Decoupler

modules/nf-core/decoupler/decoupler/main.nf

@@ -1,21 +1,20 @@
 process DECOUPLER {
     tag "$meta.id"
     label 'process_medium'
-
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/dc/dc0ee6d6033b9f04c6377ad3b1cf5f924e3243626ab8d7be836d9d6617f8da4e/data' :
         'community.wave.seqera.io/library/decoupler-py_matplotlib_pandas_scanpy:369a5afe315b9b30' }"
 
     input:
     tuple val(meta), path(mat)
-    path(net)
-    path(gtf)
+    tuple val(meta2), path(net)
+    tuple val(meta3), path(annot)
 
     output:
     tuple val(meta), path("*estimate_decoupler.tsv"), emit: dc_estimate
     tuple val(meta), path("*pvals_decoupler.tsv"), emit: dc_pvals
-    tuple val(meta), path("*decoupler_plot.png"), emit: png
+    tuple val(meta), path("*estimate_decoupler_plot.png"), emit: png
     path("versions.yml"), emit: versions
 
     when:
@@ -26,9 +25,9 @@ process DECOUPLER {
 
     stub:
     """
-    touch ${task.ext.prefix}_estimate_decoupler.tsv
-    touch ${task.ext.prefix}_pvals_decoupler.tsv
-    touch ${task.ext.prefix}_decoupler_plot.png
+    touch deseq2_estimate_decoupler.tsv
+    touch deseq2_pvals_decoupler.tsv
+    touch deseq2_estimate_decoupler_plot.png
     touch versions.yml
     """
 }

modules/nf-core/decoupler/decoupler/meta.yml

@@ -41,21 +41,31 @@ input:
         pattern: "*.tsv"
         ontologies:
           - edam: http://edamontology.org/format_3475 # TSV
-  - net:
-      type: file
-      description: |
-        The prior knowledge network linking the features of the
-        expression matrix to a process/component (e.g. gene set,
-        transcription factor, kinase, etc.)
-      pattern: "*.tsv"
-      ontologies:
-        - edam: http://edamontology.org/format_3475 # TSV
-  - gtf:
-      type: file
-      description: |
-        Annotation file in GTF format
-      pattern: "*.gtf"
-      ontologies: []
+  - - meta2:
+        type: map
+        description: Groovy map
+    - net:
+        type: file
+        description: |
+          The prior knowledge network linking the features of the
+          expression matrix to a process/component (e.g. gene set,
+          transcription factor, kinase, etc.)
+        pattern: "*.tsv"
+        ontologies:
+          - edam: http://edamontology.org/format_3475 # TSV
+  - - meta3:
+        type: map
+        description: Groovy map
+    - annot:
+        type: file
+        description: |
+          Annotation file in TSV format containing gene ID to gene name mappings.
+          Used specifically for mapping Ensembl IDs to gene names.
+          Expected format: two columns with gene_id and gene_name headers.
+        pattern: "*.tsv"
+        required: false
+        ontologies:
+          - edam: http://edamontology.org/format_3475 # TSV
 output:
   dc_estimate:
     - - meta:
@@ -90,12 +100,12 @@ output:
           description: |
             Groovy Map containing sample information
             e.g. [ id:‘test’, single_end ]
-      - "*decoupler_plot.png":
+      - "*estimate_decoupler_plot.png":
           type: file
           description: |
             The file containing the plots associated to the estimation
             results of the enrichment(s)
-          pattern: "*decoupler_plot.png"
+          pattern: "*estimate_decoupler_plot.png"
           ontologies:
             - edam: http://edamontology.org/format_3475 # TSV
   versions:

modules/nf-core/decoupler/decoupler/templates/decoupler.py

@@ -41,52 +41,35 @@ def parse_ext_args(args_string: str):
     parser.add_argument("--column", type=str, default="log2FoldChange", help="Column name to use for transposition")
     parser.add_argument("--ensembl_ids", type=str, default="FALSE", help="Convert ENSEMBL IDs to gene symbols if TRUE")
     parser.add_argument("--methods", type=str, default = "ulm", help="Comma-separated list of methods to use (e.g., 'mlm,ulm')")
+    parser.add_argument("--features_id_col", type=str, default="gene_id", help="Column name for feature IDs")
+    parser.add_argument("--features_symbol_col", type=str, default="gene_name", help="Column name for feature symbols")
     return parser.parse_args(args_list)
 
-def parse_gtf(gtf_file: str):
-    """
-    Parse an optional GTF file to create a mapping of ENSEMBL gene IDs to gene symbols (required to use Progeny data).
-    """
-    mapping = {}
-    opener = gzip.open if gtf_file.endswith('.gz') else open
-    with opener(gtf_file, 'rt') as f:
-        for line in f:
-            if line.startswith("#"):
-                continue
-            fields = line.strip().split("\t")
-            if len(fields) < 9:
-                continue
-            attributes_field = fields[8]
-            attributes = {}
-            for attr in attributes_field.split(";"):
-                attr = attr.strip()
-                if not attr:
-                    continue
-                parts = attr.split(" ", 1)
-                if len(parts) != 2:
-                    continue
-                key, value = parts
-                attributes[key] = value.replace('"', '').strip()
-            gene_id = attributes.get("gene_id")
-            gene_symbol = attributes.get("gene_name") or attributes.get("gene_symbol") or attributes.get("external_gene_name")
-            if gene_id and gene_symbol:
-                mapping[gene_id] = gene_symbol
-    return mapping
-
 # Parse external arguments
 raw_args = "${task.ext.args}"
 parsed_args = parse_ext_args(raw_args)
 methods = [m.strip() for m in parsed_args.methods.split(",") if m.strip()]
 
 if parsed_args.ensembl_ids.upper() == "TRUE":
     try:
-        gene_mapping = parse_gtf("${gtf}")
+        if not os.path.exists("${annot}"):
+            raise FileNotFoundError(f"Annotation file not found: ${annot}")
+
+        annot_df = pd.read_csv("${annot}", sep="\t")
+
+        required_cols = {parsed_args.features_id_col, parsed_args.features_symbol_col}
+
+        missing = required_cols - set(annot_df.columns)
+        if missing:
+            raise ValueError(f"Missing required columns in annotation file: {missing}. Available columns: {list(annot_df.columns)}")
+
+        gene_mapping = dict(zip(annot_df[parsed_args.features_id_col], annot_df[parsed_args.features_symbol_col]))
         new_index = [gene_mapping.get(ens, None) for ens in mat.index]
         mat.index = new_index
         mat = mat[mat.index.notnull()]
         mat = mat[~mat.index.duplicated(keep='first')]
     except Exception as e:
-        print("ERROR: Failed to parse GTF:", e)
+        print(f"ERROR: Failed to process annotation file: {e}")
         sys.exit(1)
 
 if parsed_args.transpose.upper() == "TRUE":

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

@@ -14,7 +14,7 @@ nextflow_process {
 
         when {
             params {
-                module_args = "--min_n 2 --transpose TRUE --ensembl_ids TRUE --methods mlm"
+                module_args = "--min_n 2 --transpose TRUE --ensembl_ids TRUE --methods mlm --features_id_col gene_id --features_symbol_col gene_name"
             }
             process {
                 """
@@ -23,9 +23,12 @@ nextflow_process {
                     file("https://github.com/nf-core/test-datasets/raw/differentialabundance/modules_testdata/treatment_mCherry_hND6_.deseq2.results.tsv", checkIfExists: true)
                 ]
                 input[1] = [
+                    ['id':'network'],
                     file("https://github.com/nf-core/test-datasets/raw/differentialabundance/modules_testdata/progeny/mouse_network.tsv", checkIfExists: true)
                 ]
-                input[2] = [file("https://ftp.ensembl.org/pub/release-81/gtf/mus_musculus/Mus_musculus.GRCm38.81.gtf.gz", checkIfExists: true)]
+                input[2] = [
+                    ['id':'annot'],
+                    file("https://github.com/nf-core/test-datasets/raw/differentialabundance/modules_testdata/Mus_musculus.anno.feature_metadata.tsv", checkIfExists: true)]
                 """
             }
         }
@@ -63,7 +66,7 @@ nextflow_process {
 
         when {
             params {
-                module_args = "--min_n 1"
+                module_args = "--min_n 1 --features_id_col gene_id --features_symbol_col gene_name"
             }
 
             process {
@@ -73,9 +76,12 @@ nextflow_process {
                     file(params.test_data['generic']['tsv']['expression'], checkIfExists: true)
                 ]
                 input[1] = [
+                    ['id':'network'],
                     file(params.test_data['generic']['tsv']['network'], checkIfExists: true)
                 ]
-                input[2] = [file("https://ftp.ensembl.org/pub/release-81/gtf/mus_musculus/Mus_musculus.GRCm38.81.gtf.gz", checkIfExists: true)]
+                input[2] = [
+                    ['id':'annot'],
+                    file("https://github.com/nf-core/test-datasets/raw/differentialabundance/modules_testdata/Mus_musculus.anno.feature_metadata.tsv", checkIfExists: true)]
                 """
             }
         }
@@ -114,7 +120,7 @@ nextflow_process {
 
         when {
             params {
-                module_args = "--min_n 1"
+                module_args = "--min_n 1 --features_id_col gene_id --features_symbol_col gene_name"
             }
             process {
                 """
@@ -123,9 +129,12 @@ nextflow_process {
                     file(params.test_data['generic']['tsv']['expression'], checkIfExists: true)
                 ]
                 input[1] = [
+                    ['id':'network'],
                     file(params.test_data['generic']['tsv']['network'], checkIfExists: true)
                 ]
-                input[2] = [file("https://ftp.ensembl.org/pub/release-81/gtf/mus_musculus/Mus_musculus.GRCm38.81.gtf.gz", checkIfExists: true)]
+                input[2] = [
+                    ['id':'annot'],
+                    file("https://github.com/nf-core/test-datasets/raw/differentialabundance/modules_testdata/Mus_musculus.anno.feature_metadata.tsv", checkIfExists: true)]
                 """
             }
         }

modules/nf-core/decoupler/decoupler/tests/main.nf.test.snap

@@ -3,7 +3,7 @@
         "content": [
             "[deseq2_treatment_mCherry_hND6_consensus_estimate_decoupler.tsv, deseq2_treatment_mCherry_hND6_mlm_estimate_decoupler.tsv]",
             "[deseq2_treatment_mCherry_hND6_consensus_pvals_decoupler.tsv, deseq2_treatment_mCherry_hND6_mlm_pvals_decoupler.tsv]",
-            "[deseq2_treatment_mCherry_hND6_consensus_estimate_decoupler_plot.png, deseq2_treatment_mCherry_hND6_consensus_pvals_decoupler_plot.png, deseq2_treatment_mCherry_hND6_mlm_estimate_decoupler_plot.png, deseq2_treatment_mCherry_hND6_mlm_pvals_decoupler_plot.png]",
+            "[deseq2_treatment_mCherry_hND6_consensus_estimate_decoupler_plot.png, deseq2_treatment_mCherry_hND6_mlm_estimate_decoupler_plot.png]",
             2,
             2,
             [
@@ -26,7 +26,7 @@
             "nf-test": "0.9.2",
             "nextflow": "25.04.6"
         },
-        "timestamp": "2025-07-17T03:01:11.305706897"
+        "timestamp": "2025-08-12T18:24:03.118968335"
     },
     "decoupler stub": {
         "content": [
@@ -36,23 +36,23 @@
                         {
                             "id": "test"
                         },
-                        "null_test_estimate_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "deseq2_estimate_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "1": [
                     [
                         {
                             "id": "test"
                         },
-                        "null_test_pvals_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "deseq2_pvals_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "2": [
                     [
                         {
                             "id": "test"
                         },
-                        "null_test_decoupler_plot.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "deseq2_estimate_decoupler_plot.png:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "3": [
@@ -63,23 +63,23 @@
                         {
                             "id": "test"
                         },
-                        "null_test_estimate_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "deseq2_estimate_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "dc_pvals": [
                     [
                         {
                             "id": "test"
                         },
-                        "null_test_pvals_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "deseq2_pvals_decoupler.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "png": [
                     [
                         {
                             "id": "test"
                         },
-                        "null_test_decoupler_plot.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "deseq2_estimate_decoupler_plot.png:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "versions": [
@@ -91,13 +91,13 @@
             "nf-test": "0.9.2",
             "nextflow": "25.04.6"
         },
-        "timestamp": "2025-07-17T01:49:26.123404951"
+        "timestamp": "2025-08-25T18:51:20.453145611"
     },
     "decoupler_test": {
         "content": [
             "[deseq2_test_consensus_estimate_decoupler.tsv, deseq2_test_ulm_estimate_decoupler.tsv]",
             "[deseq2_test_consensus_pvals_decoupler.tsv, deseq2_test_ulm_pvals_decoupler.tsv]",
-            "[deseq2_test_consensus_estimate_decoupler_plot.png, deseq2_test_consensus_pvals_decoupler_plot.png, deseq2_test_ulm_estimate_decoupler_plot.png, deseq2_test_ulm_pvals_decoupler_plot.png]",
+            "[deseq2_test_consensus_estimate_decoupler_plot.png, deseq2_test_ulm_estimate_decoupler_plot.png]",
             2,
             2,
             [
@@ -120,6 +120,6 @@
             "nf-test": "0.9.2",
             "nextflow": "25.04.6"
         },
-        "timestamp": "2025-07-17T04:07:01.430446461"
+        "timestamp": "2025-08-12T18:27:18.094901759"
     }
 }