DE_config_defaults.yaml

#---------------------------------------- general pipeline parameters
pipeline_param:
  # adjust pattern of stored files
  out_path_pattern: DE/{contrast}/{step}/out/{step}.{contrast}.{extension}
  log_path_pattern: DE/{contrast}/{step}/report/{step}.{contrast}.{extension}
  in_path_pattern: mapping/{step}/{sample}.{mate}/out/{step}.{sample}.{mate}.{extension}
  
  # base dir of report snippet library ("" for the default in git repo)
  report_snippets: ""

  # define choices for choose_input()
  input_choice:
    mapping:
      - import_gene_counts
      - import_sf

  test_config: true

#---------------------------------------- organism annotation (needs to be set)
organism_defaults: null

#---------------------------------------- information about experiment
experiment:
  covariate_file:
    salmon: covariate_file.txt
    star: covariate_file.txt
  design_formula: "~ group"
  #columns: null
      
#---------------------------------------- filtering of count matrices
filters:
  low_counts: 10
  experiment_blacklist: {} # {<Column>: [<Level1>,...]} for columns of covariate file
  experiment_whitelist: {}

  # these two parameters allow a more fine grained filtering:
  # setting them means that only genes will be kept which have at least
  # `min_counts` in at least `min_count_n` samples

  min_counts: 5
  min_count_n: 3

  # filtering gene lists

  gene_list:
    file: null
    type: ENSEMBL

#---------------------------------------- normalization parameters
normalization:
  DESeq2_parameters:
    min_mu: 0
  normalized_expression: vst

#---------------------------------------- description of contrasts
contrasts:
  defaults:
    max_p_adj: 0.1
    ranking_by: log2FoldChange
    ranking_order: "-abs(x)"
    results_parameters:
      lfcThreshold: 0
      altHypothesis: greaterAbs
      independentFiltering: yes
    lfcShrink_parameters:
      type: none
    ORA:
      fdr_threshold: 0.1
    cluster_profiler:
      MSigDb:
        categories: [H, C2]
        type: gsea
      GO:
        ontologies: [BP, MF]
        type: ora
        pval: 0.1
      KEGG:
        type: ora
        kegg_organism_code: hsa

  
  #contrast_list: null

#---------------------------------------- description of time series

time_series: {}

rain:
  period: 24
  peak_boarder: "c(0.3, 0.7)"
  filter:
    min_fold_change: 1.5
    frac_above_threshold:
      threshold: 5
      frac: 0.8

dodr:
  period: 24
  method: all
  comparisons: {}

#  comparisons:
#    cortex_ts_vs_scn_ts:
#      description: "cortex vs. SCN"
#      time_series1:
#        name: circ_ts
#        path: null
#      time_series2:
#        name: circ_ts
#        path: DE_scn/{contrast}/{step}/out/{step}.{contrast}.{extension}

#---------------------------------------- report parameters
report:
  #merge: null
  #
  path: "snippets"

  snippet_parameters:
    Normalisation_QC:
      n_most_varying: 500
      annotation_columns: [ "group" ]
    contrast:
      filter_results:
        qval: 0.1
      filter_goseq:
        qval: 0.1
    rain:
      filter_results:
        qval: 0.2
      plot:
        show_num: 6
    dodr:
      filter_results:
        qval: 0.2
    tmod:
      fig_qval_max: 0.01
      fig_auc_min:  0.55
      fig_n_max: 35
      fig_n_min: 10
      n_evid: 5
    tmod_contrast:
      res_auc_thr: 0.65
      res_pval_thr: 0.01
    Export_files:
      dir: "export_files"

  defaults:
    NormalisationQC:
      - PCA_plot.Rmd
      - HierarchicalClustering_plot.Rmd
      - SampleSimilarity_plot.Rmd
      - NormExprDens_plot.Rmd
      - DESeq2Norm_plot.Rmd
      - CoxOutlier_plot.Rmd
    contrast:
      - __list__: __contrasts__
    contrast_list:
      - Init_code.Rmd
      - MA_plot.Rmd
      - Result_table.Rmd
      - Goseq_GO_table.Rmd
      - tmod_contrast.Rmd
      - cluster_profiler: __defaults__
    cluster_profiler:
      - Dot_plot.Rmd
      - EnrichmentMap_plot.Rmd
      - Upset_plot.Rmd
    time_series:
      - __list__: __timeseries__
    time_series_list:
      - Rain_table.Rmd
    time_series_comparison:
      - __list__: __timeseries_comp__
    time_series_comparison_list:
      - DODR_table.Rmd

  report_snippets:
    - Covariate_table.Rmd
    - NormalisationQC: __defaults__
    - contrast: __defaults__
    #- time_series: __defaults__
    #- time_series_comparison: __defaults__
    #- Export_files.Rmd  ## export files for clients to export_files directory
#
  

#---------------------------------------- configuration for export
export:
  blueprint:
    file: SODAR_export_DE_blueprint.txt
    command: |
      imkdir -p $(dirname {dest} )
      irsync -a -K {src} i:{dest}
  path_pattern:
    - __SODAR__/{contrast}/{GENOME}/%Y_%m_%d/{files:differential_expression}/out/{step}.{contrast}.{extension}
    - __SODAR__/{contrast}/{GENOME}/%Y_%m_%d/{files:functional_analysis:rds}/{step}/out/{step}.{contrast}.{extension}
    - __SODAR__/{contrast}/{GENOME}/%Y_%m_%d/{files:functional_analysis:csv}/{step}/out/{step}.{contrast}.zip
  differential_expression:
    - files: {step: contrast, extension: rds}
  functional_analysis_rds:
    - files: {step: goseq, extension: go.rds}
    - files: {step: goseq, extension: kegg.rds}
    - files: {step: cluster_profiler, extension: rds}
  functional_analysis_csv:
    - files: {step: cluster_profiler, extension: csv}
      compress: zip