Merge pull request #68 from itrujnara/dev

Add MERGE_IDS subworkflow

README.md

@@ -1,7 +1,7 @@
 <h1>
   <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/images/nf-core-reportho_logo_dark.png">
-    <img alt="nf-core/reportho" src="docs/images/nf-core-reportho_logo_light.png">
+    <source media="(prefers-color-scheme: dark)" srcset="docs/images/nf-core-reportho_logo_hex_dark.png">
+    <img alt="nf-core/reportho" src="docs/images/nf-core-reportho_logo_hex_light.png">
   </picture>
 </h1>
 

conf/modules.config

@@ -77,7 +77,43 @@ process {
         maxRetries = 3
     }
 
-    withName: 'CONCAT_FASTA' {
+    withName: 'SPLIT_ID_FORMAT' {
+        publishDir = [
+            path: { "${params.outdir}/sequences" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'FETCH_UNIPROT_SEQUENCES' {
+        publishDir = [
+            path: { "${params.outdir}/sequences" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'FETCH_ENSEMBL_IDMAP' {
+        publishDir = [
+            path: { "${params.outdir}/sequences" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'FETCH_ENSEMBL_SEQUENCES' {
+        publishDir = [
+            path: { "${params.outdir}/sequences" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'FETCH_REFSEQ_SEQUENCES' {
         publishDir = [
             path: { "${params.outdir}/sequences" },
             mode: params.publish_dir_mode,
@@ -86,6 +122,23 @@ process {
         ]
     }
 
+    withName: 'FETCH_OMA_SEQUENCES' {
+        publishDir = [
+            path: { "${params.outdir}/sequences" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'CONCAT_FASTA' {
+        publishDir = [
+            path: { "${params.outdir}/sequences" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'CONCAT_HITS' {
         ext.prefix = {"${meta.id}_hits.txt"}
         publishDir = [
@@ -106,6 +159,68 @@ process {
         ]
     }
 
+    withName: 'MERGE_FASTA_IDS' {
+        ext.args2  = "\'/^>/ { split(\$0, arr, \"|\"); print substr(arr[1], 2) }\'"
+        ext.prefix = {"${meta.id}_ids"}
+        ext.suffix = "txt"
+        publishDir = [
+            path: { "${params.outdir}/merge" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'DIAMOND_CLUSTER' {
+        ext.args = "--approx-id 90"
+        ext.prefix = { "${meta.id}_${db.toString().tokenize(".")[0].tokenize("_")[-1]}" }
+        publishDir = [
+            path: { "${params.outdir}/merge" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'POSTPROCESS_DIAMOND' {
+        ext.args = "-F\'\\t\'"
+        ext.args2 = """\'{
+            split(\$1, col1, "|");
+            split(\$2, col2, "|");
+            if (col1[1] != col2[1]) {
+                print col1[1] "\\t" col2[1];
+            } else {
+                print col1[1];
+            }
+        }\'"""
+        ext.prefix = { "${meta.id}_ids_diamond" }
+        ext.suffix = "txt"
+        publishDir = [
+            path: { "${params.outdir}/merge" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'GROUP_DIAMOND' {
+        ext.args2 = "\'{if (NF == 1) a[\$1]=\$1; else for (i=2; i<=NF; i++) a[\$1]=a[\$1] \"\\t\" \$i} END {for (key in a) print key a[key]}\'"
+        ext.prefix = { "${meta.id}_clusters" }
+        ext.suffix = "txt"
+        publishDir = [
+            path: { "${params.outdir}/merge" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            enabled: params.output_intermediates
+        ]
+    }
+
+    withName: 'REDUCE_IDMAP' {
+        ext.args = "-F\'\t\'"
+        ext.args2 = "\'NF >= 2\'"
+        ext.prefix = { "${meta.id}_idmap" }
+    }
+
     withName: 'MERGE_CSV' {
         ext.args = '-f 1 --outer-join --na 0'
         publishDir = [

modules.json

@@ -20,11 +20,21 @@
                         "git_sha": "614abbf126f287a3068dc86997b2e1b6a93abe20",
                         "installed_by": ["modules"]
                     },
+                    "diamond/cluster": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "fastme": {
                         "branch": "master",
                         "git_sha": "5f4e755fdc22c6e40d740ab27ea9b1004e806cb5",
                         "installed_by": ["modules"]
                     },
+                    "gawk": {
+                        "branch": "master",
+                        "git_sha": "97321eded31a12598837a476d3615300af413bb7",
+                        "installed_by": ["modules"]
+                    },
                     "iqtree": {
                         "branch": "master",
                         "git_sha": "ba03053ffa300ccdd044545131ba033b73f327fe",

modules/local/convert_phylip.nf

@@ -18,7 +18,7 @@ process CONVERT_PHYLIP {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     clustal2phylip.py $input_file ${prefix}.phy
 

modules/local/create_tcoffeetemplate.nf

@@ -17,8 +17,7 @@ process CREATE_TCOFFEETEMPLATE {
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: ''
-    prefix   = task.ext.prefix ?: "${meta.id}"
+    def prefix   = task.ext.prefix ?: "${meta.id}"
     """
     # Prep templates
     for structure in \$(ls *.pdb); do

modules/local/fetch_afdb_structures.nf

@@ -21,7 +21,7 @@ process FETCH_AFDB_STRUCTURES {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     fetch_afdb_structures.py $ids $prefix 2> ${prefix}_af_versions.txt
 

modules/local/fetch_eggnog_group_local.nf

@@ -23,7 +23,7 @@ process FETCH_EGGNOG_GROUP_LOCAL {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     # get the EggNOG ID from the ID map
     zcat $eggnog_idmap | grep \$(cat $uniprot_id) | cut -f2 | cut -d',' -f1 > eggnog_id.txt || test -f eggnog_id.txt

modules/local/fetch_inspector_group_online.nf

@@ -19,7 +19,7 @@ process FETCH_INSPECTOR_GROUP_ONLINE {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     # get the Uniprot ID
     uniprot_id=\$(cat $uniprot_id)

modules/local/fetch_oma_group_local.nf

@@ -22,7 +22,7 @@ process FETCH_OMA_GROUP_LOCAL {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     # Obtain the OMA ID for the given Uniprot ID of the query protein
     uniprot2oma_local.py $uniprot_idmap $uniprot_id > oma_id.txt || test -f oma_id.txt

modules/local/fetch_oma_group_online.nf

@@ -18,7 +18,7 @@ process FETCH_OMA_GROUP_ONLINE {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     # get uniprot ID
     uniprot_id=\$(cat ${uniprot_id})

modules/local/fetch_panther_group_local.nf

@@ -19,7 +19,7 @@ process FETCH_PANTHER_GROUP_LOCAL {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     id=\$(cat ${uniprot_id})
     touch ${prefix}_panther_group_raw.txt

modules/local/fetch_panther_group_online.nf

@@ -18,7 +18,7 @@ process FETCH_PANTHER_GROUP_ONLINE {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     # get Uniprot ID and TaxID
     uniprot_id=\$(cat $uniprot_id)

modules/local/filter_fasta.nf

@@ -18,7 +18,7 @@ process FILTER_FASTA {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     filter_fasta.py ${fasta} ${structures} ${prefix}_filtered.fa
 

modules/local/filter_hits.nf

@@ -21,7 +21,7 @@ process FILTER_HITS {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix     = task.ext.prefix ?: meta.id
+    def prefix     = task.ext.prefix ?: meta.id
     targetfile = use_centroid ? "${prefix}_centroid.txt" : "${prefix}_minscore_${min_score}.txt"
     """
     score_hits.py $score_table $prefix $queryid

modules/local/identify_seq_online.nf

@@ -18,7 +18,7 @@ process IDENTIFY_SEQ_ONLINE {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     fetch_oma_by_sequence.py $fasta id_raw.txt ${prefix}_taxid.txt ${prefix}_exact.txt
     uniprotize_oma_online.py id_raw.txt > ${prefix}_id.txt

modules/local/make_hits_table.nf

@@ -18,7 +18,7 @@ process MAKE_HITS_TABLE {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     make_hits_table.py $merged_csv ${meta.id} > ${prefix}_hits_table.csv
 

modules/local/make_report.nf

@@ -2,11 +2,6 @@ process MAKE_REPORT {
     tag "$meta.id"
     label 'process_single'
 
-    // Exit if running this module with -profile conda / -profile mamba
-    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
-        error("Local MAKE_REPORT module does not support Conda. Please use Docker / Singularity / Podman instead.")
-    }
-
     container "nf-core/reportho-orthologs-report:1.0.0"
 
     input:
@@ -20,7 +15,12 @@ process MAKE_REPORT {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error("Local MAKE_REPORT module does not support Conda. Please use Docker / Singularity / Podman instead.")
+    }
+
+    def prefix = task.ext.prefix ?: meta.id
     seqhits_cmd = seq_hits ? "cp $seq_hits public/seq_hits.txt" : ''
     seqmisses_cmd = seq_misses ? "cp $seq_misses public/seq_misses.txt" : ''
     strhits_cmd = str_hits ? "cp $str_hits public/str_hits.txt" : ''

modules/local/make_score_table.nf

@@ -18,7 +18,7 @@ process MAKE_SCORE_TABLE {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     make_score_table.py $merged_csv > ${prefix}_score_table.csv
 

modules/local/make_stats.nf

@@ -18,7 +18,7 @@ process MAKE_STATS {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     make_stats.py ${score_table} > ${prefix}_stats.yml
 

modules/local/plot_orthologs.nf

@@ -20,7 +20,7 @@ process PLOT_ORTHOLOGS {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     plot_orthologs.R $score_table $prefix
 

modules/local/split_id_format.nf

@@ -18,7 +18,7 @@ process SPLIT_ID_FORMAT {
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: meta.id
+    def prefix = task.ext.prefix ?: meta.id
     """
     cut -d ',' -f 1 $ids | tail -n +2 > tmp
     split_id_format.py tmp $prefix

modules/local/split_taxids.nf

@@ -0,0 +1,48 @@
+process SPLIT_TAXIDS {
+    tag "$input_file"
+    label 'process_single'
+
+    conda "conda-forge::python=3.12.0 conda-forge::biopython=1.84.0 conda-forge::requests=2.32.3"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-bc54124b36864a4af42a9db48b90a404b5869e7e:5258b8e5ba20587b7cbf3e942e973af5045a1e59-0' :
+        'community.wave.seqera.io/library/python_requests_biopython:3c0f15f68130f062' }"
+
+    input:
+    tuple val(meta), path(input_file)
+
+    output:
+    tuple val(meta), path("*.fa"), emit: fastas
+    path "versions.yml"          , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: meta.id
+    """
+    awk -v RS=">" 'NR > 1 {
+        split(\$1, header, "|")
+        id = header[2]
+        out_filename = "${prefix}_" id ".fa"
+        print ">" \$0 >> out_filename
+        close(out_filename)
+    }' $input_file
+
+
+    cat <<- END_VERSIONS > versions.yml
+    "${task.process}":
+        awk: \$(awk -Wversion | sed '1!d; s/.*Awk //; s/,.*//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_0.fa
+
+    cat <<- END_VERSIONS > versions.yml
+    "${task.process}":
+        awk: \$(awk -Wversion | sed '1!d; s/.*Awk //; s/,.*//')
+    END_VERSIONS
+    """
+}