updated traceback subworkflow and associated modules with changes for…

modules/msk/genotypevariants/all/main.nf

@@ -39,7 +39,6 @@ process GENOTYPEVARIANTS_ALL {
     $bams_standard \\
     $bam_liquid \\
     $sample \\
-    -t $task.cpus \\
     $args
 
     cat <<-END_VERSIONS > versions.yml

modules/msk/genotypevariants/all/meta.yml

@@ -1,5 +1,4 @@
----
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+## yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "genotypevariants_all"
 description: write your description here
 keywords:
@@ -11,67 +10,78 @@ tools:
       description: "module supports genotyping and merging small variants (SNV and INDELS)."
       documentation: "https://genotype-variants.readthedocs.io/en/latest/"
       licence: ["MIT"]
+      identifier: ""
 
 input:
   # Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', patient:'patient_1' ]`
-  - bam_standard:
-      type: file
-      description: Full path to standard bam file.
-      pattern: "*.{bam}"
-  - bai_standard:
-      type: file
-      description: Requires the standard .bai file is present at same location as the bam file.
-      pattern: "*.{bai}"
-  - bam_duplex:
-      type: file
-      description: Full path to duplex bam file.
-      pattern: "*.{bam}"
-  - bai_duplex:
-      type: file
-      description: Requires the duplex .bai file is present at same location as the bam file.
-      pattern: "*.{bai}"
-  - bam_simplex:
-      type: file
-      description: Full path to simplex bam file.
-      pattern: "*.{bam}"
-  - bai_simplex:
-      type: file
-      description: Requires the simplex .bai file is present at same location as the bam file.
-      pattern: "*.{bai}"
-  - maf:
-      type: file
-      description: Full path to small variants input file in MAF format
-      pattern: "*.{maf}"
-  - fasta:
-      type: file
-      description: The reference fasta file
-      pattern: "*.fasta"
-  - fai:
-      type: file
-      description: Index of reference fasta file
-      pattern: "*.fasta.fai"
-
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', patient:'patient_1' ]`
+    - bam_standard:
+        type: file
+        description: Full path to standard bam file.
+        pattern: "*.{bam}"
+    - bai_standard:
+        type: file
+        description:
+          Requires the standard .bai file is present at same location as
+          the bam file.
+        pattern: "*.{bai}"
+    - bam_duplex:
+        type: file
+        description: Full path to duplex bam file.
+        pattern: "*.{bam}"
+    - bai_duplex:
+        type: file
+        description:
+          Requires the duplex .bai file is present at same location as the
+          bam file.
+        pattern: "*.{bai}"
+    - bam_simplex:
+        type: file
+        description: Full path to simplex bam file.
+        pattern: "*.{bam}"
+    - bai_simplex:
+        type: file
+        description:
+          Requires the simplex .bai file is present at same location as the
+          bam file.
+        pattern: "*.{bai}"
+    - maf:
+        type: file
+        description: Full path to small variants input file in MAF format
+        pattern: "*.{maf}"
+  - - fasta:
+        type: file
+        description: The reference fasta file
+        pattern: "*.fasta"
+  - - fai:
+        type: file
+        description: Index of reference fasta file
+        pattern: "*.fasta.fai"
 output:
   #Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', patient:'patient_1' ]`
   - maf:
-      type: file
-      description: Genotyped maf for each bam provided and a merged genotyped maf. The mafs will be labelled with patient identifier or sample identifier as the prefix, and end with the type of bam (duplex, simplex, or standard). The sample identifier is prioritized.
-      pattern: "*.{mafs}"
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', patient:'patient_1' ]`
+      - "*.maf":
+          type: file
+          description:
+            Genotyped maf for each bam provided and a merged genotyped maf.
+            The mafs will be labelled with patient identifier or sample identifier as
+            the prefix, and end with the type of bam (duplex, simplex, or standard). The
+            sample identifier is prioritized.
+          pattern: "*.{mafs}"
   - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
-
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
 authors:
   - "@buehlere"
 maintainers:

modules/msk/pvmaf/concat/main.nf

@@ -4,8 +4,8 @@ process PVMAF_CONCAT {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'ghcr.io/msk-access/postprocessing_variant_calls:0.3.0':
-        'ghcr.io/msk-access/postprocessing_variant_calls:0.3.0' }"
+        'ghcr.io/msk-access/postprocessing_variant_calls:0.2.6':
+        'ghcr.io/msk-access/postprocessing_variant_calls:0.2.6' }"
 
     input:
     tuple val(meta), path(maf_files, stageAs: "*?-ORG-SIMPLEX-DUPLEX_genotyped.maf")// [ id:'sample1', patient:'patient1' ], [maf_1, ... maf_n]

modules/msk/pvmaf/concat/meta.yml

@@ -1,4 +1,3 @@
----
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "pvmaf_concat"
 description: a flexible command for concatenating maf files
@@ -12,36 +11,36 @@ tools:
       homepage: "https://github.com/msk-access/postprocessing_variant_calls"
       documentation: "https://cmo-ci.gitbook.io/postprocessing_variant_calls/"
       licence: ["MIT"]
+      identifier: ""
 
 input:
   # Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', patient:'patient1' ]`
-  - maf_files:
-      type: file
-      description: list of maf files to concatenate
-      pattern: "*.{maf}"
-
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', patient:'patient1' ]`
+    - maf_files:
+        type: file
+        description: list of maf files to concatenate
+        pattern: "*.{maf}"
 output:
   #Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', patient:'patient1' ]`
-
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
   - maf:
-      type: file
-      description: concatenated maf file
-      pattern: "*.{maf}"
-
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', patient:'patient1' ]`
+      - "*.maf":
+          type: file
+          description: concatenated maf file
+          pattern: "*.{maf}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
 authors:
   - "@buehlere"
 maintainers:

modules/msk/pvmaf/concat/tests/main.nf.test.snap

@@ -28,7 +28,11 @@
                 ]
             }
         ],
-        "timestamp": "2024-02-23T11:31:39.015292"
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-10-01T12:18:30.061693329"
     },
     "chr22maf - msk": {
         "content": [
@@ -39,7 +43,7 @@
                             "id": "chr22",
                             "patient": "test"
                         },
-                        "test_combined.maf:md5,7b36c0fda7ebb28b27ddf51b7d2a09e8"
+                        "test_combined.maf:md5,e1d7d2ecaf53ce75908ad49b25289f32"
                     ]
                 ],
                 "1": [
@@ -51,14 +55,18 @@
                             "id": "chr22",
                             "patient": "test"
                         },
-                        "test_combined.maf:md5,7b36c0fda7ebb28b27ddf51b7d2a09e8"
+                        "test_combined.maf:md5,e1d7d2ecaf53ce75908ad49b25289f32"
                     ]
                 ],
                 "versions": [
                     "versions.yml:md5,c61c16c135e1cc470c79e7a579c4c76c"
                 ]
             }
         ],
-        "timestamp": "2024-02-23T11:31:28.145005"
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-10-01T12:18:20.94747798"
     }
 }

modules/msk/pvmaf/tagtraceback/environment.yml

@@ -1,9 +1,7 @@
 ---
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
-name: "pvmaf_tagtraceback"
 channels:
   - conda-forge
   - bioconda
-  - defaults
 dependencies:
-  - "YOUR-TOOL-HERE"
+  - "YOUR-TOOL=HERE"

modules/msk/pvmaf/tagtraceback/main.nf

@@ -1,14 +1,15 @@
 process PVMAF_TAGTRACEBACK {
     tag "$meta.id"
     label 'process_single'
+
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'ghcr.io/msk-access/postprocessing_variant_calls:type_traceback_0.0.7':
-        'ghcr.io/msk-access/postprocessing_variant_calls:type_traceback_0.0.7' }"
+        'ghcr.io/msk-access/postprocessing_variant_calls:0.2.6':
+        'ghcr.io/msk-access/postprocessing_variant_calls:0.2.6' }"
 
     input:
-    tuple val(meta), path(maf) // [ id:'sample1', patient:'patient1' ], *.maf
-    path(sample_sheets) // [samplesheet_1, ..., samplesheet_n]
+    tuple val(meta), path(maf)
+    path(sample_sheets)
 
     output:
     tuple val(meta), path("*.maf"), emit: maf

modules/msk/pvmaf/tagtraceback/meta.yml

@@ -1,4 +1,3 @@
----
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "pvmaf_tagtraceback"
 description: a flexible command for tagging maf files
@@ -12,43 +11,39 @@ tools:
       homepage: "https://github.com/msk-access/postprocessing_variant_calls"
       documentation: "https://cmo-ci.gitbook.io/postprocessing_variant_calls/"
       licence: ["MIT"]
+      identifier: ""
 
 input:
   # Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', patient:'patient1' ]`
-
-  - maf:
-      type: file
-      description: Maf file with columns required for selected tagging type.
-      pattern: "*.{maf}"
-
-  - path(sample_sheets):
-      type: file
-      description: |
-        Samplesheet with `sample_id` and `type` columns.
-        Used to add fillout type information to provided maf.
-        See Nucleovar for more info: https://github.com/mskcc-omics-workflows/nucleovar/blob/main/README.md.
-
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', patient:'patient1' ]`
+    - maf:
+        type: file
+        description: Maf file with columns required for selected tagging type.
+        pattern: "*.{maf}"
+  - - sample_sheets:
+        type: list
+        description: array holding the two samplesheets mandatory for running nucleovar, (pipeline_input and aux_bams)
 output:
   #Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', patient:'patient1' ]`
-  - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
   - maf:
-      type: file
-      description: tagged traceback maf.
-      pattern: "*.{maf}"
-
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', patient:'patient1' ]`
+      - "*.maf":
+          type: file
+          description: tagged maf file.
+          pattern: "*.{maf}"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
 authors:
   - "@buehlere"
 maintainers:

subworkflows/msk/traceback/main.nf

@@ -27,12 +27,12 @@ workflow TRACEBACK {
     .map {it -> [it[0].subMap('patient')[0], *it[1..-1]] }
     .set{concat_maf}
 
+
     bams
     .map { it -> [it[0].subMap('patient')[0], it[0], *it[1..-1]] }
     .combine(concat_maf, by:0)
     .map { it[1..-1] }
     .set{bam_list_maf}
-
     // genotype each bam combined maf, per patient if provided
     GENOTYPEVARIANTS_ALL(bam_list_maf, reference, reference_fai)
     ch_versions = ch_versions.mix(GENOTYPEVARIANTS_ALL.out.versions.first())