Update diff subworkflows

modules/nf-core/gprofiler2/gost/templates/gprofiler2_gost.R

@@ -139,7 +139,8 @@ opt <- list(
     domain_scope = 'annotated',
     min_diff = 1,
     round_digits = -1,
-    palette_name = 'Blues'
+    palette_name = 'Blues',
+    archive = 'gprofiler'
 )
 
 opt_types <- lapply(opt, class)
@@ -182,6 +183,8 @@ for (file_input in c('de_file')) {
     }
 }
 
+print(opt)
+
 ################################################
 ################################################
 ## Finish loading libraries                   ##
@@ -235,7 +238,7 @@ if (nrow(de.genes) > 0) {
     } else if (!is.null(opt\$organism)) {
 
         # Next, check if organism was provided. Get the GMT file from gprofiler and save both the full file as well as the filtered one to metadata
-        gmt_url <- paste0("https://biit.cs.ut.ee/gprofiler//static/gprofiler_full_", opt\$organism, ".ENSG.gmt")
+        gmt_url <- paste0("https://biit.cs.ut.ee/", opt\$archive, "//static/gprofiler_full_", opt\$organism, ".ENSG.gmt")
         tryCatch(
             {
                 gmt_path <- paste0("gprofiler_full_", opt\$organism, ".ENSG.gmt")

modules/nf-core/gprofiler2/gost/tests/main.nf.test

@@ -46,7 +46,8 @@ nextflow_process {
                     ((params.gprofiler2_token == null) ? '' : "--token \"${params.gprofiler2_token}\""),
                     ((params.gprofiler2_organism == null) ? '' : "--organism \"${params.gprofiler2_organism}\""),
                     ((params.gprofiler2_background_column == null) ? '' : "--background_column \"${params.gprofiler2_background_column}\""),
-                    ((params.gprofiler2_sources == null) ? '' : "--sources \"${params.gprofiler2_sources}\"")
+                    ((params.gprofiler2_sources == null) ? '' : "--sources \"${params.gprofiler2_sources}\""),
+                    "--archive gprofiler_archive3/e111_eg58_p18"
                 ].join(' ').trim()
             }
             process {

modules/nf-core/gprofiler2/gost/tests/main.nf.test.snap

@@ -10,7 +10,7 @@
                         "target": "KO",
                         "blocking": "batch"
                     },
-                    "Condition_genotype_WT_KO.gprofiler2.all_enriched_pathways.tsv:md5,1134a02ca061c463bcbff277eefbfb19"
+                    "Condition_genotype_WT_KO.gprofiler2.all_enriched_pathways.tsv:md5,396712577c32213078d1604b1ba247de"
                 ]
             ],
             [
@@ -23,15 +23,14 @@
                         "blocking": "batch"
                     },
                     [
-                        "Condition_genotype_WT_KO.gprofiler2.GO:BP.sub_enriched_pathways.tsv:md5,d527b94cdb160070bcaa0bfb0cecf914",
-                        "Condition_genotype_WT_KO.gprofiler2.GO:CC.sub_enriched_pathways.tsv:md5,ef418c3f06d50446317928e37ec8ddfb",
-                        "Condition_genotype_WT_KO.gprofiler2.GO:MF.sub_enriched_pathways.tsv:md5,e460d4917feb0b64d334a528f59e0731",
-                        "Condition_genotype_WT_KO.gprofiler2.HP.sub_enriched_pathways.tsv:md5,865d8f092503552831c51d775a98c6eb",
-                        "Condition_genotype_WT_KO.gprofiler2.KEGG.sub_enriched_pathways.tsv:md5,413724002abe683f376ea914d4f21ade",
-                        "Condition_genotype_WT_KO.gprofiler2.MIRNA.sub_enriched_pathways.tsv:md5,fce81051d7af955ddb2925ba2da9ff57",
-                        "Condition_genotype_WT_KO.gprofiler2.REAC.sub_enriched_pathways.tsv:md5,e89e1876698ea644671a0720c85f4dbb",
-                        "Condition_genotype_WT_KO.gprofiler2.TF.sub_enriched_pathways.tsv:md5,e272217ec7fcf01ea463ab8bcc8335cf",
-                        "Condition_genotype_WT_KO.gprofiler2.WP.sub_enriched_pathways.tsv:md5,fdd1efa836d85bb127e933e925290cba"
+                        "Condition_genotype_WT_KO.gprofiler2.GO:BP.sub_enriched_pathways.tsv:md5,d6bebdcb2401a7f7de0ec42ad2f4521d",
+                        "Condition_genotype_WT_KO.gprofiler2.GO:CC.sub_enriched_pathways.tsv:md5,98a49b69f8b724d88d6367dea494ca53",
+                        "Condition_genotype_WT_KO.gprofiler2.GO:MF.sub_enriched_pathways.tsv:md5,39ce8238319df47708df78b1c461a89d",
+                        "Condition_genotype_WT_KO.gprofiler2.HP.sub_enriched_pathways.tsv:md5,616f3a5d19844001bb8aac38049e987a",
+                        "Condition_genotype_WT_KO.gprofiler2.MIRNA.sub_enriched_pathways.tsv:md5,486ed1510dc8bba867686b021d6e6339",
+                        "Condition_genotype_WT_KO.gprofiler2.REAC.sub_enriched_pathways.tsv:md5,3571ac765c47e1c38c63c463465f2a1e",
+                        "Condition_genotype_WT_KO.gprofiler2.TF.sub_enriched_pathways.tsv:md5,032491e63bb381cc9a4d7740473efc5b",
+                        "Condition_genotype_WT_KO.gprofiler2.WP.sub_enriched_pathways.tsv:md5,e99c42df912a9ee75c7197f92d615979"
                     ]
                 ]
             ],
@@ -41,14 +40,13 @@
                 "Condition_genotype_WT_KO.gprofiler2.GO:CC.sub_enriched_pathways.png",
                 "Condition_genotype_WT_KO.gprofiler2.GO:MF.sub_enriched_pathways.png",
                 "Condition_genotype_WT_KO.gprofiler2.HP.sub_enriched_pathways.png",
-                "Condition_genotype_WT_KO.gprofiler2.KEGG.sub_enriched_pathways.png",
                 "Condition_genotype_WT_KO.gprofiler2.MIRNA.sub_enriched_pathways.png",
                 "Condition_genotype_WT_KO.gprofiler2.REAC.sub_enriched_pathways.png",
                 "Condition_genotype_WT_KO.gprofiler2.TF.sub_enriched_pathways.png",
                 "Condition_genotype_WT_KO.gprofiler2.WP.sub_enriched_pathways.png"
             ],
             [
-                
+
             ],
             [
                 "R_sessionInfo.log"
@@ -65,9 +63,9 @@
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.3"
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2025-01-21T11:29:54.746689985"
+        "timestamp": "2025-01-31T15:16:54.617930264"
     },
     "stub": {
         "content": [
@@ -278,4 +276,4 @@
         },
         "timestamp": "2025-01-21T11:31:33.394855046"
     }
-}
+}

modules/nf-core/gprofiler2/gost/tests/nextflow.config

@@ -1,3 +1,3 @@
 process {
     ext.args = params.module_args
-}
+}

modules/nf-core/gsea/gsea/main.nf

@@ -45,7 +45,7 @@ process GSEA_GSEA {
     def rpt_label = prefix.replaceAll('\\.$', '') // Remove any trailing dots from prefix when passed as report label, so GSEA doesn't produce double-dotted top-level outputs
     def chip_command = chip ? "-chip $chip -collapse true" : ''
     def VERSION = '4.3.2' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
-    if (!(args ==~ /.*-rnd_seed.*/)) {args += " -rnd_seed 10"}
+    // if (!(args ==~ /.*-rnd_seed.*/)) {args += " -rnd_seed 10"} // unable this for the moment, until a global seed option is set for differentialabundance pipeline
 
     """
     # Run GSEA

modules/nf-core/gsea/gsea/tests/main.nf.test

@@ -12,6 +12,8 @@ nextflow_process {
 
     test("test") {
 
+        config "./nextflow.config"
+
         when {
             process {
                 """

modules/nf-core/gsea/gsea/tests/nextflow.config

@@ -0,0 +1,5 @@
+process {
+    withName: 'GSEA_GSEA' {
+        ext.args = { "-rnd_seed 10" }
+    }
+}

subworkflows/nf-core/abundance_differential_filter/main.nf

@@ -9,12 +9,6 @@ include { DESEQ2_DIFFERENTIAL as DESEQ2_NORM  } from '../../../modules/nf-core/d
 include { PROPR_PROPD                         } from '../../../modules/nf-core/propr/propd/main'
 include { CUSTOM_FILTERDIFFERENTIALTABLE      } from '../../../modules/nf-core/custom/filterdifferentialtable/main'
 
-// Combine meta maps, including merging non-identical values of shared keys (e.g. 'id')
-def mergeMaps(meta, meta2){
-    (meta + meta2).collectEntries { k, v ->
-        meta[k] && meta[k] != v ? [k, "${meta[k]}_${v}"] : [k, v]
-    }
-}
 
 workflow ABUNDANCE_DIFFERENTIAL_FILTER {
     take:
@@ -31,7 +25,7 @@ workflow ABUNDANCE_DIFFERENTIAL_FILTER {
 
     // Set up how the channels crossed below will be used to generate channels for processing
     def criteria = multiMapCriteria { meta_input, abundance, analysis_method, fc_threshold, stat_threshold, meta_exp, samplesheet, meta_contrasts, variable, reference, target ->
-        def meta_for_diff = mergeMaps(meta_contrasts, meta_input) + [ 'method': analysis_method ]
+        def meta_for_diff = meta_input + meta_contrasts + [ 'method': analysis_method ]
         def meta_input_new = meta_input + [ 'method': analysis_method ]
         samples_and_matrix:
             [ meta_input_new, samplesheet, abundance ]
@@ -131,6 +125,18 @@ workflow ABUNDANCE_DIFFERENTIAL_FILTER {
     ch_model = DESEQ2_DIFFERENTIAL.out.model
         .mix(LIMMA_DIFFERENTIAL.out.model)
 
+    ch_variance_stabilised_matrix = DESEQ2_NORM.out.rlog_counts.ifEmpty([[],[]])
+        .combine(DESEQ2_NORM.out.vst_counts.ifEmpty([[],[]]))
+        .map { meta_rlog, rlog, meta_vst, vst ->
+            if (meta_rlog == meta_vst && meta_rlog != []) {
+                return [meta_rlog, [rlog, vst]]
+            } else if (meta_rlog != [] && meta_vst == []) {
+                return [meta_rlog, [rlog]]
+            } else if (meta_rlog == [] && meta_vst != []) {
+                return [meta_vst, [vst]]
+            }
+        }
+
     ch_versions = DESEQ2_DIFFERENTIAL.out.versions
         .mix(LIMMA_DIFFERENTIAL.out.versions)
         .mix(PROPR_PROPD.out.versions)
@@ -186,7 +192,7 @@ workflow ABUNDANCE_DIFFERENTIAL_FILTER {
 
     // other
     normalised_matrix          = ch_normalised_matrix
-    variance_stabilised_matrix = DESEQ2_NORM.out.rlog_counts.mix(DESEQ2_NORM.out.vst_counts)
+    variance_stabilised_matrix = ch_variance_stabilised_matrix
     model                      = ch_model
     versions                   = ch_versions
 }

subworkflows/nf-core/abundance_differential_filter/meta.yml

@@ -116,10 +116,11 @@ output:
         - meta:
             type: map
             description: Metadata map
-        - matrix:
-            type: file
-            description: Variance stabilised count matrix file
+        - matrices:
+            type: list
+            description: A list of variance stabilised count matrix files
             pattern: "*.{csv,tsv}"
+
   - model:
       description: Channel containing statistical model object from differential analysis
       structure: