Update diff subworkflows (#7414)

* [gsea] unable default seed option * [subworkflow] update abundance_differential_filter to output a list of files for variance stabilised matrices. This is to facilitate the channel handling afterwards in the differentialabundance pipeline * [gsea] add module test config * update functional subworkflow. Also update gprofiler2 related snapshots - as they changed after database update * [gprofiler2] add option to specify the database archive * [gsea] remove default seed set in gsea module * change(abundance_differential_filter): use groupTuple for ch_variance_stabilised_matrix * change(differential and functional subworkflows): add back mergeMap and update snapshots * fix(snapshot): update gprofiler2/gost test snapshots * fix(gprofiler2_gost): set base url to an old archive for reproducibility. * fix(gprofiler2_gost): update test snapshots to match with the latest database * simplify ch_variance_stabilised_matrix with groupTuple() Co-authored-by: Jonathan Manning <[email protected]> * update propd container * update differential and functional subworkflows by replacing 'method' by 'method_differential' and 'method_functional' * fix: update version snapshots for the new propd container --------- Co-authored-by: Jonathan Manning <[email protected]>
nf-core · Feb 13, 2025 · 785efc6 · 785efc6
1 parent 5bca12d
commit 785efc6
Show file tree

Hide file tree

Showing 23 changed files with 311 additions and 302 deletions.
diff --git a/modules/nf-core/gprofiler2/gost/templates/gprofiler2_gost.R b/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)
@@ -235,7 +236,9 @@ 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")
+        base_url <- paste0("https://biit.cs.ut.ee/", opt\$archive)
+        gmt_url <- paste0(base_url, "//static/gprofiler_full_", opt\$organism, ".ENSG.gmt")
+        set_base_url(base_url)
         tryCatch(
             {
                 gmt_path <- paste0("gprofiler_full_", opt\$organism, ".ENSG.gmt")

diff --git a/modules/nf-core/gprofiler2/gost/tests/main.nf.test.snap b/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:md5,31d1e4cfa1d09b30bf9126415cb93aff"
                 ]
             ],
             [
@@ -23,15 +23,15 @@
                         "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.GO:BP.sub_enriched_pathways.tsv:md5,6211f4fa1a226f3aaab77c3fb9318fe7",
+                        "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.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.MIRNA.sub_enriched_pathways.tsv:md5,9168f1d7f7d1b1db18a4652db05b81b6",
+                        "Condition_genotype_WT_KO.gprofiler2.REAC.sub_enriched_pathways.tsv:md5,3571ac765c47e1c38c63c463465f2a1e",
+                        "Condition_genotype_WT_KO.gprofiler2.TF.sub_enriched_pathways.tsv:md5,4d23e5fdc96395ea79d174b1afe84756",
+                        "Condition_genotype_WT_KO.gprofiler2.WP.sub_enriched_pathways.tsv:md5,e99c42df912a9ee75c7197f92d615979"
                     ]
                 ]
             ],
@@ -65,9 +65,9 @@
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.3"
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2025-01-21T11:29:54.746689985"
+        "timestamp": "2025-02-07T15:34:05.718473191"
     },
     "stub": {
         "content": [

diff --git a/modules/nf-core/gprofiler2/gost/tests/nextflow.config b/modules/nf-core/gprofiler2/gost/tests/nextflow.config
@@ -1,3 +1,3 @@
 process {
     ext.args = params.module_args
-}
+}
diff --git a/modules/nf-core/gsea/gsea/main.nf b/modules/nf-core/gsea/gsea/main.nf
@@ -45,7 +45,6 @@ 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"}
 
     """
     # Run GSEA

diff --git a/modules/nf-core/gsea/gsea/tests/main.nf.test b/modules/nf-core/gsea/gsea/tests/main.nf.test
@@ -12,6 +12,8 @@ nextflow_process {
 
     test("test") {
 
+        config "./nextflow.config"
+
         when {
             process {
                 """

diff --git a/modules/nf-core/gsea/gsea/tests/nextflow.config b/modules/nf-core/gsea/gsea/tests/nextflow.config
@@ -0,0 +1,5 @@
+process {
+    withName: 'GSEA_GSEA' {
+        ext.args = { "-rnd_seed 10" }
+    }
+}
diff --git a/modules/nf-core/propr/propd/environment.yml b/modules/nf-core/propr/propd/environment.yml
@@ -6,4 +6,4 @@ channels:
 
 dependencies:
   - bioconda::bioconductor-limma=3.58.1
-  - conda-forge::r-propr=5.1.5
+  - conda-forge::r-propr=5.1.6
diff --git a/modules/nf-core/propr/propd/main.nf b/modules/nf-core/propr/propd/main.nf
@@ -4,8 +4,8 @@ process PROPR_PROPD {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/b6/b65f7192866fbd9a947df15b104808abb720e7a224bbe3ca8f7f8f680f52c97a/data' :
-        'community.wave.seqera.io/library/bioconductor-limma_r-propr:f52f1d4fea746393' }"
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/27/276e08c149faa028a34ec65f74ac9eac58c2036a30db1f72acc9e35967936620/data' :
+        'community.wave.seqera.io/library/bioconductor-limma_r-propr:8d299a2da993327c' }"
 
     input:
     tuple val(meta), val(contrast_variable), val(reference), val(target)

diff --git a/modules/nf-core/propr/propd/tests/main.nf.test.snap b/modules/nf-core/propr/propd/tests/main.nf.test.snap
@@ -14,15 +14,15 @@
                 ]
             ],
             [
-                "versions.yml:md5,1d96e70c16cc53a1d7b2e1a54fd8b7e8"
+                "versions.yml:md5,f356eb5d430713b086255dfc32b5d6ee"
             ],
             "treatment_mCherry_hND6_.propd.genewise.png"
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.1"
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-11-27T10:11:40.654796611"
+        "timestamp": "2025-02-13T11:28:17.523375516"
     },
     "Test propr/propd when using Box-cox transformation": {
         "content": [
@@ -39,15 +39,15 @@
                 ]
             ],
             [
-                "versions.yml:md5,1d96e70c16cc53a1d7b2e1a54fd8b7e8"
+                "versions.yml:md5,f356eb5d430713b086255dfc32b5d6ee"
             ],
             "treatment_mCherry_hND6_.propd.genewise.png"
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.1"
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-11-27T10:12:22.252395938"
+        "timestamp": "2025-02-13T11:29:03.711287557"
     },
     "Test propr/propd when using permutation tests": {
         "content": [
@@ -76,15 +76,15 @@
                 ]
             ],
             [
-                "versions.yml:md5,1d96e70c16cc53a1d7b2e1a54fd8b7e8"
+                "versions.yml:md5,f356eb5d430713b086255dfc32b5d6ee"
             ],
             "treatment_mCherry_hND6_.propd.genewise.png"
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.1"
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-11-27T10:13:03.55054778"
+        "timestamp": "2025-02-13T11:29:38.37807294"
     },
     "Test propr/propd when saving all outputs": {
         "content": [
@@ -126,15 +126,15 @@
             ],
             null,
             [
-                "versions.yml:md5,1d96e70c16cc53a1d7b2e1a54fd8b7e8"
+                "versions.yml:md5,f356eb5d430713b086255dfc32b5d6ee"
             ],
             "treatment_mCherry_hND6_.propd.genewise.png",
             "treatment_mCherry_hND6_.propd.rds"
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.1"
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-11-27T10:12:01.936451896"
+        "timestamp": "2025-02-13T11:28:45.957361627"
     }
 }
diff --git a/subworkflows/nf-core/abundance_differential_filter/main.nf b/subworkflows/nf-core/abundance_differential_filter/main.nf
@@ -31,8 +31,8 @@ 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_input_new = meta_input + [ 'method': analysis_method ]
+        def meta_for_diff = mergeMaps(meta_contrasts, meta_input) + [ 'method_differential': analysis_method ]
+        def meta_input_new = meta_input + [ 'method_differential': analysis_method ]
         samples_and_matrix:
             [ meta_input_new, samplesheet, abundance ]
         contrasts_for_diff:
@@ -71,13 +71,13 @@ workflow ABUNDANCE_DIFFERENTIAL_FILTER {
     // LIMMA_NORM directly. It internally runs normalization + DE analysis.
 
     LIMMA_NORM(
-        norm_inputs.contrasts_for_norm.filter{it[0].method == 'limma'},
-        norm_inputs.samples_and_matrix.filter{it[0].method == 'limma'}
+        norm_inputs.contrasts_for_norm.filter{it[0].method_differential == 'limma'},
+        norm_inputs.samples_and_matrix.filter{it[0].method_differential == 'limma'}
     )
 
     LIMMA_DIFFERENTIAL(
-        inputs.contrasts_for_diff.filter{ it[0].method == 'limma' },
-        inputs.samples_and_matrix.filter{ it[0].method == 'limma' }
+        inputs.contrasts_for_diff.filter{ it[0].method_differential == 'limma' },
+        inputs.samples_and_matrix.filter{ it[0].method_differential == 'limma' }
     )
 
     // ----------------------------------------------------
@@ -92,15 +92,15 @@ workflow ABUNDANCE_DIFFERENTIAL_FILTER {
     // DESEQ2_NORM directly. It internally runs normalization + DE analysis.
 
     DESEQ2_NORM(
-        norm_inputs.contrasts_for_norm.filter{it[0].method == 'deseq2'},
-        norm_inputs.samples_and_matrix.filter{it[0].method == 'deseq2'},
+        norm_inputs.contrasts_for_norm.filter{it[0].method_differential == 'deseq2'},
+        norm_inputs.samples_and_matrix.filter{it[0].method_differential == 'deseq2'},
         ch_control_features.first(),
         ch_transcript_lengths.first()
     )
 
     DESEQ2_DIFFERENTIAL(
-        inputs.contrasts_for_diff.filter{it[0].method == 'deseq2'},
-        inputs.samples_and_matrix.filter{it[0].method == 'deseq2'},
+        inputs.contrasts_for_diff.filter{it[0].method_differential == 'deseq2'},
+        inputs.samples_and_matrix.filter{it[0].method_differential == 'deseq2'},
         ch_control_features.first(),
         ch_transcript_lengths.first()
     )
@@ -113,8 +113,8 @@ workflow ABUNDANCE_DIFFERENTIAL_FILTER {
     // not produce a normalized matrix.
 
     PROPR_PROPD(
-        inputs.contrasts_for_diff.filter{it[0].method == 'propd'},
-        inputs.samples_and_matrix.filter { it[0].method == 'propd' }
+        inputs.contrasts_for_diff.filter{it[0].method_differential == 'propd'},
+        inputs.samples_and_matrix.filter { it[0].method_differential == 'propd' }
     )
 
     // ----------------------------------------------------
@@ -131,6 +131,11 @@ 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([[],[]])
+        .mix(DESEQ2_NORM.out.vst_counts.ifEmpty([[],[]]))
+        .groupTuple()
+        .filter{ meta, files -> meta != [] }
+
     ch_versions = DESEQ2_DIFFERENTIAL.out.versions
         .mix(LIMMA_DIFFERENTIAL.out.versions)
         .mix(PROPR_PROPD.out.versions)
@@ -158,14 +163,14 @@ workflow ABUNDANCE_DIFFERENTIAL_FILTER {
             ]
             filter_input: [meta + filter_meta, results]
             fc_input: [
-                method_params[meta.method].fc_column,
+                method_params[meta.method_differential].fc_column,
                 filter_meta.fc_threshold,
-                method_params[meta.method].fc_cardinality
+                method_params[meta.method_differential].fc_cardinality
             ]
             stat_input: [
-                method_params[meta.method].stat_column,
+                method_params[meta.method_differential].stat_column,
                 filter_meta.stat_threshold,
-                method_params[meta.method].stat_cardinality
+                method_params[meta.method_differential].stat_cardinality
             ]
         }
 
@@ -186,7 +191,7 @@ 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
 }
diff --git a/subworkflows/nf-core/abundance_differential_filter/meta.yml b/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:

diff --git a/subworkflows/nf-core/abundance_differential_filter/tests/deseq2_basic.config b/subworkflows/nf-core/abundance_differential_filter/tests/deseq2_basic.config
@@ -5,10 +5,10 @@ process {
             "--vs_method rlog",
             (meta.blocking == null) ? "" : "--blocking_variables $meta.blocking"
         ].join(' ').trim() }
-        ext.prefix = { "${meta.id}_${meta.method}" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}" }
     }
 
     withName: 'DESEQ2_NORM' {
-        ext.prefix = { "${meta.id}_${meta.method}_norm" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_norm" }
     }
 }
diff --git a/subworkflows/nf-core/abundance_differential_filter/tests/deseq2_limmavoom_basic.config b/subworkflows/nf-core/abundance_differential_filter/tests/deseq2_limmavoom_basic.config
@@ -5,11 +5,11 @@ process {
             "--vs_method rlog",
             (meta.blocking == null) ? "" : "--blocking_variables $meta.blocking"
         ].join(' ').trim() }
-        ext.prefix = { "${meta.id}_${meta.method}" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}" }
     }
 
     withName: 'DESEQ2_NORM' {
-        ext.prefix = { "${meta.id}_${meta.method}_norm" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_norm" }
     }
 
     withName: 'LIMMA_DIFFERENTIAL' {
@@ -19,10 +19,10 @@ process {
             "--probe_id_col gene_id",
             "--use_voom TRUE"
         ].join(' ').trim() }
-        ext.prefix = { "${meta.id}_${meta.method}_voom" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_voom" }
     }
 
     withName: 'LIMMA_NORM' {
-        ext.prefix = { "${meta.id}_${meta.method}_voom_norm" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_voom_norm" }
     }
 }
diff --git a/subworkflows/nf-core/abundance_differential_filter/tests/deseq2_limmavoom_propd_basic.config b/subworkflows/nf-core/abundance_differential_filter/tests/deseq2_limmavoom_propd_basic.config
@@ -5,11 +5,11 @@ process {
             "--vs_method rlog",
             (meta.blocking == null) ? "" : "--blocking_variables $meta.blocking"
         ].join(' ').trim() }
-        ext.prefix = { "${meta.id}_${meta.method}" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}" }
     }
 
     withName: 'DESEQ2_NORM' {
-        ext.prefix = { "${meta.id}_${meta.method}_norm" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_norm" }
     }
 
     withName: 'LIMMA_DIFFERENTIAL' {
@@ -19,15 +19,15 @@ process {
             "--probe_id_col gene_id",
             "--use_voom TRUE"
         ].join(' ').trim() }
-        ext.prefix = { "${meta.id}_${meta.method}_voom" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_voom" }
     }
 
     withName: 'LIMMA_NORM' {
-        ext.prefix = { "${meta.id}_${meta.method}_voom_norm" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_voom_norm" }
     }
 
     withName: 'PROPR_PROPD' {
         ext.args = {"--round_digits 5 --save_adjacency true"}
-        ext.prefix = { "${meta.id}_${meta.method}" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}" }
     }
 }
diff --git a/subworkflows/nf-core/abundance_differential_filter/tests/limma_basic_microarray.config b/subworkflows/nf-core/abundance_differential_filter/tests/limma_basic_microarray.config
@@ -5,11 +5,11 @@ process {
             "--sample_id_col name",
             "--blocking_variables $meta.blocking"
         ].join(' ').trim() }
-        ext.prefix = { "${meta.id}_${meta.method}" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}" }
     }
 
     withName: 'LIMMA_NORM' {
-        ext.prefix = { "${meta.id}_${meta.method}_norm" }
+        ext.prefix = { "${meta.id}_${meta.method_differential}_norm" }
     }
 
     withName: 'AFFY_JUSTRMA' {
-Original file line number
+Diff line change
@@ Expand Up / @@ -12,6 +12,8 @@ nextflow_process { @@
         test("test") {
+            config "./nextflow.config"
             when {
                 process {
                     """
@@ Expand Down @@