl.draw_graph">
                 <expand macro="param_color"/>
-                <expand macro="gene_symbols"/>
+                <expand macro="param_gene_symbols"/>
                 <expand macro="param_use_raw"/>
-                <param argument="layout" type="select" optional="false" label="Plotting layout" help="">
+                <param argument="layout" type="select" optional="false" label="Plotting layout">
                     <expand macro="options_layout"/>
                 </param>
                 <expand macro="pl_edges"/>
                 <expand macro="param_arrows"/>
                 <expand macro="param_sort_order"/>
                 <expand macro="param_groups"/>
-                <expand macro="pl_attribute_section"/>
+                <expand macro="params_pl_attribute_section"/>
+                <expand macro="params_scatter_outine"/>
                 <expand macro="section_matplotlib_pyplot_scatter"/>
+                <expand macro="param_layer"/>
             </when>
             <when value="pl.embedding_density">
                 <param argument="basis" type="text" value="umap" label="The embedding over which the density was calculated." help="This embedded representation should be found in adata.obsm['X_[basis]']">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="key" type="text" optional="true" value="" label="Name of the .obs covariate that contains the density estimates" help="Alternatively, pass _groupby_.">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="groupby" type="text" optional="true" value="" label="Name of the condition used in tl.embedding_density" help="Alternatively, pass _key_.">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
-                <param argument="group" type="text" optional="all" value="" label="The category in the categorical observation annotation to be plotted" 
+                <param argument="group" type="text" optional="all" value="" label="The category in the categorical observation annotation to be plotted"
                     help="For example, 'G1' in the cell cycle 'phase' covariate. If multiple categories want to be plotted use a comma separated list">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <expand macro="param_color_map"/>
                 <param argument="bg_dotsize" type="integer" min="0" value="80" label="Dot size for background data points not in the group"/>
@@ -763,43 +839,58 @@ sc.pl.rank_genes_groups_stacked_violin(
                 <expand macro="param_wspace"/>
                 <expand macro="param_hspace"/>
             </when>
-            <when value="pl.dpt_groups_pseudotime">
+            <!-- This function is commented out because it is not compatible with pandas version. If the issue is not resolved in the next update, this should be removed. -->
+            <!-- <when value="pl.dpt_groups_pseudotime">
                 <expand macro="param_color_map"/>
-            </when>
+            </when> -->
             <when value="pl.dpt_timeseries">
                 <conditional name="heatmap">
-                    <param argument="as_heatmap" type="select" label="Plot the timeseries as heatmap?" help="">
-                        <option value="True">Yes</option>
+                    <param argument="as_heatmap" type="select" label="Plot the timeseries as heatmap?">
+                        <option value="True" selected="true">Yes</option>
                         <option value="False">No</option>
                     </param>
                     <when value="True">
                         <expand macro="param_color_map"/>
                     </when>
-                    <when value="False" />
+                    <when value="False"/>
                 </conditional>
             </when>
             <when value="pl.paga">
-                <expand macro="inputs_paga"/>
+                <expand macro="params_pl_paga"/>
             </when>
             <when value="pl.paga_compare">
-                <expand macro="inputs_paga"/>
+                <expand macro="params_pl_paga"/>
+                <section name="plot" title="Plot attributes">
+                    <expand macro="param_pl_components"/>
+                    <expand macro="param_projection"/>
+                    <expand macro="param_legend_loc">
+                        <option value="on data">on data</option>
+                        <option value="right margin">right margin</option>
+                    </expand>
+                    <expand macro="param_legend_fontsize"/>
+                    <expand macro="param_legend_fontweight"/>
+                    <expand macro="param_color_map"/>
+                    <expand macro="param_palette"/>
+                    <expand macro="param_frameon"/>
+                    <expand macro="param_size"/>
+                    <expand macro="param_title"/>
+                </section>
             </when>
             <when value="pl.paga_path">
-                <param argument="nodes" type="text" value="" label="A path through nodes of the abstracted graph"
-                       help="Each node is represented by its indice (within .categories) for the groups that have been used to run PAGA. Comma-separated">
-                    <expand macro="sanitize_query" />
+                <param argument="nodes" type="text" value="" label="A path through nodes of the abstracted graph" help="Each node is represented by its indice (within .categories) for the groups that have been used to run PAGA. Comma-separated">
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="keys" type="text" value="" label="Keys for accessing variables" help="One or a list of comma-separated index or key from '.var_names' or fields of '.obs'">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <expand macro="param_use_raw"/>
-                <param argument="annotations" type="text" value="" optional="true" label="Key to plot" help="Keys for obs, comma-separated">
-                    <expand macro="sanitize_query" />
+                <param argument="annotations" type="text" value="dpt_pseudotime" optional="true" label="Key to plot" help="Keys for obs, comma-separated">
+                    <expand macro="sanitize_query"/>
                 </param>
                 <expand macro="param_color_map"/>
                 <param argument="n_avg" type="integer" value="1" label="Number of data points to include in computation of running average"/>
                 <param argument="groups_key" type="text" value="" optional="true" label="Key of the grouping used to run PAGA" help="If not set, use uns/page/groups">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="as_heatmap" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Plot the timeseries as heatmap?" help="If not, annotations have no effect."/>
                 <param argument="show_node_names" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Plot the node names on the nodes bar?"/>
@@ -809,8 +900,8 @@ sc.pl.rank_genes_groups_stacked_violin(
             </when>
             <when value="pl.rank_genes_groups">
                 <expand macro="param_groups"/>
-                <expand macro="param_n_genes"/>
-                <expand macro="gene_symbols"/>
+                <expand macro="param_n_genes" value="20"/>
+                <expand macro="param_gene_symbols"/>
                 <param argument="fontsize" type="integer" min="0" value="8" label="Font size for gene names"/>
                 <expand macro="param_ncols"/>
                 <param argument="sharey" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Should the y-axis of each panels be shared?" help="If not, each panel has its own y-axis range"/>
@@ -818,51 +909,62 @@ sc.pl.rank_genes_groups_stacked_violin(
             <when value="pl.rank_genes_groups_violin">
                 <expand macro="param_groups"/>
                 <conditional name="genes">
-                    <param argument="select" type="select" label="Which genes to plot?" help="">
-                        <option value="n_genes">A number of genes</option>
+                    <param argument="select" type="select" label="Which genes to plot?">
+                        <option value="n_genes" selected="true">A number of genes</option>
                         <option value="gene_names">A custom list of genes</option>
                     </param>
                     <when value="n_genes">
-                        <expand macro="param_n_genes"/>
+                        <expand macro="param_n_genes" value="20"/>
                     </when>
                     <when value="gene_names">
                         <param argument="gene_names" type="text" value="" label="List of genes to plot" help="A list of comma-separated names">
-                            <expand macro="sanitize_query" />
+                            <expand macro="sanitize_query"/>
                         </param>
                     </when>
                 </conditional>
-                <expand macro="gene_symbols"/>
-                <expand macro="param_use_raw"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="param_use_raw" falsevalue="None"/>
                 <param argument="split" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Split the violins?"/>
                 <section name="violin_plot" title="Violin plot attributes">
                     <expand macro="conditional_stripplot"/>
-                    <expand macro="param_scale"/>
+                    <param argument="density_norm" type="select" label="Method used to scale the width of each violin">
+                        <option value="width" selected="true">width: each violin will have the same width</option>
+                        <option value="area">area: each violin will have the same area</option>
+                        <option value="count">count: the width of the violins will be scaled by the number of observations in that bin</option>
+                    </param>
                 </section>
             </when>
-            <when value="pl.rank_genes_groups_dotplot">
-                <expand macro="params_inputs"/>
+            <when value="pl.rank_genes_groups_stacked_violin">
                 <expand macro="pl_rank_genes_groups_ext"/>
                 <expand macro="params_plots"/>
-                <expand macro="gene_symbols"/>
-                <expand macro="pl_dotplot"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="params_pl_stacked_violin"/>
             </when>
             <when value="pl.rank_genes_groups_heatmap">
                 <expand macro="pl_rank_genes_groups_ext"/>
                 <expand macro="params_plots"/>
-                <expand macro="gene_symbols"/>
-                <expand macro="pl_heatmap"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="params_pl_heatmap"/>
+            </when>
+            <when value="pl.rank_genes_groups_dotplot">
+                <expand macro="pl_rank_genes_groups_ext"/>
+                <expand macro="params_plots"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="params_pl_dotplot"/>
+                <expand macro="values_to_plot"/>
             </when>
             <when value="pl.rank_genes_groups_matrixplot">
                 <expand macro="pl_rank_genes_groups_ext"/>
                 <expand macro="params_plots"/>
-                <expand macro="gene_symbols"/>
-                <expand macro="pl_matrixplot"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="params_pl_matrixplot"/>
+                <expand macro="values_to_plot"/>
             </when>
-            <when value="pl.rank_genes_groups_stacked_violin">
+            <when value="pl.rank_genes_groups_tracksplot">
                 <expand macro="pl_rank_genes_groups_ext"/>
                 <expand macro="params_plots"/>
-                <expand macro="gene_symbols"/>
-                <expand macro="pl_stacked_violin"/>
+                <expand macro="param_gene_symbols"/>
+                <expand macro="params_pl_heatmap"/>
             </when>
         </conditional>
         <expand macro="inputs_common_advanced"/>
@@ -894,9 +996,9 @@ sc.pl.rank_genes_groups_stacked_violin(
         </data>
     </outputs>
     <tests>
+        <!-- test 1 -->
         <test expect_num_outputs="2">
-            <!-- test 1: pl.scatter -->
-            <param name="adata" value="pbmc68k_reduced.h5ad" />
+            <param name="adata" value="pbmc68k_reduced.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.scatter"/>
@@ -906,30 +1008,25 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <param name="color" value="HES4"/>
                 </conditional>
                 <param name="use_raw" value="True"/>
-                <param name="sort_order" value="True"/>
                 <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontsize" value="1"/>
                     <param name="legend_fontweight" value="normal"/>
                     <param name="color_map" value="inferno"/>
                     <param name="palette" value="inferno"/>
-                    <param name="frameon" value="True"/>
                     <param name="size" value="1"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.scatter"/>
-                    <has_text_matching expression="basis='umap'" />
+                    <has_text_matching expression="basis='umap'"/>
                     <has_text_matching expression="color=\['HES4'\]"/>
                     <has_text_matching expression="use_raw=True"/>
                     <has_text_matching expression="sort_order=True"/>
                     <has_text_matching expression="projection='2d'"/>
-                    <has_text_matching expression="legend_loc='right margin'"/>
                     <has_text_matching expression="legend_fontsize=1"/>
                     <has_text_matching expression="legend_fontweight='normal'"/>
                     <has_text_matching expression="color_map='inferno'"/>
@@ -937,11 +1034,12 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="size=1.0"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.scatter.umap.pbmc68k_reduced.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.scatter.umap.pbmc68k_reduced.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 2 -->
         <test expect_num_outputs="2">
-            <!-- test 2: pl.scatter -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.scatter"/>
@@ -949,81 +1047,102 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <param name="type" value="xy"/>
                     <param name="x" value="EKLF"/>
                     <param name="y" value="Cebpa"/>
-                    <conditional name="layers">
-                        <param name="use_layers" value="false"/>
-                    </conditional>
                 </conditional>
-                <param name="use_raw" value="False"/>
-                <param name="sort_order" value="True"/>
                 <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontsize" value="1"/>
                     <param name="legend_fontweight" value="normal"/>
                     <param name="palette" value="bwr"/>
-                    <param name="frameon" value="False"/>
                     <param name="size" value="1"/>
                     <param name="title" value="A title"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.scatter"/>
-                    <has_text_matching expression="x_field='EKLF'" />
+                    <has_text_matching expression="x_field='EKLF'"/>
                     <has_text_matching expression="y_field='Cebpa'"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="sort_order=True"/>
                     <has_text_matching expression="projection='2d'"/>
-                    <has_text_matching expression="legend_loc='right margin'"/>
                     <has_text_matching expression="legend_fontsize=1"/>
                     <has_text_matching expression="legend_fontweight='normal'"/>
-                    <has_text_matching expression="frameon=False"/>
+                    <has_text_matching expression="frameon=True"/>
                     <has_text_matching expression="size=1.0"/>
                     <has_text_matching expression="title='A title'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.scatter.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.scatter.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 3 -->
         <test expect_num_outputs="2">
-            <!-- test 3: pl.heatmap -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="pbmc68k_reduced.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.heatmap"/>
-                <conditional name="var_names">
-                    <param name="type" value="all"/>
+                <param name="method" value="pl.scatter"/>
+                <conditional name="type">
+                    <param name="type" value="xy"/>
+                    <param name="x" value="n_genes"/>
+                    <param name="y" value="n_counts"/>
                 </conditional>
+                <section name="plot">
+                    <param name="legend_fontsize" value="1"/>
+                    <param name="legend_fontweight" value="normal"/>
+                    <param name="palette" value="bwr"/>
+                    <param name="size" value="1"/>
+                    <param name="title" value="A title"/>
+                </section>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pl.scatter"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="sort_order=True"/>
+                    <has_text_matching expression="projection='2d'"/>
+                    <has_text_matching expression="legend_fontsize=1"/>
+                    <has_text_matching expression="legend_fontweight='normal'"/>
+                    <has_text_matching expression="frameon=True"/>
+                    <has_text_matching expression="size=1.0"/>
+                    <has_text_matching expression="title='A title'"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" file="pl.scatter.pbmc68k_reduced.png" ftype="png" compare="image_diff"/>
+        </test>
+
+        <!-- test 4 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="krumsiek11.h5ad"/>
+            <param name="format" value="png"/>
+            <conditional name="method">
+                <param name="method" value="pl.heatmap"/>
                 <param name="groupby" value="cell_type"/>
-                <param name="num_categories" value="7"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
                 <conditional name="figsize">
-                    <param name="test" value="yes"/>
-                    <param name="width" value="10" />
+                    <param name="custom" value="yes"/>
+                    <param name="width" value="10"/>
                     <param name="height" value="3"/>
                 </conditional>
                 <param name="dendrogram" value="True"/>
                 <param name="swap_axes" value="True"/>
-                <param name="show_gene_labels" value="False"/>
                 <section name="matplotlib_pyplot_imshow">
                     <param name="cmap" value="YlGnBu"/>
-                    <param name="interpolation" value="None"/>
-                    <param name="origin" value="upper"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.heatmap"/>
-                    <has_text_matching expression="var_names=adata.var_names" />
+                    <has_text_matching expression="var_names=adata.var_names"/>
                     <has_text_matching expression="groupby='cell_type'"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="num_categories=7"/>
                     <has_text_matching expression="dendrogram=True"/>
                     <has_text_matching expression="figsize=\(10, 3\)"/>
@@ -1033,61 +1152,58 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="origin='upper'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.heatmap.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.heatmap.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 5 -->
         <test expect_num_outputs="2">
-          <!-- test 4: pl.heatmap with symbols -->
-          <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad" />
-          <param name="format" value="png"/>
-          <conditional name="method">
-              <param name="method" value="pl.heatmap"/>
-              <conditional name="var_names">
-                  <param name="type" value="custom"/>
-                  <param name="var_names" value="Fog1,EKLF,SCL"/>
-              </conditional>
-              <param name="groupby" value="cell_type"/>
-              <param name="gene_symbols" value="symbol"/>
-              <param name="num_categories" value="7"/>
-              <param name="log" value="False"/>
-              <param name="use_raw" value="False"/>
-              <conditional name="figsize">
-                  <param name="test" value="yes"/>
-                  <param name="width" value="10" />
-                  <param name="height" value="3"/>
-              </conditional>
-              <param name="dendrogram" value="True"/>
-              <param name="swap_axes" value="True"/>
-              <param name="show_gene_labels" value="True"/>
-              <section name="matplotlib_pyplot_imshow">
-                  <param name="cmap" value="YlGnBu"/>
-                  <param name="interpolation" value="None"/>
-                  <param name="origin" value="upper"/>
-              </section>
-          </conditional>
-          <section name="advanced_common">
-              <param name="show_log" value="true" />
-          </section>
-          <output name="hidden_output">
-              <assert_contents>
-                  <has_text_matching expression="sc.pl.heatmap"/>
-                  <has_text_matching expression="gene_symbols='symbol'"/>
-                  <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]" />
-                  <has_text_matching expression="groupby='cell_type'"/>
-                  <has_text_matching expression="log=False"/>
-                  <has_text_matching expression="use_raw=False"/>
-                  <has_text_matching expression="num_categories=7"/>
-                  <has_text_matching expression="dendrogram=True"/>
-                  <has_text_matching expression="figsize=\(10, 3\)"/>
-                  <has_text_matching expression="swap_axes=True"/>
-                  <has_text_matching expression="show_gene_labels=True"/>
-                  <has_text_matching expression="cmap='YlGnBu'"/>
-                  <has_text_matching expression="origin='upper'"/>
-              </assert_contents>
-          </output>
+            <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad"/>
+            <param name="format" value="png"/>
+            <conditional name="method">
+                <param name="method" value="pl.heatmap"/>
+                <conditional name="var_names">
+                    <param name="type" value="custom"/>
+                    <param name="var_names" value="Fog1,EKLF,SCL"/>
+                </conditional>
+                <param name="gene_symbols" value="symbol"/>
+                <param name="groupby" value="cell_type"/>
+                <conditional name="figsize">
+                    <param name="custom" value="yes"/>
+                    <param name="width" value="10"/>
+                    <param name="height" value="3"/>
+                </conditional>
+                <param name="dendrogram" value="True"/>
+                <param name="swap_axes" value="True"/>
+                <param name="show_gene_labels" value="True"/>
+                <section name="matplotlib_pyplot_imshow">
+                    <param name="cmap" value="YlGnBu"/>
+                </section>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pl.heatmap"/>
+                    <has_text_matching expression="gene_symbols='symbol'"/>
+                    <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]"/>
+                    <has_text_matching expression="groupby='cell_type'"/>
+                    <has_text_matching expression="log=False"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="num_categories=7"/>
+                    <has_text_matching expression="dendrogram=True"/>
+                    <has_text_matching expression="figsize=\(10, 3\)"/>
+                    <has_text_matching expression="swap_axes=True"/>
+                    <has_text_matching expression="show_gene_labels=True"/>
+                    <has_text_matching expression="cmap='YlGnBu'"/>
+                    <has_text_matching expression="origin='upper'"/>
+                </assert_contents>
+            </output>
         </test>
+        
+        <!-- test 6 -->
         <test expect_num_outputs="2">
-            <!-- test 5: pl.dotplot -->
-            <param name="adata" value="pbmc68k_reduced.h5ad" />
+            <param name="adata" value="pbmc68k_reduced.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.dotplot"/>
@@ -1096,9 +1212,6 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <param name="var_names" value="CD79A, MS4A1, CD8A, CD8B, LYZ, GNLY, NKG7, RP3-467N11.1, FCGR3A, FCER1A, CST3, POU2AF1, LINC00402"/>
                 </conditional>
                 <param name="groupby" value="louvain"/>
-                <param name="num_categories" value="7"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
                 <param name="dendrogram" value="True"/>
                 <repeat name="var_group_positions">
                     <param name="start" value="0"/>
@@ -1110,27 +1223,22 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <param name="end" value="12"/>
                     <param name="label" value="dendritic"/>
                 </repeat>
-                <conditional name="figsize">
-                    <param name="test" value="no"/>
-                </conditional>
                 <param name="color_map" value="hot"/>
                 <param name="dot_max" value="0.7"/>
                 <param name="dot_min" value="0.1"/>
                 <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0" />
-                    <param name="edgecolors" value="face"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.dotplot"/>
-                    <has_text_matching expression="var_names=\['CD79A', 'MS4A1', 'CD8A', 'CD8B', 'LYZ', 'GNLY', 'NKG7', 'RP3-467N11.1', 'FCGR3A', 'FCER1A', 'CST3', 'POU2AF1', 'LINC00402'\]" />
+                    <has_text_matching expression="var_names=\['CD79A', 'MS4A1', 'CD8A', 'CD8B', 'LYZ', 'GNLY', 'NKG7', 'RP3-467N11.1', 'FCGR3A', 'FCER1A', 'CST3', 'POU2AF1', 'LINC00402'\]"/>
                     <has_text_matching expression="groupby='louvain'"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="num_categories=7"/>
                     <has_text_matching expression="dendrogram=True"/>
                     <has_text_matching expression="var_group_positions=\[\(0, 1\), \(11, 12\)\]"/>
@@ -1138,309 +1246,271 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="color_map='hot'"/>
                     <has_text_matching expression="dot_max=0.7"/>
                     <has_text_matching expression="dot_min=0.1"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.dotplot.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.dotplot.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 7 -->
         <test expect_num_outputs="2">
-          <!-- test 6: pl.dotplot with symbols -->
-          <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad" />
-          <param name="format" value="png"/>
-          <conditional name="method">
-              <param name="method" value="pl.dotplot"/>
-              <conditional name="var_names">
-                  <param name="type" value="custom"/>
-                  <param name="var_names" value="Fog1,EKLF,SCL"/>
-              </conditional>
-              <param name="groupby" value="cell_type"/>
-              <param name="gene_symbols" value="symbol"/>
-              <param name="num_categories" value="7"/>
-              <param name="log" value="False"/>
-              <param name="use_raw" value="False"/>
-              <param name="dendrogram" value="True"/>
-              <section name="matplotlib_pyplot_imshow">
-                  <param name="cmap" value="YlGnBu"/>
-                  <param name="interpolation" value="None"/>
-                  <param name="origin" value="upper"/>
-              </section>
-          </conditional>
-          <section name="advanced_common">
-              <param name="show_log" value="true" />
-          </section>
-          <output name="hidden_output">
-              <assert_contents>
-                  <has_text_matching expression="sc.pl.dotplot"/>
-                  <has_text_matching expression="gene_symbols='symbol'"/>
-                  <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]" />
-                  <has_text_matching expression="groupby='cell_type'"/>
-                  <has_text_matching expression="log=False"/>
-                  <has_text_matching expression="use_raw=False"/>
-                  <has_text_matching expression="num_categories=7"/>
-                  <has_text_matching expression="dendrogram=True"/>
-              </assert_contents>
-          </output>
+            <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad"/>
+            <param name="format" value="png"/>
+            <conditional name="method">
+                <param name="method" value="pl.dotplot"/>
+                <conditional name="var_names">
+                    <param name="type" value="custom"/>
+                    <param name="var_names" value="Fog1,EKLF,SCL"/>
+                </conditional>
+                <param name="gene_symbols" value="symbol"/>
+                <param name="groupby" value="cell_type"/>              
+                <param name="dendrogram" value="True"/>
+                <section name="matplotlib_pyplot_imshow">
+                    <param name="cmap" value="YlGnBu"/>
+                </section>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pl.dotplot"/>
+                    <has_text_matching expression="gene_symbols='symbol'"/>
+                    <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]"/>
+                    <has_text_matching expression="groupby='cell_type'"/>
+                    <has_text_matching expression="log=False"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="num_categories=7"/>
+                    <has_text_matching expression="dendrogram=True"/>
+                </assert_contents>
+            </output>
+        </test>
+        
+        <!-- test 8 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad"/>
+            <param name="format" value="png"/>
+            <conditional name="method">
+                <param name="method" value="pl.tracksplot"/>
+                <param name="gene_symbols" value="symbol"/>
+                <param name="groupby" value="cell_type"/>              
+                <param name="dendrogram" value="True"/>
+                <section name="matplotlib_pyplot_imshow">
+                    <param name="cmap" value="YlGnBu"/>
+                </section>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pl.tracksplot"/>
+                    <has_text_matching expression="gene_symbols='symbol'"/>
+                    <has_text_matching expression="groupby='cell_type'"/>
+                    <has_text_matching expression="log=False"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="num_categories=7"/>
+                    <has_text_matching expression="dendrogram=True"/>
+                </assert_contents>
+            </output>
         </test>
+
+        <!-- test 9 -->
         <test expect_num_outputs="2">
-            <!-- test 7: pl.violin -->
-            <param name="adata" value="pbmc68k_reduced.h5ad" />
+            <param name="adata" value="pbmc68k_reduced.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.violin"/>
                 <conditional name="key_variables">
                     <param name="type" value="custom"/>
-                    <param name="keys" value="n_genes, percent_mito, n_counts" />
-                </conditional>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
+                    <param name="keys" value="n_genes, percent_mito, n_counts"/>
+                </conditional>              
                 <section name="violin_plot">
-                    <conditional name="stripplot">
-                        <param name="stripplot" value="True"/>
-                        <param name="jitter" value="True"/>
-                        <param name="size" value="1"/>
-                    </conditional>
                     <conditional name="multi_panel">
                         <param name="multi_panel" value="True"/>
-                        <param name="width" value="20"/>
-                        <param name="height" value="20"/>
                     </conditional>
-                    <param name="scale" value="width"/>
                 </section>
                 <section name="seaborn_violinplot">
-                    <param name="bw" value="scott"/>
                     <param name="linewidth" value="0"/>
-                    <param name="color" value="AliceBlue"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="saturation" value="0.75"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.violin"/>
-                    <has_text_matching expression="keys=\['n_genes', 'percent_mito', 'n_counts'\]" />
+                    <has_text_matching expression="keys=\['n_genes', 'percent_mito', 'n_counts'\]"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="stripplot=True"/>
                     <has_text_matching expression="jitter=True"/>
                     <has_text_matching expression="size=1"/>
                     <has_text_matching expression="multi_panel=True"/>
-                    <has_text_matching expression="figsize=\(20, 20\)"/>
-                    <has_text_matching expression="scale='width'"/>
-                    <has_text_matching expression="bw='scott'"/>
-                    <has_text_matching expression="scale='width'"/>
-                    <has_text_matching expression="linewidth=0.0"/>
-                    <has_text_matching expression="color='AliceBlue'"/>
+                    <has_text_matching expression="bw_method='scott'"/>
+                    <has_text_matching expression="saturation=0.75"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" file="pl.violin.pbmc68k_reduced_custom.png" ftype="png" compare="image_diff" eps="0.4"/>
+        </test>
+        
+        <!-- test 10 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="krumsiek11.h5ad"/>
+            <param name="format" value="png"/>
+            <conditional name="method">
+                <param name="method" value="pl.stacked_violin"/>
+                <param name="groupby" value="cell_type"/>
+                <param name="dendrogram" value="True"/>
+                <param name="swap_axes" value="True"/>
+                <section name="violin_plot">
+                    <param name="density_norm" value="width"/>
+                </section>
+                <section name="seaborn_violinplot">
+                    <param name="linewidth" value="0"/>
+                </section>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pl.stacked_violin"/>
+                    <has_text_matching expression="groupby='cell_type'"/>
+                    <has_text_matching expression="log=False"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="num_categories=7"/>
+                    <has_text_matching expression="dendrogram=True"/>
+                    <has_text_matching expression="swap_axes=True"/>
+                    <has_text_matching expression="stripplot=True"/>
+                    <has_text_matching expression="jitter=True"/>
+                    <has_text_matching expression="size=1"/>
+                    <has_text_matching expression="density_norm='width'"/>
+                    <has_text_matching expression="bw_method='scott'"/>
                     <has_text_matching expression="saturation=0.75"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.violin.pbmc68k_reduced_custom.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.stacked_violin.krumsiek11.png" ftype="png" compare="image_diff" eps="1.1"/>
+        </test>
+        
+        <!-- test 11 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad"/>
+            <param name="format" value="png"/>
+            <conditional name="method">
+                <param name="method" value="pl.stacked_violin"/>
+                <conditional name="var_names">
+                    <param name="type" value="custom"/>
+                    <param name="var_names" value="Fog1,EKLF,SCL"/>
+                </conditional>
+                <param name="gene_symbols" value="symbol"/>
+                <param name="groupby" value="cell_type"/>
+                <param name="dendrogram" value="True"/>
+                <param name="swap_axes" value="True"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pl.stacked_violin"/>
+                    <has_text_matching expression="gene_symbols='symbol'"/>
+                    <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]"/>
+                    <has_text_matching expression="groupby='cell_type'"/>
+                    <has_text_matching expression="log=False"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="num_categories=7"/>
+                    <has_text_matching expression="dendrogram=True"/>
+                    <has_text_matching expression="swap_axes=True"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" file="pl.stacked_violin_pp.filter_genes_dispersion.krumsiek11-seurat.png" compare="image_diff" eps="0.6"/>
         </test>
+        
+        <!-- test 12 -->
         <test expect_num_outputs="2">
-            <!-- test 8: pl.stacked_violin -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.stacked_violin"/>
-                <conditional name="var_names">
-                    <param name="type" value="all"/>
-                </conditional>
+                <param name="method" value="pl.matrixplot"/>
                 <param name="groupby" value="cell_type"/>
-                <param name="num_categories" value="7"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
                 <param name="dendrogram" value="True"/>
-                <conditional name="figsize">
-                    <param name="test" value="no"/>
-                </conditional>
                 <param name="swap_axes" value="True"/>
-                <section name="violin_plot">
-                    <conditional name="stripplot">
-                        <param name="stripplot" value="True"/>
-                        <param name="jitter" value="True"/>
-                        <param name="size" value="1"/>
-                    </conditional>
-                    <param name="scale" value="width"/>
-                </section>
-                <param name="row_palette" value="muted"/>
-                <param name="standard_scale" value="None"/>
-                <section name="seaborn_violinplot">
-                    <param name="bw" value="scott"/>
-                    <param name="linewidth" value="0"/>
-                    <param name="color" value="AliceBlue"/>
-                    <param name="saturation" value="0.75"/>
-                </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
-                    <has_text_matching expression="sc.pl.stacked_violin"/>
+                    <has_text_matching expression="sc.pl.matrixplot"/>
+                    <has_text_matching expression="var_names=adata.var_names"/>
                     <has_text_matching expression="groupby='cell_type'"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="num_categories=7"/>
                     <has_text_matching expression="dendrogram=True"/>
                     <has_text_matching expression="swap_axes=True"/>
-                    <has_text_matching expression="stripplot=True"/>
-                    <has_text_matching expression="jitter=True"/>
-                    <has_text_matching expression="size=1"/>
-                    <has_text_matching expression="scale='width'"/>
-                    <has_text_matching expression="bw='scott'"/>
-                    <has_text_matching expression="scale='width'"/>
-                    <has_text_matching expression="linewidth=0.0"/>
-                    <has_text_matching expression="color='AliceBlue'"/>
-                    <has_text_matching expression="saturation=0.75"/>
+                    <has_text_matching expression="snap=False"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.stacked_violin.krumsiek11.png" ftype="png" compare="sim_size"/>
-        </test>
-        <test expect_num_outputs="2">
-          <!-- test 9: pl.stacked_violin with symbols -->
-          <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad" />
-          <param name="format" value="png"/>
-          <conditional name="method">
-              <param name="method" value="pl.stacked_violin"/>
-              <conditional name="var_names">
-                  <param name="type" value="custom"/>
-                  <param name="var_names" value="Fog1,EKLF,SCL"/>
-              </conditional>
-              <param name="groupby" value="cell_type"/>
-              <param name="gene_symbols" value="symbol"/>
-              <param name="num_categories" value="7"/>
-              <param name="log" value="False"/>
-              <param name="use_raw" value="False"/>
-              <param name="dendrogram" value="True"/>
-              <param name="swap_axes" value="True"/>
-          </conditional>
-          <section name="advanced_common">
-              <param name="show_log" value="true" />
-          </section>
-          <output name="hidden_output">
-              <assert_contents>
-                  <has_text_matching expression="sc.pl.stacked_violin"/>
-                  <has_text_matching expression="gene_symbols='symbol'"/>
-                  <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]" />
-                  <has_text_matching expression="groupby='cell_type'"/>
-                  <has_text_matching expression="log=False"/>
-                  <has_text_matching expression="use_raw=False"/>
-                  <has_text_matching expression="num_categories=7"/>
-                  <has_text_matching expression="dendrogram=True"/>
-                  <has_text_matching expression="swap_axes=True"/>
-              </assert_contents>
-          </output>
+            <output name="out_png" file="pl.matrixplot.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 13 -->
         <test expect_num_outputs="2">
-            <!-- test 10: pl.matrixplot -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.matrixplot"/>
                 <conditional name="var_names">
-                    <param name="type" value="all"/>
+                    <param name="type" value="custom"/>
+                    <param name="var_names" value="Fog1,EKLF,SCL"/>
                 </conditional>
+                <param name="gene_symbols" value="symbol"/>
                 <param name="groupby" value="cell_type"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
-                <param name="num_categories" value="7"/>
-                <param name="dendrogram" value="True"/>
                 <conditional name="figsize">
-                    <param name="test" value="no"/>
+                    <param name="custom" value="yes"/>
+                    <param name="width" value="10"/>
+                    <param name="height" value="3"/>
                 </conditional>
-                <param name="swap_axes" value="True"/>
-                <section name="matplotlib_pyplot_pcolor">
-                    <param name="cmap" value="viridis"/>
-                    <param name="edgecolors" value="face"/>
-                    <param name="snap" value="False"/>
-                </section>
+                <param name="dendrogram" value="True"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.matrixplot"/>
-                    <has_text_matching expression="var_names=adata.var_names" />
+                    <has_text_matching expression="gene_symbols='symbol'"/>
+                    <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]"/>
                     <has_text_matching expression="groupby='cell_type'"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="num_categories=7"/>
                     <has_text_matching expression="dendrogram=True"/>
-                    <has_text_matching expression="swap_axes=True"/>
-                    <has_text_matching expression="cmap='viridis'"/>
-                    <has_text_matching expression="ec='face'"/>
-                    <has_text_matching expression="snap=False"/>
+                    <has_text_matching expression="swap_axes=False"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.matrixplot.krumsiek11.png" ftype="png" compare="sim_size"/>
         </test>
+        
+        <!-- test 14 -->
         <test expect_num_outputs="2">
-          <!-- test 11: pl.matrixplot with symbols -->
-          <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad" />
-          <param name="format" value="png"/>
-          <conditional name="method">
-              <param name="method" value="pl.matrixplot"/>
-              <conditional name="var_names">
-                  <param name="type" value="custom"/>
-                  <param name="var_names" value="Fog1,EKLF,SCL"/>
-              </conditional>
-              <param name="groupby" value="cell_type"/>
-              <param name="gene_symbols" value="symbol"/>
-              <param name="num_categories" value="7"/>
-              <param name="log" value="False"/>
-              <param name="use_raw" value="False"/>
-              <conditional name="figsize">
-                  <param name="test" value="yes"/>
-                  <param name="width" value="10" />
-                  <param name="height" value="3"/>
-              </conditional>
-              <param name="dendrogram" value="True"/>
-              <param name="swap_axes" value="False"/>
-          </conditional>
-          <section name="advanced_common">
-              <param name="show_log" value="true" />
-          </section>
-          <output name="hidden_output">
-              <assert_contents>
-                  <has_text_matching expression="sc.pl.matrixplot"/>
-                  <has_text_matching expression="gene_symbols='symbol'"/>
-                  <has_text_matching expression="var_names=\['Fog1', 'EKLF', 'SCL'\]" />
-                  <has_text_matching expression="groupby='cell_type'"/>
-                  <has_text_matching expression="log=False"/>
-                  <has_text_matching expression="use_raw=False"/>
-                  <has_text_matching expression="num_categories=7"/>
-                  <has_text_matching expression="dendrogram=True"/>
-                  <has_text_matching expression="swap_axes=False"/>
-              </assert_contents>
-          </output>
-        </test>
-        <test expect_num_outputs="2">
-            <!-- test 12: pl.clustermap -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.clustermap"/>
-                <param name="use_raw" value="False"/>
                 <section name="seaborn_clustermap">
                     <param name="method" value="single"/>
-                    <param name="metric" value="euclidean"/>
-                    <param name="z_score" value="None"/>
-                    <param name="standard_scale" value="None"/>
                     <param name="col_cluster" value="False"/>
                     <param name="row_cluster" value="False"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.clustermap"/>
-                    <has_text_matching expression="adata=adata" />
+                    <has_text_matching expression="adata=adata"/>
                     <has_text_matching expression="use_raw=False"/>
                     <has_text_matching expression="method='single'"/>
                     <has_text_matching expression="metric='euclidean'"/>
@@ -1448,66 +1518,85 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="row_cluster=False"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.clustermap.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.clustermap.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 15 -->
         <test expect_num_outputs="2">
-            <!-- test 13: pl.highest_expr_genes -->
-            <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad" />
+            <param name="adata" value="pp.filter_genes_dispersion.krumsiek11-seurat.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.highest_expr_genes"/>
-                <param name="n_top" value="30"/>
-                <param name="gene_symbols" value="means"/>
+                <param name="gene_symbols" value="symbol"/>
                 <section name="setseaborn_boxplot">
                     <param name="color" value="blue"/>
                     <param name="saturation" value="0.5"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.highest_expr_genes"/>
-                    <has_text_matching expression="n_top=30" />
-                    <has_text_matching expression="gene_symbols='means'" />
+                    <has_text_matching expression="n_top=30"/>
+                    <has_text_matching expression="gene_symbols='symbol'"/>
                     <has_text_matching expression="color='blue'"/>
                     <has_text_matching expression="saturation=0.5"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.highest_expr_genes.filter_genes_dispersion.krumsiek11-seurat.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.highest_expr_genes.filter_genes_dispersion.krumsiek11-seurat.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 16 -->
         <test expect_num_outputs="2">
-            <!-- test 14: pl.highly_variable_genes -->
-            <param name="adata" value="pp.highly_variable_genes.seurat.blobs.h5ad" />
+            <param name="adata" value="pp.highly_variable_genes.seurat.blobs.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.highly_variable_genes"/>
-                <param name="log" value="false"/>
-                <param name="highly_variable_genes" value="true"/>
+                <param name="method" value="pl.highly_variable_genes"/>                
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.highly_variable_genes"/>
-                    <has_text_matching expression="adata_or_result=adata" />
-                    <has_text_matching expression="log=False" />
+                    <has_text_matching expression="adata_or_result=adata"/>
+                    <has_text_matching expression="log=False"/>
                     <has_text_matching expression="highly_variable_genes=True"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.highly_variable_genes.seurat.blobs.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.highly_variable_genes.seurat.blobs.png" ftype="png" compare="image_diff"/>
+        </test>
+        
+        <!-- test 17 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="pp.scrublet.krumsiek11.h5ad"/>
+            <param name="format" value="png"/>
+            <conditional name="method">
+                <param name="method" value="pl.scrublet_score_distribution"/>                
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.pl.scrublet_score_distribution"/>
+                    <has_text_matching expression="adata=adata"/>
+                    <has_text_matching expression="scale_hist_obs='log'"/>
+                    <has_text_matching expression="scale_hist_sim='linear'"/>
+                </assert_contents>
+            </output>
+            <output name="out_png" file="pl.scrublet_score_distribution.png" ftype="png" compare="image_diff"/>
         </test>
+
+        <!-- test 18 -->
         <test expect_num_outputs="2">
-            <!-- test 15: pl.pca -->
-            <param name="adata" value="pbmc68k_reduced.h5ad" />
+            <param name="adata" value="pbmc68k_reduced.h5ad"/>
             <param name="format" value="pdf"/>
             <conditional name="method">
                 <param name="method" value="pl.pca"/>
                 <param name="color" value="CD3D,CD79A"/>
-                <param name="use_raw" value="False"/>
-                <param name="sort_order" value="True"/>
                 <section name="plot">
                     <repeat name="components">
                         <param name="axis1" value="1"/>
@@ -1517,112 +1606,90 @@ sc.pl.rank_genes_groups_stacked_violin(
                         <param name="axis1" value="1"/>
                         <param name="axis2" value="3"/>
                     </repeat>
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontsize" value="1"/>
                     <param name="legend_fontweight" value="normal"/>
                     <param name="size" value="1"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="frameon" value="True"/>
                     <param name="ncols" value="2"/>
-                    <param name="wspace" value="0.1"/>
-                    <param name="hspace" value="0.25"/>
-                </section>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0"/>
-                    <param name="edgecolors" value="face"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.pca"/>
-                    <has_text_matching expression="save='.pdf'" />
-                    <has_text_matching expression="color=\['CD3D', 'CD79A'\]" />
-                    <has_text_matching expression="use_raw=False" />
-                    <has_text_matching expression="sort_order=True" />
-                    <has_text_matching expression="components=\['1,2', '1,3'\]" />
-                    <has_text_matching expression="projection='2d'" />
-                    <has_text_matching expression="legend_loc='right margin'" />
-                    <has_text_matching expression="legend_fontsize=1" />
-                    <has_text_matching expression="legend_fontweight='normal'" />
-                    <has_text_matching expression="size=1.0" />
-                    <has_text_matching expression="palette='viridis'" />
-                    <has_text_matching expression="frameon=True" />
-                    <has_text_matching expression="ncols=2" />
-                    <has_text_matching expression="wspace=0.1" />
-                    <has_text_matching expression="hspace=0.25" />
-                    <has_text_matching expression="lw=0.0" />
-                    <has_text_matching expression="ec='face'" />
+                    <has_text_matching expression="save='.pdf'"/>
+                    <has_text_matching expression="color=\['CD3D', 'CD79A'\]"/>
+                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="sort_order=True"/>
+                    <has_text_matching expression="components=\['1,2', '1,3'\]"/>
+                    <has_text_matching expression="projection='2d'"/>
+                    <has_text_matching expression="legend_loc='right margin'"/>
+                    <has_text_matching expression="legend_fontsize=1"/>
+                    <has_text_matching expression="legend_fontweight='normal'"/>
+                    <has_text_matching expression="size=1.0"/>
+                    <has_text_matching expression="frameon=True"/>
+                    <has_text_matching expression="ncols=2"/>
+                    <has_text_matching expression="wspace=0.1"/>
+                    <has_text_matching expression="hspace=0.25"/>
                 </assert_contents>
             </output>
             <output name="out_pdf" file="pl.pca.pbmc68k_reduced.CD3D_CD79A_components_2d.pdf" ftype="pdf" compare="sim_size"/>
         </test>
+        
+        <!-- test 19 -->
         <test expect_num_outputs="2">
-            <!-- test 16: pl.pca_loadings -->
-            <param name="adata" value="pp.pca.krumsiek11.h5ad" />
+            <param name="adata" value="pp.pca.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.pca_loadings"/>
                 <param name="components" value="1,2,3"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.pca_loadings"/>
-                    <has_text_matching expression="components=\[1, 2, 3\]" />
+                    <has_text_matching expression="components=\[1, 2, 3\]"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.pca_loadings.pp.pca.krumsiek11.png" compare="sim_size"/>
+            <output name="out_png" file="pl.pca_loadings.pp.pca.krumsiek11.png" compare="image_diff"/>
         </test>
+        
+        <!-- test 20 -->
         <test expect_num_outputs="2">
-            <!-- test 17: pl.pca_variance_ratio -->
-            <param name="adata" value="pp.pca.krumsiek11.h5ad" />
+            <param name="adata" value="pp.pca.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.pca_variance_ratio"/>
-                <param name="n_pcs" value="5"/>
-                <param name="log" value="False"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.pca_variance_ratio"/>
-                    <has_text_matching expression="n_pcs=5" />
-                    <has_text_matching expression="log=False" />
+                    <has_text_matching expression="log=False"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.pca_variance_ratio.pp.pca.krumsiek11.png" compare="sim_size"/>
+            <output name="out_png" file="pl.pca_variance_ratio.pp.pca.krumsiek11.png" compare="image_diff"/>
         </test>
+        
+        <!-- test 21 -->
         <test expect_num_outputs="2">
-            <!-- test 18: pl.pca_overview -->
-            <param name="adata" value="pp.pca.krumsiek11.h5ad" />
+            <param name="adata" value="pp.pca.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.pca_overview"/>
-                <param name="use_raw" value="False"/>
-                <param name="sort_order" value="True"/>
                 <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontsize" value="1"/>
                     <param name="legend_fontweight" value="normal"/>
                     <param name="size" value="1"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="frameon" value="True"/>
-                    <param name="ncols" value="4"/>
-                    <param name="wspace" value="0.1"/>
-                    <param name="hspace" value="0.25"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -1634,46 +1701,29 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="legend_fontsize=1"/>
                     <has_text_matching expression="legend_fontweight='normal'"/>
                     <has_text_matching expression="size=1.0"/>
-                    <has_text_matching expression="palette='viridis'"/>
                     <has_text_matching expression="frameon=True"/>
                     <has_text_matching expression="ncols=4"/>
                     <has_text_matching expression="wspace=0.1"/>
                     <has_text_matching expression="hspace=0.25"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.pca_overview.pp.pca.krumsiek11.png" compare="sim_size"/>
+            <output name="out_png" file="pl.pca_overview.pp.pca.krumsiek11.png" compare="image_diff"/>
         </test>
+        
+        <!-- test 22 -->
         <test expect_num_outputs="2">
-            <!-- test 19: pl.tsne -->
-            <param name="adata" value="tl.tsne.krumsiek11.h5ad" />
+            <param name="adata" value="tl.tsne.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.tsne"/>
-                <param name="use_raw" value="False"/>
-                <conditional name="edges">
-                    <param name="edges" value="False" />
-                </conditional>
-                <param name="arrows" value="False" />
-                <param name="sort_order" value="True"/>
                 <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontsize" value="1"/>
                     <param name="legend_fontweight" value="normal"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="frameon" value="True"/>
                     <param name="size" value="1"/>
-                    <param name="ncols" value="4"/>
-                    <param name="wspace" value="0.1"/>
-                    <param name="hspace" value="0.25"/>
-                </section>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0"/>
-                    <param name="edgecolors" value="face"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -1687,50 +1737,33 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="legend_fontsize=1"/>
                     <has_text_matching expression="legend_fontweight='normal'"/>
                     <has_text_matching expression="size=1.0"/>
-                    <has_text_matching expression="palette='viridis'"/>
                     <has_text_matching expression="frameon=True"/>
                     <has_text_matching expression="ncols=4"/>
                     <has_text_matching expression="wspace=0.1"/>
                     <has_text_matching expression="hspace=0.25"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.tsne.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.tsne.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 23 -->
         <test expect_num_outputs="2">
-            <!-- test 20: pl.umap -->
-            <param name="adata" value="tl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="tl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.umap"/>
                 <param name="color" value="paul15_clusters"/>
-                <param name="use_raw" value="False"/>
                 <conditional name="edges">
-                    <param name="edges" value="True" />
-                    <param name="edges_width" value="0.1" />
-                    <param name="edges_color" value="AliceBlue"/>
+                    <param name="edges" value="True"/>
                 </conditional>
-                <param name="arrows" value="False" />
                 <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontsize" value="1"/>
                     <param name="legend_fontweight" value="normal"/>
                     <param name="size" value="1"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="frameon" value="True"/>
-                    <param name="ncols" value="4"/>
-                    <param name="wspace" value="0.1"/>
-                    <param name="hspace" value="0.25"/>
-                </section>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0"/>
-                    <param name="edgecolors" value="face"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -1739,7 +1772,6 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="use_raw=False"/>
                     <has_text_matching expression="edges=True"/>
                     <has_text_matching expression="edges_width=0.1"/>
-                    <has_text_matching expression="edges_color='AliceBlue'"/>
                     <has_text_matching expression="arrows=False"/>
                     <has_text_matching expression="sort_order=True"/>
                     <has_text_matching expression="projection='2d'"/>
@@ -1747,45 +1779,31 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="legend_fontsize=1"/>
                     <has_text_matching expression="legend_fontweight='normal'"/>
                     <has_text_matching expression="size=1.0"/>
-                    <has_text_matching expression="palette='viridis'"/>
                     <has_text_matching expression="frameon=True"/>
                     <has_text_matching expression="ncols=4"/>
                     <has_text_matching expression="wspace=0.1"/>
                     <has_text_matching expression="hspace=0.25"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face'"/>
+                    
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 24 -->
         <test expect_num_outputs="2">
-            <!-- test 21: pl.diffmap -->
-            <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="tl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.diffmap"/>
                 <param name="color" value="paul15_clusters"/>
-                <param name="use_raw" value="False"/>
-                <param name="sort_order" value="True"/>
                 <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontsize" value="1"/>
                     <param name="legend_fontweight" value="normal"/>
                     <param name="size" value="1"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="frameon" value="True"/>
-                    <param name="ncols" value="4"/>
-                    <param name="wspace" value="0.1"/>
-                    <param name="hspace" value="0.25"/>
-                </section>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0"/>
-                    <param name="edgecolors" value="face"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -1798,49 +1816,34 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="legend_fontsize=1"/>
                     <has_text_matching expression="legend_fontweight='normal'"/>
                     <has_text_matching expression="size=1.0"/>
-                    <has_text_matching expression="palette='viridis'"/>
                     <has_text_matching expression="frameon=True"/>
                     <has_text_matching expression="ncols=4"/>
                     <has_text_matching expression="wspace=0.1"/>
                     <has_text_matching expression="hspace=0.25"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face'"/>
+                    
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 25 -->
         <test expect_num_outputs="2">
-            <!-- test 22: pl.draw_graph -->
-            <param name="adata" value="tl.draw_graph.pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="tl.draw_graph.pp.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.draw_graph"/>
-                <param name="use_raw" value="false"/>
                 <param name="layout" value="fr"/>
                 <conditional name="edges">
                     <param name="edges" value="True"/>
-                    <param name="edges_width" value="0.1"/>
                     <param name="edges_color" value="Crimson"/>
                 </conditional>
-                <param name="arrows" value="false"/>
                 <param name="sort_order" value="false"/>
                 <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
                     <param name="legend_fontweight" value="normal"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="frameon" value="True"/>
-                    <param name="ncols" value="4"/>
-                    <param name="wspace" value="0.1"/>
-                    <param name="hspace" value="0.25"/>
-                </section>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0"/>
-                    <param name="edgecolors" value="face"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -1854,48 +1857,47 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="projection='2d'"/>
                     <has_text_matching expression="legend_loc='right margin'"/>
                     <has_text_matching expression="legend_fontweight='normal'"/>
-                    <has_text_matching expression="palette='viridis'"/>
                     <has_text_matching expression="frameon=True"/>
                     <has_text_matching expression="ncols=4"/>
                     <has_text_matching expression="wspace=0.1"/>
                     <has_text_matching expression="hspace=0.25"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.draw_graph.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.draw_graph.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 26 -->
         <test expect_num_outputs="2">
-            <!-- test 23: pl.embedding_density -->
-            <param name="adata" value="tl.embedding_density.umap.pbmc68k_reduced.h5ad" />
+            <param name="adata" value="tl.embedding_density.umap.pbmc68k_reduced.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.embedding_density"/>
-                <param name="basis" value="umap"/>
                 <param name="key" value="umap_density_bulk_labels"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.embedding_density"/>
-                    <has_text_matching expression="basis='umap'" />
+                    <has_text_matching expression="basis='umap'"/>
                     <has_text_matching expression="key='umap_density_bulk_labels'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.embedding_density.pbmc68k_reduced.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.embedding_density.pbmc68k_reduced.png" ftype="png" compare="image_diff"/>
         </test>
-        <test expect_num_outputs="2">
-            <!-- test 24: pl.dpt_groups_pseudotime -->
-            <param name="adata" value="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
+        
+        <!-- This function is commented out because it is not compatible with pandas version. If the issue is not resolved in the next update, this should be removed. -->
+        <!-- test 27 -->
+        <!-- <test expect_num_outputs="2">
+            <param name="adata" value="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.dpt_groups_pseudotime"/>
-                <param name="color_map" value="viridis"/>
+                
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -1903,94 +1905,73 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="color_map='viridis'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.dpt_groups_pseudotime.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="sim_size"/>
-        </test>
+            <output name="out_png" file="pl.dpt_groups_pseudotime.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="image_diff"/>
+        </test> -->
+        
+        <!-- test 28 -->
         <test expect_num_outputs="2">
-            <!-- test 25: pl.dpt_timeseries -->
-            <param name="adata" value="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad" />
+            <param name="adata" value="tl.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.dpt_timeseries"/>
-                <conditional name="heatmap">
-                    <param name="as_heatmap" value="True"/>
-                    <param name="color_map" value="viridis"/>
-                </conditional>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.dpt_timeseries"/>
-                    <has_text_matching expression="color_map='viridis'"/>
                     <has_text_matching expression="as_heatmap=True"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.dpt_timeseries.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.dpt_timeseries.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 29 -->
         <test expect_num_outputs="1">
-             <!-- test 26: pl.paga -->
-            <param name="adata" value="tl.paga.neighbors.paul15_gauss_braycurtis.h5ad" />
+            <param name="adata" value="tl.paga.neighbors.paul15_gauss_braycurtis.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.paga"/>
                 <param name="threshold" value="0.01"/>
                 <param name="color" value="louvain"/>
                 <param name="layout" value="fr"/>
-                <param name="random_state" value="0"/>
-                <param name="solid_edges" value="connectivities"/>
-                <param name="single_component" value="False"/>
                 <param name="fontsize" value="1"/>
-                <param name="node_size_scale" value="1.0"/>
-                <param name="node_size_power" value="0.5"/>
                 <param name="edge_width_scale" value="5"/>
-                <param name="arrowsize" value="30"/>
-                <param name="normalize_to_color" value="False"/>
-                <param name="cmap" value="viridis"/>
-                <param name="frameon" value="True"/>
             </conditional>
-            <output name="out_png" file="pl.paga.paul15_gauss_braycurtis.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.paga.paul15_gauss_braycurtis.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 30 -->
         <test expect_num_outputs="1">
-             <!-- test 27: pl.paga_compare -->
-            <param name="adata" value="tl.paga.neighbors.paul15_gauss_braycurtis.h5ad" />
+            <param name="adata" value="tl.paga.neighbors.paul15_gauss_braycurtis.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.paga_compare"/>
                 <param name="threshold" value="0.01"/>
                 <param name="color" value="louvain"/>
                 <param name="layout" value="fr"/>
-                <param name="random_state" value="0"/>
-                <param name="solid_edges" value="connectivities"/>
-                <param name="single_component" value="False"/>
                 <param name="fontsize" value="1"/>
-                <param name="node_size_scale" value="1.0"/>
-                <param name="node_size_power" value="0.5"/>
                 <param name="edge_width_scale" value="5"/>
-                <param name="arrowsize" value="30"/>
-                <param name="normalize_to_color" value="False"/>
-                <param name="cmap" value="viridis"/>
-                <param name="frameon" value="True"/>
             </conditional>
-            <output name="out_png" file="pl.paga_compare.paul15_gauss_braycurtis.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.paga_compare.paul15_gauss_braycurtis.png" ftype="png" compare="image_diff"/>
         </test>
-        <!--<test expect_num_outputs="2">
+
+        <!-- test 31 -->
+        <!-- <test expect_num_outputs="2">
              test pl.paga_path
-        </test>-->
+        </test> -->
+        
+        <!-- test 32 -->
         <test expect_num_outputs="2">
-            <!-- test 28: pl.rank_genes_groups -->
-            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad" />
+            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.rank_genes_groups"/>
-                <param name="gene_symbols" value="symbol"/>
-                <param name="n_genes" value="10"/>
-                <param name="fontsize" value="8"/>
-                <param name="ncols" value="4"/>
-                <param name="sharey" value="true"/>
+                <param name="n_genes" value="10"/>                
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
@@ -1998,14 +1979,14 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <has_text_matching expression="n_genes=10"/>
                     <has_text_matching expression="fontsize=8"/>
                     <has_text_matching expression="ncols=4"/>
-                    <has_text_matching expression="sharey=True"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.rank_genes_groups.rank_genes_groups.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups.rank_genes_groups.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 33 -->
         <test expect_num_outputs="2">
-            <!-- test 29: pl.rank_genes_groups_violin -->
-            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad" />
+            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.rank_genes_groups_violin"/>
@@ -2013,270 +1994,178 @@ sc.pl.rank_genes_groups_stacked_violin(
                     <param name="select" value="n_genes"/>
                     <param name="n_genes" value="10"/>
                 </conditional>
-                <param name="use_raw" value="false"/>
-                <param name="split" value="true"/>
-                <section name="violin_plot">
-                    <conditional name="stripplot">
-                        <param name="stripplot" value="True"/>
-                        <param name="jitter" value="True"/>
-                        <param name="size" value="1"/>
-                    </conditional>
-                    <param name="scale" value="width"/>
-                </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.rank_genes_groups_violin"/>
                     <has_text_matching expression="n_genes=10"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="split=True"/>
                     <has_text_matching expression="strip=True"/>
                     <has_text_matching expression="jitter=True"/>
                     <has_text_matching expression="size=1"/>
-                    <has_text_matching expression="scale='width'"/>
+                    <has_text_matching expression="density_norm='width'"/>
                 </assert_contents>
             </output>
             <output_collection name="collection_png">
-                <element name="cell_type_Ery" file="pl.rank_genes_groups_violin.Ery.png" ftype="png" compare="sim_size"/>
-                <element name="cell_type_Mk" file="pl.rank_genes_groups_violin.Mk.png" ftype="png" compare="sim_size"/>
-                <element name="cell_type_Mo" file="pl.rank_genes_groups_violin.Mo.png" ftype="png" compare="sim_size"/>
-                <element name="cell_type_Neu" file="pl.rank_genes_groups_violin.Neu.png" ftype="png" compare="sim_size"/>
-                <element name="cell_type_progenitor" file="pl.rank_genes_groups_violin.progenitor.png" ftype="png" compare="sim_size"/>
+                <element name="cell_type_Ery" file="pl.rank_genes_groups_violin.Ery.png" ftype="png" compare="image_diff" eps="3.5"/>
+                <element name="cell_type_Mk" file="pl.rank_genes_groups_violin.Mk.png" ftype="png" compare="image_diff" eps="3.5"/>
+                <element name="cell_type_Mo" file="pl.rank_genes_groups_violin.Mo.png" ftype="png" compare="image_diff" eps="3.5"/>
+                <element name="cell_type_Neu" file="pl.rank_genes_groups_violin.Neu.png" ftype="png" compare="image_diff" eps="3.5"/>
+                <element name="cell_type_progenitor" file="pl.rank_genes_groups_violin.progenitor.png" ftype="png" compare="image_diff" eps="3.5"/>
             </output_collection>
         </test>
+        
+        <!-- test 34 -->
         <test expect_num_outputs="2">
-            <!-- test 30: pl.rank_genes_groups_dotplot -->
-            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad" />
+            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.rank_genes_groups_dotplot"/>
-                <param name="gene_symbols" value="symbol"/>
+                <param name="method" value="pl.rank_genes_groups_stacked_violin"/>
                 <param name="n_genes" value="10"/>
-                <conditional name="var_names">
-                  <param name="type" value="all"/>
-                </conditional>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
-                <param name="dendrogram" value="False"/>
-                <param name="color_map" value="viridis"/>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0" />
-                    <param name="edgecolors" value="face"/>
+                <param name="dendrogram" value="True"/>
+                <param name="swap_axes" value="True"/>
+                <section name="violin_plot">
+                    <conditional name="stripplot">
+                        <param name="size" value="1"/>
+                    </conditional>
+                    <param name="density_norm" value="width"/>
                 </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
-                    <has_text_matching expression="sc.pl.rank_genes_groups_dotplot"/>
+                    <has_text_matching expression="sc.pl.rank_genes_groups_stacked_violin"/>
                     <has_text_matching expression="n_genes=10"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
-                    <has_text_matching expression="dendrogram=False"/>
-                    <has_text_matching expression="color_map='viridis'"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face'"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="dendrogram=True"/>
+                    <has_text_matching expression="swap_axes=True"/>
+                    <has_text_matching expression="stripplot=True"/>
+                    <has_text_matching expression="jitter=True"/>
+                    <has_text_matching expression="size=1"/>
+                    <has_text_matching expression="density_norm='width'"/>
+                    <has_text_matching expression="bw_method='scott'"/>
+                    <has_text_matching expression="saturation=0.75"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.rank_genes_groups_dotplot.rank_genes_groups.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups_stacked_violin.rank_genes_groups.krumsiek11.png" ftype="png" compare="image_diff" eps="1.5"/>
         </test>
+        
+        <!-- test 35 -->
         <test expect_num_outputs="2">
-            <!-- test 31: pl.rank_genes_groups_heatmap -->
-            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad" />
+            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.rank_genes_groups_heatmap"/>
-                <param name="gene_symbols" value="symbol"/>
                 <param name="n_genes" value="10"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
-                <param name="dendrogram" value="False"/>
-                <param name="swap_axes" value="False"/>
-                <param name="show_gene_labels" value="False"/>
-                <section name="matplotlib_pyplot_imshow">
-                    <param name="cmap" value="viridis"/>
-                    <param name="interpolation" value="None"/>
-                    <param name="origin" value="upper"/>
-                </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.rank_genes_groups_heatmap"/>
                     <has_text_matching expression="n_genes=10"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="dendrogram=False"/>
                     <has_text_matching expression="swap_axes=False"/>
                     <has_text_matching expression="show_gene_labels=False"/>
-                    <has_text_matching expression="cmap='viridis'"/>
                     <has_text_matching expression="origin='upper'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.rank_genes_groups_heatmap.rank_genes_groups.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups_heatmap.rank_genes_groups.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+
+        <!-- test 36 -->
         <test expect_num_outputs="2">
-            <!-- test 32: pl.rank_genes_groups_matrixplot -->
-            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad" />
+            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.rank_genes_groups_matrixplot"/>
-                <param name="gene_symbols" value="symbol"/>
+                <param name="method" value="pl.rank_genes_groups_dotplot"/>
                 <param name="n_genes" value="10"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
-                <param name="dendrogram" value="False"/>
-                <param name="swap_axes" value="False"/>
-                <section name="matplotlib_pyplot_pcolor">
-                    <param name="cmap" value="viridis"/>
-                    <param name="edgecolors" value="face"/>
-                    <param name="snap" value="False"/>
-                </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
-                    <has_text_matching expression="sc.pl.rank_genes_groups_matrixplot"/>
+                    <has_text_matching expression="sc.pl.rank_genes_groups_dotplot"/>
                     <has_text_matching expression="n_genes=10"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="dendrogram=False"/>
-                    <has_text_matching expression="swap_axes=False"/>
-                    <has_text_matching expression="cmap='viridis'"/>
-                    <has_text_matching expression="ec='face'"/>
-                    <has_text_matching expression="snap=False"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.rank_genes_groups_matrixplot.rank_genes_groups.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups_dotplot.rank_genes_groups.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 37 -->
         <test expect_num_outputs="2">
-            <!-- test 33: pl.rank_genes_groups_stacked_violin -->
-            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad" />
+            <param name="adata" value="tl.rank_genes_groups.krumsiek11.h5ad"/>
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.rank_genes_groups_stacked_violin"/>
-                <param name="gene_symbols" value="symbol"/>
+                <param name="method" value="pl.rank_genes_groups_matrixplot"/>
                 <param name="n_genes" value="10"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
-                <param name="dendrogram" value="True"/>
-                <param name="swap_axes" value="True"/>
-                <section name="violin_plot">
-                    <conditional name="stripplot">
-                        <param name="stripplot" value="True"/>
-                        <param name="jitter" value="True"/>
-                        <param name="size" value="1"/>
-                    </conditional>
-                    <param name="scale" value="width"/>
-                </section>
-                <param name="row_palette" value="muted"/>
-                <param name="standard_scale" value="None"/>
-                <section name="seaborn_violinplot">
-                    <param name="bw" value="scott"/>
-                    <param name="linewidth" value="0"/>
-                    <param name="color" value="AliceBlue"/>
-                    <param name="palette" value="viridis"/>
-                    <param name="saturation" value="0.75"/>
-                </section>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
-                    <has_text_matching expression="sc.pl.rank_genes_groups_stacked_violin"/>
+                    <has_text_matching expression="sc.pl.rank_genes_groups_matrixplot"/>
                     <has_text_matching expression="n_genes=10"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
-                    <has_text_matching expression="dendrogram=True"/>
-                    <has_text_matching expression="swap_axes=True"/>
-                    <has_text_matching expression="stripplot=True"/>
-                    <has_text_matching expression="jitter=True"/>
-                    <has_text_matching expression="size=1"/>
-                    <has_text_matching expression="scale='width'"/>
-                    <has_text_matching expression="bw='scott'"/>
-                    <has_text_matching expression="scale='width'"/>
-                    <has_text_matching expression="linewidth=0.0"/>
-                    <has_text_matching expression="color='AliceBlue'"/>
-                    <has_text_matching expression="saturation=0.75"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="dendrogram=False"/>
+                    <has_text_matching expression="swap_axes=False"/>
+                    <has_text_matching expression="snap=False"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.rank_genes_groups_stacked_violin.rank_genes_groups.krumsiek11.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups_matrixplot.rank_genes_groups.krumsiek11.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 38 pl.rank_genes_groups_dotplot with marker list-->
         <test expect_num_outputs="2">
-            <!-- test 34: pl.scatter log !-->
-            <param name="adata" value="pbmc68k_reduced.h5ad" />
+            <param name="adata" value="cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad" />
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.scatter"/>
-                <conditional name="type">
-                    <param name="type" value="xy"/>
-                    <param name="x" value="n_genes"/>
-                    <param name="y" value="n_counts"/>
-                    <param name="log" value="True"/>
-                    <conditional name="layers">
-                        <param name="use_layers" value="false"/>
-                    </conditional>
+                <param name="method" value="pl.rank_genes_groups_dotplot"/>
+                <conditional name="var_names">
+                  <param name="type" value="customfile"/>
+                  <param name="var_names" value="tl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.tsv"/>
                 </conditional>
-                <param name="use_raw" value="False"/>
-                <param name="sort_order" value="True"/>
-                <section name="plot">
-                    <param name="projection" value="2d"/>
-                    <param name="legend_loc" value="right margin"/>
-                    <param name="legend_fontsize" value="1"/>
-                    <param name="legend_fontweight" value="normal"/>
-                    <param name="palette" value="bwr"/>
-                    <param name="frameon" value="False"/>
-                    <param name="size" value="1"/>
-                    <param name="title" value="A title"/>
-                </section>
             </conditional>
             <section name="advanced_common">
                 <param name="show_log" value="true" />
             </section>
             <output name="hidden_output">
                 <assert_contents>
-                    <has_text_matching expression="sc.pl.scatter"/>
-                    <has_text_matching expression="use_raw=False"/>
-                    <has_text_matching expression="sort_order=True"/>
-                    <has_text_matching expression="projection='2d'"/>
-                    <has_text_matching expression="legend_loc='right margin'"/>
-                    <has_text_matching expression="legend_fontsize=1"/>
-                    <has_text_matching expression="legend_fontweight='normal'"/>
-                    <has_text_matching expression="frameon=False"/>
-                    <has_text_matching expression="size=1.0"/>
-                    <has_text_matching expression="title='A title'"/>
+                    <has_text_matching expression="sc.pl.rank_genes_groups_dotplot"/>
+                    <has_text_matching expression="log=False"/>
+                    <has_text_matching expression="use_raw=None"/>
+                    <has_text_matching expression="dendrogram=False"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.scatter.pbmc68k_reduced.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.png" ftype="png" compare="image_diff"/>
         </test>
+        
+        <!-- test 39: pl.rank_genes_groups_dotplot with marker list -->
         <test expect_num_outputs="2">
-            <!-- test 35: pl.rank_genes_groups_dotplot with marker list -->
             <param name="adata" value="cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad" />
             <param name="format" value="png"/>
             <conditional name="method">
                 <param name="method" value="pl.rank_genes_groups_dotplot"/>
                 <conditional name="var_names">
                   <param name="type" value="customfile"/>
-                  <param name="var_names" value="tl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.tsv"/>
+                  <param name="var_names" value="tl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.tsv"/>
                 </conditional>
-                <param name="groupby" value="bulk_labels"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
-                <param name="dendrogram" value="False"/>
-                <param name="color_map" value="viridis"/>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0" />
-                    <param name="edgecolors" value="face"/>
-                </section>
             </conditional>
             <section name="advanced_common">
                 <param name="show_log" value="true" />
@@ -2284,53 +2173,30 @@ sc.pl.rank_genes_groups_stacked_violin(
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pl.rank_genes_groups_dotplot"/>
-                    <has_text_matching expression="groupby='bulk_labels'"/>
                     <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="use_raw=None"/>
                     <has_text_matching expression="dendrogram=False"/>
-                    <has_text_matching expression="color_map='viridis'"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face'"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png" ftype="png" compare="image_diff"/>
         </test>
+
+        <!-- test 40 -->
         <test expect_num_outputs="2">
-            <!-- test 36: pl.rank_genes_groups_dotplot with marker list -->
             <param name="adata" value="cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad" />
             <param name="format" value="png"/>
             <conditional name="method">
-                <param name="method" value="pl.rank_genes_groups_dotplot"/>
-                <conditional name="var_names">
-                  <param name="type" value="customfile"/>
-                  <param name="var_names" value="tl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.tsv"/>
-                </conditional>
-                <param name="groupby" value="bulk_labels"/>
-                <param name="log" value="False"/>
-                <param name="use_raw" value="False"/>
-                <param name="dendrogram" value="False"/>
-                <param name="color_map" value="viridis"/>
-                <section name="matplotlib_pyplot_scatter">
-                    <param name="linewidths" value="0" />
-                    <param name="edgecolors" value="face"/>
-                </section>
+                <param name="method" value="pl.rank_genes_groups_tracksplot"/>
             </conditional>
             <section name="advanced_common">
                 <param name="show_log" value="true" />
             </section>
             <output name="hidden_output">
                 <assert_contents>
-                    <has_text_matching expression="sc.pl.rank_genes_groups_dotplot"/>
-                    <has_text_matching expression="groupby='bulk_labels'"/>
-                    <has_text_matching expression="log=False"/>
-                    <has_text_matching expression="use_raw=False"/>
-                    <has_text_matching expression="dendrogram=False"/>
-                    <has_text_matching expression="color_map='viridis'"/>
-                    <has_text_matching expression="lw=0.0"/>
-                    <has_text_matching expression="ec='face'"/>
+                    <has_text_matching expression="sc.pl.rank_genes_groups_tracksplot"/>
                 </assert_contents>
             </output>
-            <output name="out_png" file="pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png" ftype="png" compare="sim_size"/>
+            <output name="out_png" file="pl.rank_genes_groups_tracksplot.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png" ftype="png" compare="image_diff"/>
         </test>
     </tests>
     <help><![CDATA[
@@ -2372,6 +2238,15 @@ expressing the gene can be visualized for each cluster.
 More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.pl.dotplot.html>`__
 
+Generic: Tracks plot (`pl.tracksplot`)
+======================================
+
+In this type of plot each var_name is plotted as a filled line plot where the y values correspond to the var_name values and x is each of the cells.
+Best results are obtained when using raw counts that are not log.
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/generated/scanpy.pl.tracksplot.html>`__
+
 Generic: Violin plot (`pl.violin`)
 ==================================
 
@@ -2438,6 +2313,15 @@ It produces Supp. Fig. 5c of Zheng et al. (2017) and MeanVarPlot() of Seurat.
 More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.highly_variable_genes.html>`__
 
+Preprocessing: Plot histogram of doublet scores for observed transcriptomes and simulated doublets (`pl.scrublet_score_distribution`)
+=====================================================================================================================================
+
+The histogram for simulated doublets is useful for determining the correct doublet score threshold.
+Scrublet must have been run previously with the input object.
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.scrublet_score_distribution.html>`__
+
 PCA: Scatter plot in PCA coordinates (`pl.pca`)
 ===============================================
 
@@ -2483,11 +2367,24 @@ Embeddings: Scatter plot in Diffusion Map basis (`pl.diffmap`)
 More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.diffmap.html>`__
 
-Branching trajectories and pseudotime, clustering: Plot groups and pseudotime (`pl.dpt_groups_pseudotime`)
-===========================================================================================================
+Embeddings: Scatter plot in graph-drawing basis (`pl.draw_graph`)
+=================================================================
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.draw_graph.html>`__
+
+Embeddings: Plot the density of cells in an embedding (per condition) (`pl.embedding_density`)
+==============================================================================================
 
 More details on the `scanpy documentation
-<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.dpt_groups_pseudotime.html>`__
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.embedding_density.html>`__
+
+.. This function is commented out because it is not compatible with pandas version. If the issue is not resolved in the next update, this should be removed.
+.. Branching trajectories and pseudotime, clustering: Plot groups and pseudotime (`pl.dpt_groups_pseudotime`)
+.. ===========================================================================================================
+
+.. More details on the `scanpy documentation
+.. <https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.dpt_groups_pseudotime.html>`__
 
 Branching trajectories and pseudotime, clustering: Heatmap of pseudotime series (`pl.dpt_timeseries`)
 =====================================================================================================
@@ -2533,11 +2430,11 @@ Marker genes: Plot ranking of genes as violin plot (`pl.rank_genes_groups_violin
 More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.rank_genes_groups_violin.html>`__
 
-Marker genes: Plot ranking of genes as dotplot plot (`pl.rank_genes_groups_dotplot`)
-====================================================================================
+Marker genes: Plot ranking of genes as stacked violin plot (`pl.rank_genes_groups_stacked_violin`)
+==================================================================================================
 
 More details on the `scanpy documentation
-<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.rank_genes_groups_dotplot.html>`__
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.rank_genes_groups_stacked_violin.html>`__
 
 Marker genes: Plot ranking of genes as heatmap plot (`pl.rank_genes_groups_heatmap`)
 ====================================================================================
@@ -2545,17 +2442,19 @@ Marker genes: Plot ranking of genes as heatmap plot (`pl.rank_genes_groups_heatm
 More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.rank_genes_groups_heatmap.html>`__
 
+Marker genes: Plot ranking of genes as dotplot plot (`pl.rank_genes_groups_dotplot`)
+====================================================================================
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.rank_genes_groups_dotplot.html>`__
+
 Marker genes: Plot ranking of genes as matrixplot plot (`pl.rank_genes_groups_matrixplot`)
 ==========================================================================================
 
 More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.rank_genes_groups_matrixplot.html>`__
 
-Marker genes: Plot ranking of genes as stacked violin plot (`pl.rank_genes_groups_stacked_violin`)
-==================================================================================================
-
-More details on the `scanpy documentation
-<https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pl.rank_genes_groups_stacked_violin.html>`__
-    ]]></help>
+    ]]>
+    </help>
     <expand macro="citations"/>
 </tool>
diff --git a/tools/scanpy/remove_confounders.xml b/tools/scanpy/remove_confounders.xml
index 6c355c721f8..76bceab1d3a 100644
--- a/tools/scanpy/remove_confounders.xml
+++ b/tools/scanpy/remove_confounders.xml
@@ -1,67 +1,164 @@
-<tool id="scanpy_remove_confounders" name="Remove confounders" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
+<tool id="scanpy_remove_confounders" name="Scanpy remove confounders" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
     <description>with scanpy</description>
     <macros>
         <import>macros.xml</import>
     </macros>
     <expand macro="bio_tools"/>
-    <expand macro="requirements"/>
+    <expand macro="requirements">
+        <requirement type="package" version="1.6.0">bbknn</requirement>
+        <requirement type="package" version="0.0.10">harmonypy</requirement>
+        <requirement type="package" version="1.7.4">scanorama</requirement>
+        <requirement type="package" version="0.5.13">pynndescent</requirement>
+    </expand>
     <command detect_errors="exit_code"><![CDATA[
 @CMD@
       ]]></command>
     <configfiles>
         <configfile name="script_file"><![CDATA[
-@CMD_imports@
-@CMD_read_inputs@
+@CMD_IMPORTS@
+@CMD_READ_INPUTS@
 
-#if $method.method == "pp.regress_out"
+#if str($method.method) == 'pp.regress_out':
+print("stats before regress_out:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
+
+import os
 sc.pp.regress_out(
    adata=adata,
+   #if str($method.layer) != '':
+   layer='$method.layer',
+   #end if
    #set $keys = [str(x.strip()) for x in str($method.keys).split(',')]
    keys=$keys,
+   n_jobs = int(os.getenv("GALAXY_SLOTS", 4)),
    copy=False)
 
-#else if $method.method == "pp.mnn_correct"
-    #for i, filepath in enumerate($methods.extra_adata)
-adata_$i = ad.read('$filepath')
-    #end for
+print("stats after regress_out:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
+
+## This function is commented out because the conda package is not working. Please add this if there is user demand and the conda package is fixed. If not please remove in the next update.
+## #else if str($method.method) == 'external.pp.mnn_correct':
+##     #if $method.extra_adata:
+##     #for i, filepath in enumerate($method.extra_adata)
+## adata_$i = sc.read_h5ad('$filepath')
+##     #end for
+##     #end if
+## import os
+## corrected = sc.external.pp.mnn_correct(
+##                 adata,
+##                 #if $method.extra_adata:
+##                 #for i, filepath in enumerate($method.extra_adata)
+##                 adata_$i,
+##                 #end for
+##                 #end if
+##                 #if str($method.var_subset) != '':
+##                 #set $var_subset=([x.strip() for x in str($method.var_subset).split(',')])
+##                 var_subset=$var_subset,
+##                 #end if
+##                 batch_key='$method.batch_key',
+##                 index_unique='$method.index_unique',
+##                 #if str($method.batch_categories) != '':
+##                 #set $batch_categories=([x.strip() for x in str($method.batch_categories).split(',')])
+##                 batch_categories=$batch_categories,
+##                 #end if
+##                 k=$method.k,
+##                 sigma=$method.sigma,
+##                 cos_norm_in=$method.cos_norm_in,
+##                 cos_norm_out=$method.cos_norm_out,
+##                 #if str($method.svd_dim) != '':
+##                 svd_dim=$method.svd_dim,
+##                 #end if
+##                 var_adj=$method.var_adj,
+##                 compute_angle=$method.compute_angle,
+##                 #if str($method.mnn_order) != '':
+##                 mnn_order='$method.mnn_order',
+##                 #end if
+##                 #if str($method.svd_mode) != '':
+##                 svd_mode='$method.svd_mode',
+##                 #end if
+##                 do_concatenate=True,
+##                 save_raw=True,
+##                 n_jobs = int(os.getenv("GALAXY_SLOTS", 4)))
+
+## adata = corrected[0]
+
 
-sc.pp.mnn_correct(
+#else if str($method.method) == 'pp.combat':
+print("stats before combat:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
+
+sc.pp.combat(
     adata,
-    #for i, filepath in enumerate($methods.extra_adata)
-    adata_$i,
-    #end for
-    #if $methods.var_subset
-    #set $var_subset=([x.strip() for x in str($method.var_subset).split(',')])
-    var_subset=$var_subset,
+    key='$method.key',
+    #if str($method.covariates) != '':
+        #set $covariates = [str(x.strip()) for x in str($method.covariates).split(',')]
+        covariates=$covariates,
     #end if
+    inplace=True)
+
+print("stats after combat:", "min=", adata.X.min(), "max=", adata.X.max(), "mean=", adata.X.mean())
+
+#else if str($method.method) == 'external.pp.bbknn':
+sc.external.pp.bbknn(
+    adata,
     batch_key='$method.batch_key',
-    index_unique='$method.index_unique'
-    #if $methods.batch_categories
-    #set $batch_categories=([x.strip() for x in str($method.batch_categories).split(',')])
-    batch_categories=$batch_categories,
+    use_rep='$method.use_rep',
+    #if str($method.approx.approx_method) == 'no':
+    approx=False,
+    #else if str($method.approx.approx_method) == 'annoy':
+    approx=True,
+    use_annoy=True,
+    annoy_n_trees=$method.approx.annoy_n_trees,
+    #else if str($method.approx.approx_method) == 'pyNNDescent':
+    approx=True,
+    use_annoy=False,
+    pynndescent_n_neighbors=$method.approx.pynndescent_n_neighbors,
+    pynndescent_random_state=$method.approx.pynndescent_random_state,
     #end if
-    k=$method.k,
-    sigma=$method.sigma,
-    cos_norm_in=$method.cos_norm_in,
-    cos_norm_out=$method.cos_norm_out,
-    svd_dim=$method.svd_dim,
-    var_adj=$method.var_adj,
-    compute_angle=$method.compute_angle,
-    mnn_order='$method.mnn_order',
-    svd_mode='$method.svd_mode',
-    do_concatenate=True,
-    save_raw=True,
-    n_jobs=\${GALAXY_SLOTS:-4})
-
-#else if $method.method == "pp.combat"
-sc.pp.combat(
+    metric='$method.metric',
+    neighbors_within_batch=$method.neighbors_within_batch,
+    n_pcs=$method.n_pcs,
+    #if str($method.trim) != '':
+    trim=$method.trim,
+    #end if
+    set_op_mix_ratio=$method.set_op_mix_ratio,
+    local_connectivity=$method.local_connectivity,
+    copy=False)
+
+#else if str($method.method) == 'external.pp.harmony_integrate':
+sc.external.pp.harmony_integrate(
     adata,
     key='$method.key',
-    inplace=True)
+    basis='$method.basis',
+    adjusted_basis='$method.adjusted_basis',
+    #if str($method.theta) != '':
+    theta=$method.theta,
+    #end if
+    #if str($method.lamb) != '':
+    lamb=$method.lamb,
+    #end if
+    sigma=$method.sigma,
+    #if str($method.nclust) != '':
+    nclust=$method.nclust,
+    #end if
+    tau=$method.tau,
+    block_size=$method.block_size,
+    max_iter_harmony=$method.max_iter_harmony,
+    max_iter_kmeans=$method.max_iter_kmeans,
+    epsilon_cluster=$method.epsilon_cluster,
+    epsilon_harmony=$method.epsilon_harmony)
 
+#else if str($method.method) == 'external.pp.scanorama_integrate':
+sc.external.pp.scanorama_integrate(
+    adata,
+    key='$method.key',
+    basis='$method.basis',
+    adjusted_basis='$method.adjusted_basis',
+    knn=$method.knn,
+    sigma=$method.sigma,
+    approx=$method.approx,
+    alpha=$method.alpha,
+    batch_size=$method.batch_size)
 #end if
 
-@CMD_anndata_write_outputs@
+@CMD_ANNDATA_WRITE_OUTPUTS@
 ]]></configfile>
     </configfiles>
     <inputs>
@@ -69,21 +166,29 @@ sc.pp.combat(
         <conditional name="method">
             <param argument="method" type="select" label="Method used for plotting">
                 <option value="pp.regress_out">Regress out unwanted sources of variation, using 'pp.regress_out'</option>
-                <option value="pp.mnn_correct">Correct batch effects by matching mutual nearest neighbors, using 'pp.mnn_correct'</option>
+                <!-- This function is commented out because the conda package is not working. Please add this if there is user demand and the conda package is fixed. If not please remove in the next update. -->
+                <!-- <option value="external.pp.mnn_correct">Correct batch effects by matching mutual nearest neighbors, using 'pp.mnn_correct'</option> -->
                 <option value="pp.combat">Correct batch effects with ComBat function, using 'pp.combat'</option>
+                <option value="external.pp.bbknn">Batch effect removal with Batch balanced KNN (BBKNN), using 'external.pp.bbknn'</option>
+                <option value="external.pp.harmony_integrate">Integrate multiple single-cell experiments with Harmony, using 'external.pp.harmony_integrate'</option>
+                <option value="external.pp.scanorama_integrate">Integrate multiple single-cell experiments with Scanorama, using 'external.pp.scanorama_integrate'</option>
             </param>
             <when value="pp.regress_out">
+                <param argument="layer" type="text" value="" label="Which element of layers to regress on">
+                    <expand macro="sanitize_query"/>
+                </param>
                 <param argument="keys" type="text" value="" label="Keys for observation annotation on which to regress on" help="Keys separated by a comma">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
             </when>
-            <when value="pp.mnn_correct">
+            <!-- This function is commented out because the conda package is not working. Please add this if there is user demand and the conda package is fixed. If not please remove in the next update. -->
+            <!-- <when value="external.pp.mnn_correct">
                 <param name="extra_adata" type="data" multiple="true" optional="true" format="h5ad" label="Extra annotated data matrix" help="They should have same number of variables."/>
                 <param argument="var_subset" type="text" value="" optional="true" label="The subset of vars to be used when performing MNN correction" help="List of comma-separated key from '.var_names'. If not set, all vars are used">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="batch_key" type="text" value="batch" label="Batch key for the concatenate">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param name="index_unique" type="select" label="Separator to join the existing index names with the batch category" help="Leave it empty to keep existing indices">
                     <option value="-">-</option>
@@ -92,7 +197,7 @@ sc.pp.combat(
                     <option value="/">/</option>
                 </param>
                 <param argument="batch_categories" type="text" value="" optional="true" label="Batch categories for the concatenate" help="List of comma-separated key">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param argument="k" type="integer" value="20" label="Number of mutual nearest neighbors"/>
                 <param argument="sigma" type="float" value="1" label="The bandwidth of the Gaussian smoothing kernel used to compute the correction vectors"/>
@@ -102,18 +207,89 @@ sc.pp.combat(
                 <param argument="var_adj" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Adjust variance of the correction vectors?" help="This step takes most computing time."/>
                 <param argument="compute_angle" type="boolean" truevalue="True" falsevalue="False" checked="false" label="compute the angle between each cell’s correction vector and the biological subspace of the reference batch?"/>
                 <param argument="mnn_order" type="text" value="" optional="true" label="The order in which batches are to be corrected" help="List of comma-separated key. If not set, datas are corrected sequentially">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
                 </param>
                 <param name="svd_mode" type="select" label="SVD mode">
                     <option value="svd">svd: SVD using a non-randomized SVD-via-ID algorithm</option>
                     <option value="rsvd" selected="true">rsvd: SVD using a randomized SVD-via-ID algorithm</option>
                     <option value="irlb">irlb: truncated SVD by implicitly restarted Lanczos bidiagonalization</option>
                 </param>
-            </when>
+            </when> -->
             <when value="pp.combat">
                 <param argument="key" type="text" value="batch" label="Key to a categorical annotation from adata.obs that will be used for batch effect removal">
-                    <expand macro="sanitize_query" />
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="covariates" type="text" value="" optional="true" label="Additional covariates besides the batch variable such as adjustment variables or biological condition.">
+                    <expand macro="sanitize_query"/>
+                </param>
+            </when>
+            <when value="external.pp.bbknn">
+                <param argument="batch_key" type="text" value="batch" label="Batch key for the concatenate">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="use_rep" type="text" value="X_pca" label="The dimensionality reduction in .obsm to use for neighbour detection">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <conditional name="approx">
+                    <param name="approx_method" type="select" label="Approximate neighbour finding">
+                        <option value="annoy" selected="true">Yes, using ANNOY algorithm</option>
+                        <option value="pyNNDescent">Yes, using pyNNDescent</option>
+                        <option value="no">Do not use approximate neighbor finding</option>
+                    </param>
+                    <when value="annoy">
+                        <param argument="annoy_n_trees" type="integer" value="10" label="The number of trees to construct in the annoy forest" help="More trees give higher precision when querying, at the cost of increased run time and resource intensity"/>
+                    </when>
+                    <when value="pyNNDescent">
+                        <param argument="pynndescent_n_neighbors" type="integer" value="30" label="The number of neighbours to include in the approximate neighbour graph" help="More neighbours give higher precision when querying, at the cost of increased run time and resource intensity"/>
+                        <param argument="pynndescent_random_state" type="integer" value="0" label="The RNG seed to use when creating the graph"/>
+                    </when>
+                    <when value="no"/>
+                </conditional>
+                <param name="metric" type="select" label="Distance metric to use for the data">
+                    <expand macro="distance_metric_options"/>
                 </param>
+                <param argument="neighbors_within_batch" type="integer" value="3" label="Number of top neighbours to report for each batch" help="total number of neighbours in the initial k-nearest-neighbours computation will be this number times the number of batches. This then serves as the basis for the construction of a symmetrical matrix of connectivities"/>
+                <param argument="n_pcs" type="integer" value="50" label="Number of dimensions to use in the analysis" help="in case of PCA, principal components"/>
+                <param argument="trim" type="integer" value="" optional="true" label="Trim the neighbours of each cell to these many top connectivities" help=" The lower the value the more independent the individual populations, at the cost of more conserved batch effect. If not set, sets the parameter value automatically to 10 times neighbors_within_batch times the number of batches. Set to 0 to skip."/>
+                <param argument="set_op_mix_ratio" type="float" value="1.0" min="0" max="1" label="UMAP connectivity computation parameter" help="controlling the blend between a connectivity matrix formed exclusively from mutual nearest neighbour pairs (0) and a union of all observed neighbour relationships with the mutual pairs emphasised (1)"/>
+                <param argument="local_connectivity" type="integer" value="1" label="Number of nearest neighbors of each cell are assumed to be fully connected"/>
+            </when>
+            <when value="external.pp.harmony_integrate">
+                <param argument="key" type="text" value="batch" label="The name of the column in adata.obs that differentiates among experiments/batches">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="basis" type="text" value="X_pca" label="The name of the field in adata.obsm where the PCA table is stored">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="adjusted_basis" type="text" value="X_pca_harmony" label="The name of the field in adata.obsm where the adjusted PCA table will be stored after running this function">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="theta" type="integer" value="" optional="true" label="Diversity clustering penalty parameter" help="Default theta=2. theta=0 does not encourage any diversity. Larger values of theta result in more diverse clusters."/>
+                <param argument="lamb" type="integer" value="" optional="true" min="1" label="Ridge regression penalty parameter" help="Default lamb=1. Lambda must be strictly positive. Smaller values result in more aggressive correction."/>
+                <param argument="sigma" type="float" value="0.1" label="Width of soft kmeans clusters" help="Sigma scales the distance from a cell to cluster centroids. Larger values of sigma result in cells assigned to more clusters. Smaller values of sigma make soft kmeans cluster approach hard clustering."/>
+                <param argument="nclust" type="integer" value="" optional="true" label="Number of clusters in model" help="nclust=1 equivalent to simple linear regression."/>
+                <param argument="tau" type="integer" value="0" label="Expected number of cells per cluster" help="Protection against overclustering small datasets with large ones"/>
+                <param argument="block_size" type="float" value="0.05" min="0" max="1" label="Proportion of cells to update during clustering" help="Larger values may be faster but less accurate"/>
+                <param argument="max_iter_harmony" type="integer" value="10" label="Maximum number of rounds to run Harmony" help="One round of Harmony involves one clustering and one correction step"/>
+                <param argument="max_iter_kmeans" type="integer" value="20" label="Maximum number of rounds to run clustering at each round of Harmony"/>
+                <param argument="epsilon_cluster" type="float" value="1e-5" label="Convergence tolerance for clustering round of Harmony"/>
+                <param argument="epsilon_harmony" type="float" value="1e-4" label="Convergence tolerance for Harmony"/>
+            </when>
+            <when value="external.pp.scanorama_integrate">
+                <param argument="key" type="text" value="batch" label="The name of the column in adata.obs that differentiates among experiments/batches">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="basis" type="text" value="X_pca" label="The name of the field in adata.obsm where the PCA table is stored">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="adjusted_basis" type="text" value="X_scanorama" label="The name of the field in adata.obsm where the adjusted PCA table will be stored after running this function">
+                    <expand macro="sanitize_query"/>
+                </param>
+                <param argument="knn" type="integer" value="20" label="Number of nearest neighbors to use for matching"/>
+                <param argument="sigma" type="integer" value="15" label="Correction smoothing parameter on Gaussian kernel"/>
+                <param argument="approx" type="boolean" truevalue="True" falsevalue="False" checked="true" label="Use approximate nearest neighbors with Python annoy" help="greatly speeds up matching runtime"/>
+                <param argument="alpha" type="float" value="0.1" label="Alignment score minimum cutoff"/>
+                <param argument="batch_size" type="integer" value="5000" label="The batch size used in the alignment vector computation" help="Useful when integrating very large (>100k samples) datasets. Set to large value that runs within available memory."/>
             </when>
         </conditional>
         <expand macro="inputs_common_advanced"/>
@@ -122,76 +298,228 @@ sc.pp.combat(
         <expand macro="anndata_outputs"/>
     </outputs>
     <tests>
+        
+        <!-- test 1 -->
         <test expect_num_outputs="2">
-            <!-- test 0 -->
-            <param name="adata" value="krumsiek11.h5ad" />
+            <param name="adata" value="pp.pca.krumsiek11.batch.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.regress_out"/>
-                <param name="keys" value="cell_type"/>
+                <param name="keys" value="batch"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.regress_out"/>
-                    <has_text_matching expression="keys=\['cell_type'\]"/>
+                    <has_text_matching expression="keys=\['batch'\]"/>
+                    <has_text_matching expression="stats before regress_out: min= -0.0163 max= 1.0106 mean= 0.2864376"/>
+                    <has_text_matching expression="stats after regress_out: min= -0.7017021868145134 max= 0.7091581022301392 mean= -1.730938624756494e-16"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="varm/PCs"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.regress_out.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
-        <!--<test expect_num_outputs="2">
-            < test 2 >
-            <param name="adata" value="krumsiek11.h5ad" />
+
+        <!-- This function is commented out because the conda package is not working. Please add this if there is user demand and the conda package is fixed. If not please remove in the next update. -->
+        <!-- test 2 -->
+        <!-- <test expect_num_outputs="2">
+            <param name="adata" value="pp.pca.krumsiek11.batch.h5ad"/>
+            <param name="extra_adata" value="pp.pca.krumsiek11.batch.h5ad"/>
             <conditional name="method">
-                <param name="method" value="pp.mnn_correct"/>
-                <param name="reg_keys" value="cell_type"/>
+                <param name="method" value="external.pp.mnn_correct"/>
+                <param name="batch_key" value="batch"/>
             </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
             <assert_stdout>
-                <has_text_matching expression="sc.pp.mnn_correct"/>
-                <has_text_matching expression="keys='cell_type'"/>
+                <has_text_matching expression="I_have_to_check"/>
             </assert_stdout>
-            <output name="anndata_out" file="pp.mnn_correct.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
-        </test>-->
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="sc.external.pp.mnn_correct"/>
+                    <has_text_matching expression="batch_key='batch'"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" file="external.pp.mnn_correct.krumsiek11.h5ad" ftype="h5ad" compare="sim_size"/>
+        </test> -->
+
+        <!-- test 3 -->
         <test expect_num_outputs="2">
-            <!-- test 1 -->
-            <param name="adata" value="blobs.h5ad" />
+            <param name="adata" value="pp.pca.krumsiek11.batch.h5ad"/>
             <conditional name="method">
                 <param name="method" value="pp.combat"/>
-                <param name="key" value="blobs"/>
             </conditional>
             <section name="advanced_common">
-                <param name="show_log" value="true" />
+                <param name="show_log" value="true"/>
             </section>
             <output name="hidden_output">
                 <assert_contents>
                     <has_text_matching expression="sc.pp.combat"/>
-                    <has_text_matching expression="key='blobs'"/>
+                    <has_text_matching expression="key='batch'"/>
+                    <has_text_matching expression="stats before combat: min= -0.0163 max= 1.0106 mean= 0.2864376"/>
+                    <has_text_matching expression="stats after combat: min= -0.07474318799213325 max= 1.2280063438242503 mean= 0.2870530757430964"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obsm/X_pca"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 4 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="pp.pca.krumsiek11.batch.h5ad"/>
+            <conditional name="method">
+                <param name="method" value="external.pp.bbknn"/>
+                <param name="n_pcs" value="10"/>
+                <param name="set_op_mix_ratio" value="0.5"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="external.pp.bbknn"/>
+                    <has_text_matching expression="batch_key='batch'"/>
+                    <has_text_matching expression="use_rep='X_pca'"/>
+                    <has_text_matching expression="use_annoy=True"/>
+                    <has_text_matching expression="annoy_n_trees=10"/>
+                    <has_text_matching expression="neighbors_within_batch=3"/>
+                    <has_text_matching expression="n_pcs=10"/>
+                    <has_text_matching expression="set_op_mix_ratio=0.5"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/neighbors"/>
+                    <has_h5_keys keys="obsp/distances,obsp/connectivities"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 5 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="pp.pca.krumsiek11.batch.h5ad"/>
+            <conditional name="method">
+                <param name="method" value="external.pp.bbknn"/>
+                <conditional name="approx">
+                    <param name="approx_method" value="pyNNDescent"/>
+                    <param name="pynndescent_n_neighbors" value="10"/>
+                </conditional>
+                <param name="n_pcs" value="10"/>
+                <param name="set_op_mix_ratio" value="0.5"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="external.pp.bbknn"/>
+                    <has_text_matching expression="batch_key='batch'"/>
+                    <has_text_matching expression="use_rep='X_pca'"/>
+                    <has_text_matching expression="use_annoy=False"/>
+                    <has_text_matching expression="pynndescent_n_neighbors=10"/>
+                    <has_text_matching expression="pynndescent_random_state=0"/>
+                    <has_text_matching expression="neighbors_within_batch=3"/>
+                    <has_text_matching expression="n_pcs=10"/>
+                    <has_text_matching expression="set_op_mix_ratio=0.5"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="uns/neighbors"/>
+                    <has_h5_keys keys="obsp/distances,obsp/connectivities"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 6 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="pp.pca.krumsiek11.batch.h5ad"/>
+            <conditional name="method">
+                <param name="method" value="external.pp.harmony_integrate"/>
+                <param name="theta" value="2"/>
+                <param name="lamb" value="1"/>
+                <param name="block_size" value="0.1"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="external.pp.harmony_integrate"/>
+                    <has_text_matching expression="key='batch'"/>
+                    <has_text_matching expression="basis='X_pca'"/>
+                    <has_text_matching expression="adjusted_basis='X_pca_harmony'"/>
+                    <has_text_matching expression="theta=2"/>
+                    <has_text_matching expression="lamb=1"/>
+                    <has_text_matching expression="block_size=0.1"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obsm/X_pca_harmony"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- test 7 -->
+        <test expect_num_outputs="2">
+            <param name="adata" value="pp.pca.krumsiek11.batch.h5ad"/>
+            <conditional name="method">
+                <param name="method" value="external.pp.scanorama_integrate"/>
+                <param name="knn" value="2"/>
+                <param name="sigma" value="10"/>
+                <param name="batch_size" value="100"/>
+            </conditional>
+            <section name="advanced_common">
+                <param name="show_log" value="true"/>
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="external.pp.scanorama_integrate"/>
+                    <has_text_matching expression="key='batch'"/>
+                    <has_text_matching expression="basis='X_pca'"/>
+                    <has_text_matching expression="adjusted_basis='X_scanorama'"/>
+                    <has_text_matching expression="knn=2"/>
+                    <has_text_matching expression="sigma=1"/>
+                    <has_text_matching expression="batch_size=100"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" ftype="h5ad">
+                <assert_contents>
+                    <has_h5_keys keys="obsm/X_scanorama"/>
                 </assert_contents>
             </output>
-            <output name="anndata_out" file="pp.combat.blobs.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
     </tests>
     <help><![CDATA[
 Regress out unwanted sources of variation, using `pp.regress_out`
 =================================================================
 
-Regress out unwanted sources of variation, using simple linear regression. This is 
+Regress out unwanted sources of variation, using simple linear regression. This is
 inspired by Seurat's `regressOut` function in R.
 
 More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/scanpy.pp.regress_out.html>`__
 
-Correct batch effects by matching mutual nearest neighbors, using `pp.mnn_correct`
-==================================================================================
+.. This function is commented out because the conda package is not working. Please add this if there is user demand and the conda package is fixed. If not please remove in the next update.
+.. Correct batch effects by matching mutual nearest neighbors, using `external.pp.mnn_correct`
+.. ===========================================================================================
 
-This uses the implementation of mnnpy. Depending on do_concatenate, it returns AnnData objects in the 
-original order containing corrected expression values or a concatenated matrix or AnnData object.
+.. This uses the implementation of mnnpy. Depending on do_concatenate, it returns AnnData objects in the
+.. original order containing corrected expression values or a concatenated matrix or AnnData object.
 
-Be reminded that it is not advised to use the corrected data matrices for differential expression testing.
+.. Be reminded that it is not advised to use the corrected data matrices for differential expression testing.
 
-More details on the `scanpy documentation
-<https://scanpy.readthedocs.io/en/stable/generated/scanpy.external.pp.mnn_correct.html>`__
+.. More details on the `scanpy documentation
+.. <https://scanpy.readthedocs.io/en/stable/generated/scanpy.external.pp.mnn_correct.html>`__
 
 
 Correct batch effects with ComBat function (`pp.combat`)
@@ -203,6 +531,33 @@ More details on the `scanpy documentation
 <https://scanpy.readthedocs.io/en/stable/api/generated/scanpy.pp.combat.html>`__
 
 
+Correct batch effects with bbknn function (`external.pp.bbknn`)
+===============================================================
+
+Batch balanced kNN alters the kNN procedure to identify each cell’s top neighbours in each batch separately instead of the entire cell pool with no accounting for batch. The nearest neighbours for each batch are then merged to create a final list of neighbours for the cell. Aligns batches in a quick and lightweight manner.
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/generated/scanpy.external.pp.bbknn.html>`__
+
+
+Correct batch effects with harmony function (`external.pp.harmony_integrate`)
+=============================================================================
+
+Harmony is an algorithm for integrating single-cell data from multiple experiments.
+As Harmony works by adjusting the principal components, this function should be run after performing PCA but before computing the neighbor graph.
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/generated/scanpy.external.pp.harmony_integrate.html>`__
+
+
+Correct batch effects with scanprama function (`external.pp.scanorama_integrate`)
+=================================================================================
+
+Scanprama is an algorithm for integrating single-cell data from multiple experiments stored in an AnnData object. This function should be run after performing PCA but before computing the neighbor graph.
+
+More details on the `scanpy documentation
+<https://scanpy.readthedocs.io/en/stable/generated/scanpy.external.pp.scanorama_integrate.html>`__
+
     ]]></help>
     <expand macro="citations"/>
 </tool>
diff --git a/tools/scanpy/test-data/cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad b/tools/scanpy/test-data/cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad
index cb1fab576b2..a0ff6c82bf4 100644
Binary files a/tools/scanpy/test-data/cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad and b/tools/scanpy/test-data/cosg.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_1.h5ad differ
diff --git a/tools/scanpy/test-data/external.pp.bbknn.krumsiek11.h5ad b/tools/scanpy/test-data/external.pp.bbknn.krumsiek11.h5ad
new file mode 100644
index 00000000000..b0c3b29cff4
Binary files /dev/null and b/tools/scanpy/test-data/external.pp.bbknn.krumsiek11.h5ad differ
diff --git a/tools/scanpy/test-data/external.pp.magic.all_genes.krumsiek11.h5ad b/tools/scanpy/test-data/external.pp.magic.all_genes.krumsiek11.h5ad
deleted file mode 100644
index 074cce38f53..00000000000
Binary files a/tools/scanpy/test-data/external.pp.magic.all_genes.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/external.pp.magic.pca_only.krumsiek11.h5ad b/tools/scanpy/test-data/external.pp.magic.pca_only.krumsiek11.h5ad
deleted file mode 100644
index de53754bd12..00000000000
Binary files a/tools/scanpy/test-data/external.pp.magic.pca_only.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pbmc68k_reduced.h5ad b/tools/scanpy/test-data/pbmc68k_reduced.h5ad
index 38d15e1c5cd..11568b60943 100644
Binary files a/tools/scanpy/test-data/pbmc68k_reduced.h5ad and b/tools/scanpy/test-data/pbmc68k_reduced.h5ad differ
diff --git a/tools/scanpy/test-data/pl.clustermap.krumsiek11.png b/tools/scanpy/test-data/pl.clustermap.krumsiek11.png
index cb355b5ec7e..ae5a28a1355 100644
Binary files a/tools/scanpy/test-data/pl.clustermap.krumsiek11.png and b/tools/scanpy/test-data/pl.clustermap.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png b/tools/scanpy/test-data/pl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png
index aaafda2a721..1bfe9655ae3 100644
Binary files a/tools/scanpy/test-data/pl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png and b/tools/scanpy/test-data/pl.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png differ
diff --git a/tools/scanpy/test-data/pl.dotplot.krumsiek11.png b/tools/scanpy/test-data/pl.dotplot.krumsiek11.png
index 80912949f4c..57ae4f2f532 100644
Binary files a/tools/scanpy/test-data/pl.dotplot.krumsiek11.png and b/tools/scanpy/test-data/pl.dotplot.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.dpt_timeseries.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png b/tools/scanpy/test-data/pl.dpt_timeseries.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png
index a01cbdf9c8c..e193161dba2 100644
Binary files a/tools/scanpy/test-data/pl.dpt_timeseries.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png and b/tools/scanpy/test-data/pl.dpt_timeseries.dpt.diffmap.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.png differ
diff --git a/tools/scanpy/test-data/pl.draw_graph.png b/tools/scanpy/test-data/pl.draw_graph.png
index 945b3d96049..36e794acf18 100644
Binary files a/tools/scanpy/test-data/pl.draw_graph.png and b/tools/scanpy/test-data/pl.draw_graph.png differ
diff --git a/tools/scanpy/test-data/pl.embedding_density.pbmc68k_reduced.png b/tools/scanpy/test-data/pl.embedding_density.pbmc68k_reduced.png
index 24df624e193..221c96d744f 100644
Binary files a/tools/scanpy/test-data/pl.embedding_density.pbmc68k_reduced.png and b/tools/scanpy/test-data/pl.embedding_density.pbmc68k_reduced.png differ
diff --git a/tools/scanpy/test-data/pl.heatmap.krumsiek11.png b/tools/scanpy/test-data/pl.heatmap.krumsiek11.png
index 1a7d034f442..d495f7bb209 100644
Binary files a/tools/scanpy/test-data/pl.heatmap.krumsiek11.png and b/tools/scanpy/test-data/pl.heatmap.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.highest_expr_genes.filter_genes_dispersion.krumsiek11-seurat.png b/tools/scanpy/test-data/pl.highest_expr_genes.filter_genes_dispersion.krumsiek11-seurat.png
index 7eb19bdd1d3..cba50e2d84f 100644
Binary files a/tools/scanpy/test-data/pl.highest_expr_genes.filter_genes_dispersion.krumsiek11-seurat.png and b/tools/scanpy/test-data/pl.highest_expr_genes.filter_genes_dispersion.krumsiek11-seurat.png differ
diff --git a/tools/scanpy/test-data/pl.highly_variable_genes.seurat.blobs.png b/tools/scanpy/test-data/pl.highly_variable_genes.seurat.blobs.png
index 5afcb1ef3d0..0a33ceaf83d 100644
Binary files a/tools/scanpy/test-data/pl.highly_variable_genes.seurat.blobs.png and b/tools/scanpy/test-data/pl.highly_variable_genes.seurat.blobs.png differ
diff --git a/tools/scanpy/test-data/pl.matrixplot.krumsiek11.png b/tools/scanpy/test-data/pl.matrixplot.krumsiek11.png
index e5d75912d27..95c2690d44f 100644
Binary files a/tools/scanpy/test-data/pl.matrixplot.krumsiek11.png and b/tools/scanpy/test-data/pl.matrixplot.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.paga.paul15_gauss_braycurtis.png b/tools/scanpy/test-data/pl.paga.paul15_gauss_braycurtis.png
index 0c7fe37c319..d8eba5fbad3 100644
Binary files a/tools/scanpy/test-data/pl.paga.paul15_gauss_braycurtis.png and b/tools/scanpy/test-data/pl.paga.paul15_gauss_braycurtis.png differ
diff --git a/tools/scanpy/test-data/pl.paga_compare.paul15_gauss_braycurtis.png b/tools/scanpy/test-data/pl.paga_compare.paul15_gauss_braycurtis.png
index 858afdec5c6..561242d6f63 100644
Binary files a/tools/scanpy/test-data/pl.paga_compare.paul15_gauss_braycurtis.png and b/tools/scanpy/test-data/pl.paga_compare.paul15_gauss_braycurtis.png differ
diff --git a/tools/scanpy/test-data/pl.pca.pbmc68k_reduced.CD3D_CD79A_components_2d.pdf b/tools/scanpy/test-data/pl.pca.pbmc68k_reduced.CD3D_CD79A_components_2d.pdf
index e88bbb34cfb..579226202e6 100644
Binary files a/tools/scanpy/test-data/pl.pca.pbmc68k_reduced.CD3D_CD79A_components_2d.pdf and b/tools/scanpy/test-data/pl.pca.pbmc68k_reduced.CD3D_CD79A_components_2d.pdf differ
diff --git a/tools/scanpy/test-data/pl.pca_loadings.pp.pca.krumsiek11.png b/tools/scanpy/test-data/pl.pca_loadings.pp.pca.krumsiek11.png
index 9ff0c1bf6d2..1be3ff9b75e 100644
Binary files a/tools/scanpy/test-data/pl.pca_loadings.pp.pca.krumsiek11.png and b/tools/scanpy/test-data/pl.pca_loadings.pp.pca.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.pca_overview.pp.pca.krumsiek11.png b/tools/scanpy/test-data/pl.pca_overview.pp.pca.krumsiek11.png
index e8aea21b359..e8a9f64750b 100644
Binary files a/tools/scanpy/test-data/pl.pca_overview.pp.pca.krumsiek11.png and b/tools/scanpy/test-data/pl.pca_overview.pp.pca.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.pca_variance_ratio.pp.pca.krumsiek11.png b/tools/scanpy/test-data/pl.pca_variance_ratio.pp.pca.krumsiek11.png
index 10a06ed4d9d..5bdf3e7bdb0 100644
Binary files a/tools/scanpy/test-data/pl.pca_variance_ratio.pp.pca.krumsiek11.png and b/tools/scanpy/test-data/pl.pca_variance_ratio.pp.pca.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.png b/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.png
index 7e0af20d80e..8e10a632ef0 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.png and b/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_1.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png b/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png
index 2c8e1089c41..d2993c06d1c 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png and b/tools/scanpy/test-data/pl.rank_genes_groups.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups.rank_genes_groups.krumsiek11.png b/tools/scanpy/test-data/pl.rank_genes_groups.rank_genes_groups.krumsiek11.png
index 461b00542e3..df7ff1d5799 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups.rank_genes_groups.krumsiek11.png and b/tools/scanpy/test-data/pl.rank_genes_groups.rank_genes_groups.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_dotplot.rank_genes_groups.krumsiek11.png b/tools/scanpy/test-data/pl.rank_genes_groups_dotplot.rank_genes_groups.krumsiek11.png
index de1627e8ac8..a9931830303 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_dotplot.rank_genes_groups.krumsiek11.png and b/tools/scanpy/test-data/pl.rank_genes_groups_dotplot.rank_genes_groups.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_heatmap.rank_genes_groups.krumsiek11.png b/tools/scanpy/test-data/pl.rank_genes_groups_heatmap.rank_genes_groups.krumsiek11.png
index 81baac35f5e..fe1ad855277 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_heatmap.rank_genes_groups.krumsiek11.png and b/tools/scanpy/test-data/pl.rank_genes_groups_heatmap.rank_genes_groups.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_matrixplot.rank_genes_groups.krumsiek11.png b/tools/scanpy/test-data/pl.rank_genes_groups_matrixplot.rank_genes_groups.krumsiek11.png
index 3b541916bad..a69099020b5 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_matrixplot.rank_genes_groups.krumsiek11.png and b/tools/scanpy/test-data/pl.rank_genes_groups_matrixplot.rank_genes_groups.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_stacked_violin.rank_genes_groups.krumsiek11.png b/tools/scanpy/test-data/pl.rank_genes_groups_stacked_violin.rank_genes_groups.krumsiek11.png
index c581cce512b..36d71d8ff00 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_stacked_violin.rank_genes_groups.krumsiek11.png and b/tools/scanpy/test-data/pl.rank_genes_groups_stacked_violin.rank_genes_groups.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_tracksplot.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png b/tools/scanpy/test-data/pl.rank_genes_groups_tracksplot.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png
new file mode 100644
index 00000000000..b5df09e786e
Binary files /dev/null and b/tools/scanpy/test-data/pl.rank_genes_groups_tracksplot.newton-cg.pbmc68k_highly_reduced_marker_filtered_1.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Ery.png b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Ery.png
index b65728fe117..7b870bf59ed 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Ery.png and b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Ery.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mk.png b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mk.png
index db704dc2566..7b890a0c71d 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mk.png and b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mk.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mo.png b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mo.png
index 9fe89735b79..62409c06589 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mo.png and b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Mo.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Neu.png b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Neu.png
index c51265ae9e2..9f1b4944027 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_violin.Neu.png and b/tools/scanpy/test-data/pl.rank_genes_groups_violin.Neu.png differ
diff --git a/tools/scanpy/test-data/pl.rank_genes_groups_violin.progenitor.png b/tools/scanpy/test-data/pl.rank_genes_groups_violin.progenitor.png
index b4274dea654..d04ba172c97 100644
Binary files a/tools/scanpy/test-data/pl.rank_genes_groups_violin.progenitor.png and b/tools/scanpy/test-data/pl.rank_genes_groups_violin.progenitor.png differ
diff --git a/tools/scanpy/test-data/pl.scatter.krumsiek11.png b/tools/scanpy/test-data/pl.scatter.krumsiek11.png
index 18adde30523..36e2bac81b2 100644
Binary files a/tools/scanpy/test-data/pl.scatter.krumsiek11.png and b/tools/scanpy/test-data/pl.scatter.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.scatter.pbmc68k_reduced.png b/tools/scanpy/test-data/pl.scatter.pbmc68k_reduced.png
index 96241c4c4a8..94f91a5bd1c 100644
Binary files a/tools/scanpy/test-data/pl.scatter.pbmc68k_reduced.png and b/tools/scanpy/test-data/pl.scatter.pbmc68k_reduced.png differ
diff --git a/tools/scanpy/test-data/pl.scatter.umap.pbmc68k_reduced.png b/tools/scanpy/test-data/pl.scatter.umap.pbmc68k_reduced.png
index 38cbe030af5..0ce7f2a5574 100644
Binary files a/tools/scanpy/test-data/pl.scatter.umap.pbmc68k_reduced.png and b/tools/scanpy/test-data/pl.scatter.umap.pbmc68k_reduced.png differ
diff --git a/tools/scanpy/test-data/pl.scrublet_score_distribution.png b/tools/scanpy/test-data/pl.scrublet_score_distribution.png
new file mode 100644
index 00000000000..393c3c3d8fb
Binary files /dev/null and b/tools/scanpy/test-data/pl.scrublet_score_distribution.png differ
diff --git a/tools/scanpy/test-data/pl.stacked_violin.krumsiek11.png b/tools/scanpy/test-data/pl.stacked_violin.krumsiek11.png
index 271b428928c..070d9f3a4d5 100644
Binary files a/tools/scanpy/test-data/pl.stacked_violin.krumsiek11.png and b/tools/scanpy/test-data/pl.stacked_violin.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.stacked_violin_pp.filter_genes_dispersion.krumsiek11-seurat.png b/tools/scanpy/test-data/pl.stacked_violin_pp.filter_genes_dispersion.krumsiek11-seurat.png
new file mode 100644
index 00000000000..c244c9349d2
Binary files /dev/null and b/tools/scanpy/test-data/pl.stacked_violin_pp.filter_genes_dispersion.krumsiek11-seurat.png differ
diff --git a/tools/scanpy/test-data/pl.tsne.krumsiek11.png b/tools/scanpy/test-data/pl.tsne.krumsiek11.png
index 81c2ade889e..e58a30d8b1e 100644
Binary files a/tools/scanpy/test-data/pl.tsne.krumsiek11.png and b/tools/scanpy/test-data/pl.tsne.krumsiek11.png differ
diff --git a/tools/scanpy/test-data/pl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.png b/tools/scanpy/test-data/pl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.png
index d935144b1d5..e73f79ae9c4 100644
Binary files a/tools/scanpy/test-data/pl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.png and b/tools/scanpy/test-data/pl.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.png differ
diff --git a/tools/scanpy/test-data/pl.violin.pbmc68k_reduced_custom.png b/tools/scanpy/test-data/pl.violin.pbmc68k_reduced_custom.png
index 996be8e38c7..cf7d76142ff 100644
Binary files a/tools/scanpy/test-data/pl.violin.pbmc68k_reduced_custom.png and b/tools/scanpy/test-data/pl.violin.pbmc68k_reduced_custom.png differ
diff --git a/tools/scanpy/test-data/pp.calculate_qc_metrics.sparce_csr_matrix.h5ad b/tools/scanpy/test-data/pp.calculate_qc_metrics.sparce_csr_matrix.h5ad
deleted file mode 100644
index 72ffbd66b44..00000000000
Binary files a/tools/scanpy/test-data/pp.calculate_qc_metrics.sparce_csr_matrix.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.downsample_counts.random-randint.h5ad b/tools/scanpy/test-data/pp.downsample_counts.random-randint.h5ad
deleted file mode 100644
index a7b2121f5f0..00000000000
Binary files a/tools/scanpy/test-data/pp.downsample_counts.random-randint.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.filter_cells.krumsiek11-min_counts.h5ad b/tools/scanpy/test-data/pp.filter_cells.krumsiek11-min_counts.h5ad
deleted file mode 100644
index 0c573119dcd..00000000000
Binary files a/tools/scanpy/test-data/pp.filter_cells.krumsiek11-min_counts.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.filter_genes.krumsiek11-min_counts.h5ad b/tools/scanpy/test-data/pp.filter_genes.krumsiek11-min_counts.h5ad
deleted file mode 100644
index ad34a988683..00000000000
Binary files a/tools/scanpy/test-data/pp.filter_genes.krumsiek11-min_counts.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.filter_rank_genes_groups.h5ad b/tools/scanpy/test-data/pp.filter_rank_genes_groups.h5ad
deleted file mode 100644
index 92ffcc5089c..00000000000
Binary files a/tools/scanpy/test-data/pp.filter_rank_genes_groups.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.highly_variable_genes.krumsiek11-cell_ranger.h5ad b/tools/scanpy/test-data/pp.highly_variable_genes.krumsiek11-cell_ranger.h5ad
deleted file mode 100644
index 50bbc1e3b64..00000000000
Binary files a/tools/scanpy/test-data/pp.highly_variable_genes.krumsiek11-cell_ranger.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.log1p.krumsiek11.h5ad b/tools/scanpy/test-data/pp.log1p.krumsiek11.h5ad
deleted file mode 100644
index a1a0074e85c..00000000000
Binary files a/tools/scanpy/test-data/pp.log1p.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.normalize_total.krumsiek11.h5ad b/tools/scanpy/test-data/pp.normalize_total.krumsiek11.h5ad
deleted file mode 100644
index d409d8c2806..00000000000
Binary files a/tools/scanpy/test-data/pp.normalize_total.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.filter_cells.krumsiek11-max_genes.h5ad b/tools/scanpy/test-data/pp.pca.krumsiek11.batch.h5ad
similarity index 58%
rename from tools/scanpy/test-data/pp.filter_cells.krumsiek11-max_genes.h5ad
rename to tools/scanpy/test-data/pp.pca.krumsiek11.batch.h5ad
index 00ebd0a7974..4cd7a70adb7 100644
Binary files a/tools/scanpy/test-data/pp.filter_cells.krumsiek11-max_genes.h5ad and b/tools/scanpy/test-data/pp.pca.krumsiek11.batch.h5ad differ
diff --git a/tools/scanpy/test-data/pp.pca.krumsiek11_chunk.h5ad b/tools/scanpy/test-data/pp.pca.krumsiek11_chunk.h5ad
deleted file mode 100644
index 65d11391daa..00000000000
Binary files a/tools/scanpy/test-data/pp.pca.krumsiek11_chunk.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.recipe_seurat.recipe_zheng17.h5ad b/tools/scanpy/test-data/pp.recipe_seurat.recipe_zheng17.h5ad
deleted file mode 100644
index b878dff879d..00000000000
Binary files a/tools/scanpy/test-data/pp.recipe_seurat.recipe_zheng17.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.recipe_weinreb17.paul15_subsample.updated.h5ad b/tools/scanpy/test-data/pp.recipe_weinreb17.paul15_subsample.updated.h5ad
deleted file mode 100644
index 2f23d9bb88e..00000000000
Binary files a/tools/scanpy/test-data/pp.recipe_weinreb17.paul15_subsample.updated.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.recipe_zheng17.random-randint.h5ad b/tools/scanpy/test-data/pp.recipe_zheng17.random-randint.h5ad
index 13013747917..c377b429122 100644
Binary files a/tools/scanpy/test-data/pp.recipe_zheng17.random-randint.h5ad and b/tools/scanpy/test-data/pp.recipe_zheng17.random-randint.h5ad differ
diff --git a/tools/scanpy/test-data/pp.scale.krumsiek11.h5ad b/tools/scanpy/test-data/pp.scale.krumsiek11.h5ad
deleted file mode 100644
index f6379a2bf13..00000000000
Binary files a/tools/scanpy/test-data/pp.scale.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.scale_max_value.krumsiek11.h5ad b/tools/scanpy/test-data/pp.scale_max_value.krumsiek11.h5ad
deleted file mode 100644
index f6379a2bf13..00000000000
Binary files a/tools/scanpy/test-data/pp.scale_max_value.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/tl.score_genes_cell_cycle.krumsiek11.h5ad b/tools/scanpy/test-data/pp.scrublet.krumsiek11.h5ad
similarity index 52%
rename from tools/scanpy/test-data/tl.score_genes_cell_cycle.krumsiek11.h5ad
rename to tools/scanpy/test-data/pp.scrublet.krumsiek11.h5ad
index 7f73a3627ec..a1ac2398188 100644
Binary files a/tools/scanpy/test-data/tl.score_genes_cell_cycle.krumsiek11.h5ad and b/tools/scanpy/test-data/pp.scrublet.krumsiek11.h5ad differ
diff --git a/tools/scanpy/test-data/pp.sqrt.krumsiek11.h5ad b/tools/scanpy/test-data/pp.sqrt.krumsiek11.h5ad
deleted file mode 100644
index 4c5a7cad101..00000000000
Binary files a/tools/scanpy/test-data/pp.sqrt.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.subsample.krumsiek11_fraction.h5ad b/tools/scanpy/test-data/pp.subsample.krumsiek11_fraction.h5ad
deleted file mode 100644
index 9196e5b5ff7..00000000000
Binary files a/tools/scanpy/test-data/pp.subsample.krumsiek11_fraction.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/pp.subsample.krumsiek11_n_obs.h5ad b/tools/scanpy/test-data/pp.subsample.krumsiek11_n_obs.h5ad
deleted file mode 100644
index 331b3e449c5..00000000000
Binary files a/tools/scanpy/test-data/pp.subsample.krumsiek11_n_obs.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/random-randint.h5ad b/tools/scanpy/test-data/random-randint.h5ad
index 90f5dd38139..27e815e2036 100644
Binary files a/tools/scanpy/test-data/random-randint.h5ad and b/tools/scanpy/test-data/random-randint.h5ad differ
diff --git a/tools/scanpy/test-data/sparce_csr_matrix.h5ad b/tools/scanpy/test-data/sparce_csr_matrix.h5ad
index 42332ef6d62..5f5788d5381 100644
Binary files a/tools/scanpy/test-data/sparce_csr_matrix.h5ad and b/tools/scanpy/test-data/sparce_csr_matrix.h5ad differ
diff --git a/tools/scanpy/test-data/tl.embedding_density.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad b/tools/scanpy/test-data/tl.embedding_density.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad
deleted file mode 100644
index 8330ebdb376..00000000000
Binary files a/tools/scanpy/test-data/tl.embedding_density.umap.neighbors_umap_euclidean.recipe_weinreb17.paul15_subsample.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/tl.embedding_density.umap.pbmc68k_reduced.h5ad b/tools/scanpy/test-data/tl.embedding_density.umap.pbmc68k_reduced.h5ad
index 4368d833abe..124b6f9166b 100644
Binary files a/tools/scanpy/test-data/tl.embedding_density.umap.pbmc68k_reduced.h5ad and b/tools/scanpy/test-data/tl.embedding_density.umap.pbmc68k_reduced.h5ad differ
diff --git a/tools/scanpy/test-data/tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad b/tools/scanpy/test-data/tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad
deleted file mode 100644
index 9b17133bd15..00000000000
Binary files a/tools/scanpy/test-data/tl.leiden.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad b/tools/scanpy/test-data/tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad
deleted file mode 100644
index ee425eefe7a..00000000000
Binary files a/tools/scanpy/test-data/tl.louvain.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad b/tools/scanpy/test-data/tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad
deleted file mode 100644
index d5cc448b8d7..00000000000
Binary files a/tools/scanpy/test-data/tl.paga.neighbors_gauss_braycurtis.recipe_weinreb17.paul15_subsample.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/tl.rank_genes_groups.liblinear.krumsiek11.h5ad b/tools/scanpy/test-data/tl.rank_genes_groups.liblinear.krumsiek11.h5ad
deleted file mode 100644
index 70de28282d2..00000000000
Binary files a/tools/scanpy/test-data/tl.rank_genes_groups.liblinear.krumsiek11.h5ad and /dev/null differ
diff --git a/tools/scanpy/test-data/tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad b/tools/scanpy/test-data/tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad
index 8e151d08d18..63c699b4f93 100644
Binary files a/tools/scanpy/test-data/tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad and b/tools/scanpy/test-data/tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad differ
diff --git a/tools/scanpy/test-data/tl.score_genes.krumsiek11.h5ad b/tools/scanpy/test-data/tl.score_genes.krumsiek11.h5ad
deleted file mode 100644
index 7ac8723043b..00000000000
Binary files a/tools/scanpy/test-data/tl.score_genes.krumsiek11.h5ad and /dev/null differ