add custom/fingerprintcorrelation

Author: anoronh4

modules/msk/custom/fingerprintcombine/main.nf

@@ -10,15 +10,12 @@ process CUSTOM_FINGERPRINTCOMBINE {
 
 
     input:
-    tuple val(meta),
-        path(fp_tsv), // list of paths to fingerprint TSV files
-        val(sample), // list of sample identifiers, one per TSV file, in the same order
-        val(genome_build) // list of genome builds, one per TSV file, in the same order
+    tuple val(meta), path(fp_tsv), val(sample), val(genome_build)
     path(liftover_loci_mapping)
 
     output:
-    tuple val(meta), path("*DPfilter_ALL_FP.txt"), emit: combined_fp_tsv
-    path "versions.yml"                          , emit: versions
+    tuple val(meta), path("*DPfilter_ALL_FP.txt")                         , emit: combined_fp_tsv
+    tuple val("${task.process}"), val('complete_FP_table.R'), val('0.1.0'), emit: versions_fingerprintcombine, topic: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -44,11 +41,6 @@ process CUSTOM_FINGERPRINTCOMBINE {
         -i input.tsv \\
         -l $liftover_loci_mapping \\
         $args
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        complete_FP_table.R: 0.1.0
-    END_VERSIONS
     """
 
     stub:
@@ -58,10 +50,5 @@ process CUSTOM_FINGERPRINTCOMBINE {
     echo $args
 
     touch XDPfilter_ALL_FP.txt
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        complete_FP_table.R: 0.1.0
-    END_VERSIONS
     """
 }

modules/msk/custom/fingerprintcombine/meta.yml

@@ -1,55 +1,82 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
-# # TODO nf-core: Add a description of the module and list keywords
 name: "custom_fingerprintcombine"
 description: |
   A module to combine multiple fingerprint TSV files into a single comprehensive
   table, with optional liftover of loci coordinates.
 keywords:
-- fingerprint
-- qc
-- loci
-- tsv
-- correlation
+  - fingerprint
+  - qc
+  - loci
+  - tsv
+  - correlation
 tools:
-## TODO nf-core: Add a description and other details for the software below
-- "custom":
-    description: "A custom R script to combine fingerprint TSV files"
-    homepage: "https://github.com/mskcc-omics-workflows/modules/tree/main/modules/msk/custom/fingerprintcombine/meta.yml"
-
+  - "custom":
+      description: "A custom R script to combine fingerprint TSV files"
+      homepage: "https://github.com/mskcc-omics-workflows/modules/tree/main/modules/msk/custom/fingerprintcombine/meta.yml"
+      identifier: ""
 input:
-  - - fp_tsv:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test' ]
+    - fp_tsv:
         type: file
         description: |
           Fingerprint TSV files to be combined.
           Structure: [ val(sample), val(genome_build), path(fp_tsv) ]
+        ontologies: []
     - sample:
         type: string
         description: Sample identifier corresponding to each fingerprint TSV file.
     - genome_build:
         type: string
-        description: Genome build (e.g., hg19, hg38) corresponding to each fingerprint TSV file.
-  - liftover_loci_mapping:
-      type: file
-      description: |
-        A TSV file mapping original loci to liftover loci.
-        Format: original_chr, original_pos, liftover_chr, liftover_pos
-      pattern: "*.tsv"
-output:
-  combined_fp_tsv:
-    - "*DPfilter_ALL_FP.txt":
+        description:
+          Genome build (e.g., hg19, hg38) corresponding to each fingerprint
+          TSV file.
+  - - liftover_loci_mapping:
         type: file
-        description: Wide table combining all input fingerprint TSV files.
-        pattern: '*DPfilter_ALL_FP.txt'
+        description: |
+          A TSV file mapping original loci to liftover loci.
+          Format: original_chr, original_pos, liftover_chr, liftover_pos
+        pattern: "*.tsv"
         ontologies:
-          - edam: http://edamontology.org/format_3750  # TSV
+          - edam: http://edamontology.org/format_3475 # TSV
+output:
+  combined_fp_tsv:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*DPfilter_ALL_FP.txt":
+          type: file
+          description: Wide table combining all input fingerprint TSV files.
+          pattern: "*DPfilter_ALL_FP.txt"
+          ontologies:
+            - edam: http://edamontology.org/format_3750 # TSV
+  versions_fingerprintcombine:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - complete_FP_table.R:
+          type: string
+          description: The name of the tool
+      - 0.1.0:
+          type: string
+          description: Version of the custom script
+topics:
   versions:
-    - versions.yml:
-        type: file
-        description: File containing software versions
-        pattern: versions.yml
-        ontologies:
-          - edam: http://edamontology.org/format_3750  # YAML
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - complete_FP_table.R:
+          type: string
+          description: The name of the tool
+      - 0.1.0:
+          type: string
+          description: Version of the custom script
 authors:
-- "@anoronh4"
+  - "@anoronh4"
 maintainers:
-- "@anoronh4"
+  - "@anoronh4"

modules/msk/custom/fingerprintcombine/resources/usr/bin/complete_FP_table.R

@@ -49,7 +49,7 @@ hg19_hg38_mapper$Loci_hg38 = paste(hg19_hg38_mapper$GRCH38_CHROM,hg19_hg38_mappe
 hg19_hg38_mapper = hg19_hg38_mapper %>% select(Loci_hg19, Loci_hg38) %>% unique()
 
 message("Loading Samples")
-input_table = fread(args$input_table, header = T)
+input_table = fread(args$input_table, header = T) %>% arrange(sample_id)
 for (i in 1:nrow(input_table)){
   sample = input_table$sample_id[i]
   genome_build = input_table$genome_build[i]

modules/msk/custom/fingerprintcombine/tests/main.nf.test

@@ -56,7 +56,7 @@ nextflow_process {
                 """
                 input[0] = CUSTOM_FINGERPRINTVCFPARSER.out.tsv
                     .map{ meta, tsv ->
-                        def meta2 = [id:meta.pool]
+                        println meta
                         [[id:meta.pool], tsv, meta.id, "hg19"]
                     }.groupTuple(by:[0])
                 input[1] = file("$baseDir/modules/msk/custom/fingerprintcombine/tests/loci_mapping.tsv", checkIfExists:true)
@@ -82,6 +82,7 @@ nextflow_process {
             process {
                 """
                 input[0] = [
+                    [id:"testsample"],
                     [file(params.test_data['sarscov2']['illumina']['test_single_end_sorted_bam'], checkIfExists: true)],
                     ["testsample"],
                     ["hg19"]

modules/msk/custom/fingerprintcombine/tests/main.nf.test.snap

@@ -3,46 +3,82 @@
         "content": [
             {
                 "0": [
-                    "XDPfilter_ALL_FP.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    [
+                        {
+                            "id": "testsample"
+                        },
+                        "XDPfilter_ALL_FP.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "1": [
-                    "versions.yml:md5,3bd40a0fd11a907f31110dd113fd88c2"
+                    [
+                        "CUSTOM_FINGERPRINTCOMBINE",
+                        "complete_FP_table.R",
+                        "0.1.0"
+                    ]
                 ],
                 "combined_fp_tsv": [
-                    "XDPfilter_ALL_FP.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    [
+                        {
+                            "id": "testsample"
+                        },
+                        "XDPfilter_ALL_FP.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
-                "versions": [
-                    "versions.yml:md5,3bd40a0fd11a907f31110dd113fd88c2"
+                "versions_fingerprintvcfparser": [
+                    [
+                        "CUSTOM_FINGERPRINTCOMBINE",
+                        "complete_FP_table.R",
+                        "0.1.0"
+                    ]
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.9.2",
-            "nextflow": "25.04.6"
+            "nf-test": "0.9.3",
+            "nextflow": "25.10.2"
         },
-        "timestamp": "2025-09-25T22:47:09.499353594"
+        "timestamp": "2025-12-17T13:28:48.061258305"
     },
     "sarscov2 - bam": {
         "content": [
             {
                 "0": [
-                    "0DPfilter_ALL_FP.txt:md5,509d9f7c1d89b9f8e2825bcc4793da3a"
+                    [
+                        {
+                            "id": "mypool"
+                        },
+                        "0DPfilter_ALL_FP.txt:md5,66113c255cf1f52e27802183764a406d"
+                    ]
                 ],
                 "1": [
-                    "versions.yml:md5,3bd40a0fd11a907f31110dd113fd88c2"
+                    [
+                        "CUSTOM_FINGERPRINTCOMBINE",
+                        "complete_FP_table.R",
+                        "0.1.0"
+                    ]
                 ],
                 "combined_fp_tsv": [
-                    "0DPfilter_ALL_FP.txt:md5,509d9f7c1d89b9f8e2825bcc4793da3a"
+                    [
+                        {
+                            "id": "mypool"
+                        },
+                        "0DPfilter_ALL_FP.txt:md5,66113c255cf1f52e27802183764a406d"
+                    ]
                 ],
-                "versions": [
-                    "versions.yml:md5,3bd40a0fd11a907f31110dd113fd88c2"
+                "versions_fingerprintvcfparser": [
+                    [
+                        "CUSTOM_FINGERPRINTCOMBINE",
+                        "complete_FP_table.R",
+                        "0.1.0"
+                    ]
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.9.2",
-            "nextflow": "25.04.6"
+            "nf-test": "0.9.3",
+            "nextflow": "25.10.2"
         },
-        "timestamp": "2025-09-25T22:47:03.219089934"
+        "timestamp": "2025-12-17T13:28:39.908034467"
     }
 }

modules/msk/custom/fingerprintcontamination/main.nf

@@ -12,8 +12,8 @@ process CUSTOM_FINGERPRINTCONTAMINATION {
     tuple val(meta), path(fp_tumor), path(fp_normal)
 
     output:
-    tuple val(meta), path("*.contamination.tsv"), emit: contamination_tsv
-    path "versions.yml"                         , emit: versions
+    tuple val(meta), path("*.contamination.tsv")                                                                           , emit: contamination_tsv
+    tuple val("${task.process}"), val('calculate_contamination.py'), eval('calculate_contamination.py -v | cut -f 2 -d" "'), emit: versions_fingerprintvcfparser, topic: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -28,20 +28,12 @@ process CUSTOM_FINGERPRINTCONTAMINATION {
         -o ${prefix}.contamination.tsv \\
         ${args}
 
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        calculate_contamination.py: \$( calculate_contamination.py --version | rev | cut -f 1 -d " " | rev )
-    END_VERSIONS
     """
 
     stub:
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
     touch ${prefix}.contamination.tsv
 
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        calculate_contamination.py: \$( calculate_contamination.py --version | rev | cut -f 1 -d " " | rev )
-    END_VERSIONS
     """
 }

modules/msk/custom/fingerprintcontamination/meta.yml

@@ -11,11 +11,13 @@ tools:
       description: "Python Data Analysis Library"
       homepage: "https://pandas.pydata.org/"
       documentation: "https://pandas.pydata.org/docs/"
+      identifier: biotools:pandas
   - "numpy":
       description: "Scientific computing library for Python"
       homepage: "https://numpy.org/"
       documentation: "https://numpy.org/doc/"
 
+      identifier: biotools:numpy
 input:
   - - meta:
         type: map
@@ -27,17 +29,19 @@ input:
         description: Fingerprint table file for tumor sample
         pattern: "*.fp.tsv"
         ontologies:
-          - edam: "http://edamontology.org/format_3750"     # TSV
+          - edam: "http://edamontology.org/format_3750" # TSV
+          - edam: http://edamontology.org/format_3475 # TSV
     - fp_normal:
         type: file
         description: Fingerprint table file for normal sample
         pattern: "*.fp.tsv"
         ontologies:
           - edam: "http://edamontology.org/format_3750"
 
+          - edam: http://edamontology.org/format_3475 # TSV
 output:
-  - contamination_tsv:
-      - meta:
+  contamination_tsv:
+    - - meta:
           type: map
           description: |
             Groovy Map containing sample information
@@ -48,12 +52,11 @@ output:
           pattern: "*.contamination.tsv"
           ontologies:
             - edam: "http://edamontology.org/format_3750" # TSV
-  - versions:
-      - versions.yml:
-          type: file
-          description: File containing software versions
-          pattern: "versions.yml"
-
+            - edam: http://edamontology.org/format_3475 # TSV
+  versions_fingerprintvcfparser:
+    - - ${task.process}: {}
+      - calculate_contamination.py: {}
+      - 'calculate_contamination.py -v | cut -f 2 -d" ': {}
 authors:
   - "@anoronh4"
 maintainers: