Merge pull request #48 from mskcc-omics-workflows/feature/neoantigen_…

…parse_cnvs

Module phylowgs parser

.github/workflows/test.yml

@@ -286,6 +286,8 @@ jobs:
             tags: snppileup
           - profile: "conda"
             tags: mutect1
+          - profile: "conda"
+            tags: phylowgsparsecnvs
     env:
       NXF_ANSI_LOG: false
       SENTIEON_LICENSE_BASE64: ${{ secrets.SENTIEON_LICENSE_BASE64 }}

modules/msk/phylowgsparsecnvs/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "phylowgsparsecnvs"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "PHYLOWGS"

modules/msk/phylowgsparsecnvs/main.nf

@@ -0,0 +1,46 @@
+process PHYLOWGSPARSECNVS {
+    tag "$meta.id"
+    label 'process_low'
+
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://mskcc/phylowgs:v1.4-msk':
+        'docker.io/mskcc/phylowgs:v1.4-msk' }"
+
+    input:
+    tuple val(meta), path(facetsgenelevel)
+
+    output:
+    tuple val(meta), path("cnvs.txt"), emit: cnv
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    python2 \\
+        /usr/bin/parser/parse_cnvs.py \\
+        ${args} \\
+        ${facetsgenelevel}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        phylowgsparsecnvs: \$PHYLOWGS_TAG
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch cnvs.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        phylowgsparsecnvs: \$PHYLOWGS_TAG
+    END_VERSIONS
+    """
+}

modules/msk/phylowgsparsecnvs/meta.yml

@@ -0,0 +1,49 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "phylowgsparsecnvs"
+description: parse cnvs from FACETS for input to phylowgs
+keywords:
+  - phylowgs
+  - CNVs
+  - FACETs
+tools:
+  - "phylowgsparsecnvs":
+      description: "parser to convert FACETs output to phylowgs expected input"
+      homepage: "https://genomebiology.biomedcentral.com/articles/10.1186/s13059-015-0602-8"
+      tool_dev_url: "https://github.com/mskcc/phylowgs"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - facetsgenelevel:
+      type: file
+      description: single sample facets gene level output
+      pattern: "*.{txt}"
+
+## TODO nf-core: Add a description of all of the variables used as output
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  ## TODO nf-core: Delete / customise this example output
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@pintoa1-mskcc"
+maintainers:
+  - "@pintoa1-mskcc"

modules/msk/phylowgsparsecnvs/tests/main.nf.test

@@ -0,0 +1,37 @@
+nextflow_process {
+
+    name "Test Process PHYLOWGSPARSECNVS"
+    script "../main.nf"
+    process "PHYLOWGSPARSECNVS"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "modules_msk"
+    tag "phylowgsparsecnvs"
+
+    test("phylowgsparsecnvs - txt") {
+
+        when {
+            process {
+                """                
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.test_data_mskcc['neoantigen']['facets_gene_level_txt'], checkIfExists: true)
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+
+            )
+        }
+
+    }
+
+
+}

modules/msk/phylowgsparsecnvs/tests/main.nf.test.snap

@@ -0,0 +1,37 @@
+{
+    "phylowgsparsecnvs - txt": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "cnvs.txt:md5,a2073057a3fe3ffa83ae3c6a6f00d4ab"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,59b3e223572b67b72eb21c625003973d"
+                ],
+                "cnv": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "cnvs.txt:md5,a2073057a3fe3ffa83ae3c6a6f00d4ab"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,59b3e223572b67b72eb21c625003973d"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-03-06T14:35:27.270866"
+    }
+}

modules/msk/phylowgsparsecnvs/tests/nextflow.config

@@ -0,0 +1,10 @@
+params {
+    enable_conda = false
+}
+
+process {
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: 'PHYLOWGSPARSECNVS' {
+        ext.args = '-c 0 -f facets'
+    }
+}

modules/msk/phylowgsparsecnvs/tests/tags.yml

@@ -0,0 +1,2 @@
+phylowgsparsecnvs:
+  - "modules/msk/phylowgsparsecnvs/**"

tests/config/test_data.config

@@ -723,5 +723,8 @@ params {
                 dbsnp_138_b37_chr17_vcf_gz                     = "${params.test_data_base_msk}/hg37/genomic_reference/GRCH37/vcf/dbsnp_138.b37.chr17.vcf.gz"
                 dbsnp_138_b37_chr17_vcf_gz_tbi                 = "${params.test_data_base_msk}/hg37/genomic_reference/GRCH37/vcf/dbsnp_138.b37.chr17.vcf.gz.tbi"
             }
+            'neoantigen' {
+                facets_gene_level_txt                          = "${params.test_data_base_msk}/neoantigen/neoantigen/facets_gene_level.txt"
+            }
     }
 }