fix(custom/orfmerge): deterministic orf_id ordering and prefix-based output naming

Sort clusters by genomic coordinate (chrom, start, end, strand, gene_id,
transcript_id, orf_class) before assigning orf_ids so numbering no longer
follows the nondeterministic .collect() order. Move the catalogue
descriptor out of the hard path() outputs into the default prefix
(${meta.id}.catalogue).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: pinin4fjords

modules/nf-core/custom/orfmerge/main.nf

@@ -11,27 +11,27 @@ process CUSTOM_ORFMERGE {
     tuple val(meta), path(bed12s, arity: '1..*', stageAs: 'beds/*'), path(tsvs, arity: '1..*', stageAs: 'tsvs/*')
 
     output:
-    tuple val(meta), path("${prefix}.catalogue.bed12")    , emit: bed12
-    tuple val(meta), path("${prefix}.catalogue.tsv")      , emit: catalogue_tsv
-    tuple val(meta), path("${prefix}.orf_to_gene.tsv")    , emit: orf_to_gene_tsv
-    tuple val(meta), path("${prefix}.catalogue.mqc.tsv")  , emit: multiqc
-    path "versions.yml"                                   , emit: versions, topic: versions
+    tuple val(meta), path("${prefix}.bed12")           , emit: bed12
+    tuple val(meta), path("${prefix}.tsv")             , emit: catalogue_tsv
+    tuple val(meta), path("${prefix}.orf_to_gene.tsv") , emit: orf_to_gene_tsv
+    tuple val(meta), path("${prefix}.mqc.tsv")         , emit: multiqc
+    path "versions.yml"                                , emit: versions, topic: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    prefix = task.ext.prefix ?: "${meta.id}"
+    prefix = task.ext.prefix ?: "${meta.id}.catalogue"
     args   = task.ext.args ?: ''
     template 'orfmerge.py'
 
     stub:
-    prefix = task.ext.prefix ?: "${meta.id}"
+    prefix = task.ext.prefix ?: "${meta.id}.catalogue"
     """
-    touch ${prefix}.catalogue.bed12
-    touch ${prefix}.catalogue.tsv
+    touch ${prefix}.bed12
+    touch ${prefix}.tsv
     touch ${prefix}.orf_to_gene.tsv
-    touch ${prefix}.catalogue.mqc.tsv
+    touch ${prefix}.mqc.tsv
 
     python -c "import platform, yaml; yaml.safe_dump({'${task.process}': {'python': platform.python_version()}}, open('versions.yml', 'w'), default_flow_style=False, sort_keys=False)"
     """

modules/nf-core/custom/orfmerge/meta.yml

@@ -88,25 +88,25 @@ output:
           type: map
           description: |
             Groovy Map matching the input meta.
-      - ${prefix}.catalogue.bed12:
+      - ${prefix}.bed12:
           type: file
           description: Merged ORF catalogue as BED12 (genomic blocks).
-          pattern: "*.catalogue.bed12"
+          pattern: "*.bed12"
           ontologies:
             - edam: http://edamontology.org/format_3586 # BED
   catalogue_tsv:
     - - meta:
           type: map
           description: |
             Groovy Map matching the input meta.
-      - ${prefix}.catalogue.tsv:
+      - ${prefix}.tsv:
           type: file
           description: |
             Per-ORF table with `called_by_<caller>` and `score_<caller>`
             columns for each supported caller, `n_samples` / `samples`
             cross-sample recurrence columns, plus orf_class, aa_length,
             and host gene_id / transcript_id.
-          pattern: "*.catalogue.tsv"
+          pattern: "*.tsv"
           ontologies:
             - edam: http://edamontology.org/format_3475 # TSV
   orf_to_gene_tsv:
@@ -129,11 +129,11 @@ output:
           type: map
           description: |
             Groovy Map matching the input meta.
-      - ${prefix}.catalogue.mqc.tsv:
+      - ${prefix}.mqc.tsv:
           type: file
           description: |
             MultiQC custom-content TSV (per-class ORF counts).
-          pattern: "*.catalogue.mqc.tsv"
+          pattern: "*.mqc.tsv"
           ontologies:
             - edam: http://edamontology.org/format_3475 # TSV
   versions:

modules/nf-core/custom/orfmerge/templates/orfmerge.py

@@ -26,11 +26,11 @@
 
 Outputs:
 
-  ${prefix}.catalogue.bed12      merged catalogue (genomic blocks).
-  ${prefix}.catalogue.tsv        per-ORF table with caller-tracking cols.
+  ${prefix}.bed12                merged catalogue (genomic blocks).
+  ${prefix}.tsv                  per-ORF table with caller-tracking cols.
   ${prefix}.orf_to_gene.tsv      one row per (orf_id, gene_id, transcript_id);
                                  an ORF can map to multiple host transcripts.
-  ${prefix}.catalogue.mqc.tsv    MultiQC custom-content sidecar
+  ${prefix}.mqc.tsv              MultiQC custom-content sidecar
                                  (per-class counts).
 """
 
@@ -183,10 +183,10 @@ def load_normalised(tsv_paths, bed_paths):
 
 
 def write_catalogue(prefix, clusters, bed_index):
-    cat_bed = Path(f"{prefix}.catalogue.bed12")
-    cat_tsv = Path(f"{prefix}.catalogue.tsv")
+    cat_bed = Path(f"{prefix}.bed12")
+    cat_tsv = Path(f"{prefix}.tsv")
     o2g_tsv = Path(f"{prefix}.orf_to_gene.tsv")
-    mqc_tsv = Path(f"{prefix}.catalogue.mqc.tsv")
+    mqc_tsv = Path(f"{prefix}.mqc.tsv")
 
     catalogue_cols = (
         ["orf_id", "chrom", "start", "end", "strand", "gene_id", "transcript_id", "orf_class", "aa_length"]
@@ -197,6 +197,22 @@ def write_catalogue(prefix, clusters, bed_index):
 
     per_class_counts = defaultdict(int)
 
+    # orf_ids are assigned in iteration order below, so sort first to make the
+    # numbering deterministic.
+    def _sort_key(cluster):
+        r = representative(cluster)
+        return (
+            r.get("chrom", ""),
+            int(r.get("start") or 0),
+            int(r.get("end") or 0),
+            r.get("strand", ""),
+            r.get("gene_id") or "",
+            r.get("transcript_id") or "",
+            r.get("orf_class", ""),
+        )
+
+    clusters = sorted(clusters, key=_sort_key)
+
     with open(cat_bed, "w") as bh, open(cat_tsv, "w") as th, open(o2g_tsv, "w") as oh:
         th.write("\\t".join(catalogue_cols) + "\\n")
         oh.write("orf_id\\tgene_id\\ttranscript_id\\n")

modules/nf-core/custom/orfmerge/tests/main.nf.test

@@ -18,7 +18,7 @@ nextflow_process {
                 """
                 input[0] = channel.of([
                     [id: 'sample1', caller: 'ribotish'],
-                    file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
                     'ribotish'
                 ])
                 input[1] = channel.of([
@@ -35,7 +35,7 @@ nextflow_process {
                 """
                 input[0] = channel.of([
                     [id: 'sample1', caller: 'ribocode'],
-                    file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribocode.txt', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribocode.txt', checkIfExists: true),
                     'ribocode'
                 ])
                 input[1] = channel.of([
@@ -52,7 +52,7 @@ nextflow_process {
                 """
                 input[0] = channel.of([
                     [id: 'sample2', caller: 'ribotish'],
-                    file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
                     'ribotish'
                 ])
                 input[1] = channel.of([

modules/nf-core/custom/orfmerge/tests/main.nf.test.snap

@@ -7,23 +7,23 @@
                         {
                             "id": "cohort"
                         },
-                        "cohort.catalogue.bed12:md5,d0de23019fbec9d96fd9302103a16278"
+                        "cohort.catalogue.bed12:md5,59b9b0c4ceb890b58b8bcde4fecb2ac7"
                     ]
                 ],
                 "1": [
                     [
                         {
                             "id": "cohort"
                         },
-                        "cohort.catalogue.tsv:md5,d2695c6f6eab75fd03a20d7441533d36"
+                        "cohort.catalogue.tsv:md5,d6af31aac0548c8ce0f447be02d06397"
                     ]
                 ],
                 "2": [
                     [
                         {
                             "id": "cohort"
                         },
-                        "cohort.orf_to_gene.tsv:md5,79699c0188eadd2aaf912a31a2c14464"
+                        "cohort.catalogue.orf_to_gene.tsv:md5,eebb86a1c52a7418ee9dc68c53bd9866"
                     ]
                 ],
                 "3": [
@@ -42,15 +42,15 @@
                         {
                             "id": "cohort"
                         },
-                        "cohort.catalogue.bed12:md5,d0de23019fbec9d96fd9302103a16278"
+                        "cohort.catalogue.bed12:md5,59b9b0c4ceb890b58b8bcde4fecb2ac7"
                     ]
                 ],
                 "catalogue_tsv": [
                     [
                         {
                             "id": "cohort"
                         },
-                        "cohort.catalogue.tsv:md5,d2695c6f6eab75fd03a20d7441533d36"
+                        "cohort.catalogue.tsv:md5,d6af31aac0548c8ce0f447be02d06397"
                     ]
                 ],
                 "multiqc": [
@@ -66,18 +66,18 @@
                         {
                             "id": "cohort"
                         },
-                        "cohort.orf_to_gene.tsv:md5,79699c0188eadd2aaf912a31a2c14464"
+                        "cohort.catalogue.orf_to_gene.tsv:md5,eebb86a1c52a7418ee9dc68c53bd9866"
                     ]
                 ],
                 "versions": [
                     "versions.yml:md5,8e0b24bd9e91050a8715f1b1b61f0805"
                 ]
             }
         ],
-        "timestamp": "2026-06-12T13:28:01.081036",
+        "timestamp": "2026-06-16T11:49:30.349632545",
         "meta": {
             "nf-test": "0.9.5",
-            "nextflow": "25.10.4"
+            "nextflow": "26.04.1"
         }
     }
 }