Module:snppileup

.github/workflows/test.yml

@@ -282,6 +282,8 @@ jobs:
             tags: gbcms
           - profile: "conda"
             tags: polysolver
+          - profile: "conda"
+            tags: snppileup
     env:
       NXF_ANSI_LOG: false
       SENTIEON_LICENSE_BASE64: ${{ secrets.SENTIEON_LICENSE_BASE64 }}

modules/msk/snppileup/environment.yml

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

modules/msk/snppileup/main.nf

@@ -0,0 +1,57 @@
+process SNPPILEUP {
+    tag "$meta.id"
+    label 'process_medium'
+
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://mskcc/facets-suite:2.0.9':
+        'docker.io/mskcc/facets-suite:2.0.9' }"
+
+    input:
+
+    tuple val(meta),  path(normal), path(normal_index), path(tumor),  path(tumor_index)
+    tuple val(meta1), path(dbsnp),  path(dbsnp_index)
+
+
+    output:
+    tuple val(meta), path("*.snp_pileup.gz")   , emit: pileup
+    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}"
+
+    """
+    /usr/bin/snp-pileup \
+        ${args} \
+        ${dbsnp} \
+        ${prefix}.snp_pileup.gz \
+        ${normal} \
+        ${tumor}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        htslib: \$(bgzip --version | grep -oP '(?<=\\(htslib\\) ).*')
+        htstools: 0.1.1
+        r: \$(R --version | grep -oP '(?<=R version ).*(?=\\()')
+    END_VERSIONS
+    """
+
+    stub:
+    def args =   task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    echo "stub test" >> ${prefix}.snp_pileup
+    gzip ${prefix}.snp_pileup
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        htslib: \$(bgzip --version | grep -oP '(?<=\\(htslib\\) ).*')
+        htstools: 0.1.1
+        r: \$(R --version | grep -oP '(?<=R version ).*(?=\\()')
+    END_VERSIONS
+    """
+}

modules/msk/snppileup/meta.yml

@@ -0,0 +1,65 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "snppileup"
+description: Calculate snp pileups from a bam pair
+keywords:
+  - snp
+  - pileup
+  - bams
+  - dbsnp
+tools:
+  - "htstools":
+      description: "Contains tools to process bam files for downstream copy number analysis."
+      homepage: "https://github.com/mskcc/htstools"
+      documentation: "https://github.com/mskcc/htstools"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'pair_id' ]`
+  - meta1:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'pair_id' ]`
+  - normal:
+      type: file
+      description: "Normal bam file"
+      pattern: "*.bam"
+  - normal_index:
+      type: file
+      description: "Index of the normal bam file"
+      pattern: "*.bai"
+  - tumor:
+      type: file
+      description: "Tumor bam file"
+      pattern: "*.bam"
+  - tumor_index:
+      type: file
+      description: "Index of tumor bam file"
+      pattern: "*.bai"
+  - dbsnp:
+      type: file
+      description: The NCBI provided database vcf file on genetic variation
+      pattern: "*.vcf.gz"
+  - dbsnp_index:
+      type: file
+      description: The index of the dbsnp vcf file
+      pattern: "*.vcf.gz.tbi"
+
+output:
+  - pileup:
+      type: file
+      description: The pileup file
+      pattern: "*.snp_pileup.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@nikhil"
+maintainers:
+  - "@nikhil"

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

@@ -0,0 +1,77 @@
+nextflow_process {
+
+    name "Test SNPPILEUP"
+    script "../main.nf"
+    process "SNPPILEUP"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "modules_msk"
+    tag "snppileup"
+
+    test("snppileup - bam") {
+
+        when {
+            process {
+                """
+                    meta = [ id:'test' ] // meta map
+                    input[0] = [
+                                    meta,
+                                    file(params.test_data_mskcc['bam_files']['test_argos_sample_1_normal_bam'], checkIfExists: true),
+                                    file(params.test_data_mskcc['bam_files']['test_argos_sample_1_normal_bam_bai'], checkIfExists: true),
+                                    file(params.test_data_mskcc['bam_files']['test_argos_sample_1_tumor_bam'], checkIfExists: true),
+                                    file(params.test_data_mskcc['bam_files']['test_argos_sample_1_tumor_bam_bai'], checkIfExists: true)
+                                ]
+                    input[1] = [
+                                    meta,
+                                    file(params.test_data_mskcc['hg37']['dbsnp_138_b37_chr17_vcf_gz'], checkIfExists: true),
+                                    file(params.test_data_mskcc['hg37']['dbsnp_138_b37_chr17_vcf_gz_tbi'], checkIfExists: true)
+                               ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("snppileup - bam - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                    meta = [ id:'test' ] // meta map
+                    input[0] = [
+                                    meta,
+                                    file("stub_file"),
+                                    file("stub_file1"),
+                                    file("stub_file2"),
+                                    file("stub_file3")
+                                ]
+                    input[1] = [
+                                    meta,
+                                    file("stub_file4"),
+                                    file("stub_file5")
+                               ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

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

@@ -0,0 +1,60 @@
+{
+    "snppileup - bam - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.snp_pileup.gz:md5,3d77e3e110a219d3495d44e243450313"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,0ca251848ee099aebdade397bedf463f"
+                ],
+                "pileup": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.snp_pileup.gz:md5,3d77e3e110a219d3495d44e243450313"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0ca251848ee099aebdade397bedf463f"
+                ]
+            }
+        ],
+        "timestamp": "2024-01-29T15:06:34.676228"
+    },
+    "snppileup - bam": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.snp_pileup.gz:md5,deac57ec8a27969028af701840d2b0ee"
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,0ca251848ee099aebdade397bedf463f"
+                ],
+                "pileup": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.snp_pileup.gz:md5,deac57ec8a27969028af701840d2b0ee"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0ca251848ee099aebdade397bedf463f"
+                ]
+            }
+        ],
+        "timestamp": "2024-01-29T15:06:28.546836"
+    }
+}

modules/msk/snppileup/tests/nextflow.config

@@ -0,0 +1,10 @@
+params {
+    enable_conda = false
+}
+
+process {
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    withName: 'SNPPILEUP' {
+        ext.args = '--count-orphans --gzip --pseudo-snps 50 -r 25,0'
+    }
+}

modules/msk/snppileup/tests/tags.yml

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

tests/config/test_data.config

@@ -3,7 +3,8 @@
 
 params {
     // Base directory for test data
-    test_data_base = "https://raw.githubusercontent.com/nf-core/test-datasets/modules"
+    test_data_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules'
+    test_data_base_msk = 'https://github.com/mskcc-omics-workflows/test-datasets/raw'
 
     test_data {
         'sarscov2' {
@@ -293,7 +294,6 @@ params {
                 vep_cache                                      = "${params.test_data_base}/data/genomics/homo_sapiens/genome/vep.tar.gz"
                 affy_array_samplesheet                         = "${params.test_data_base}/data/genomics/homo_sapiens/array_expression/GSE38751.csv"
                 affy_array_celfiles_tar                        = "${params.test_data_base}/data/genomics/homo_sapiens/array_expression/GSE38751_RAW.tar"
-
             }
             'pangenome' {
                 pangenome_fa                                   = "${params.test_data_base}/data/pangenomics/homo_sapiens/pangenome.fa"
@@ -520,8 +520,8 @@ params {
                 gmx                             = "${params.test_data_base}/data/genomics/homo_sapiens/gene_set_analysis/c1.symbols.reduced.gmx"
             }
             'cnvkit' {
-                amplicon_cnr                    = "https://raw.githubusercontent.com/etal/cnvkit/v0.9.9/test/formats/amplicon.cnr"
-                amplicon_cns                    = "https://raw.githubusercontent.com/etal/cnvkit/v0.9.9/test/formats/amplicon.cns"
+                amplicon_cnr                    = 'https://raw.githubusercontent.com/etal/cnvkit/v0.9.9/test/formats/amplicon.cnr'
+                amplicon_cns                    = 'https://raw.githubusercontent.com/etal/cnvkit/v0.9.9/test/formats/amplicon.cns'
             }
         }
         'bacteroides_fragilis' {
@@ -530,7 +530,6 @@ params {
                 genome_gbff_gz                  = "${params.test_data_base}/data/genomics/prokaryotes/bacteroides_fragilis/genome/genome.gbff.gz"
                 genome_paf                      = "${params.test_data_base}/data/genomics/prokaryotes/bacteroides_fragilis/genome/genome.paf"
                 genome_gff_gz                   = "${params.test_data_base}/data/genomics/prokaryotes/bacteroides_fragilis/genome/genome.gff.gz"
-
             }
             'hamronization' {
                 genome_abricate_tsv             = "${params.test_data_base}/data/genomics/prokaryotes/bacteroides_fragilis/hamronization/genome.abricate.tsv"
@@ -599,7 +598,7 @@ params {
             'txt' {
                 hello                           = "${params.test_data_base}/data/generic/txt/hello.txt"
             }
-            'cooler'{
+            'cooler' {
                 test_pairix_pair_gz             = "${params.test_data_base}/data/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz"
                 test_pairix_pair_gz_px2         = "${params.test_data_base}/data/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz.px2"
                 test_pairs_pair                 = "${params.test_data_base}/data/genomics/homo_sapiens/cooler/cload/hg19/hg19.sample1.pairs"
@@ -608,7 +607,6 @@ params {
                 hg19_chrom_sizes                = "${params.test_data_base}/data/genomics/homo_sapiens/cooler/cload/hg19/hg19.chrom.sizes"
                 test_merge_cool                 = "${params.test_data_base}/data/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cool"
                 test_merge_cool_cp2             = "${params.test_data_base}/data/genomics/homo_sapiens/cooler/merge/toy/toy.symm.upper.2.cp2.cool"
-
             }
             'pairtools' {
                 mock_4dedup_pairsam             = "${params.test_data_base}/data/genomics/homo_sapiens/pairtools/mock.4dedup.pairsam"
@@ -626,7 +624,7 @@ params {
                     genome_file                 = "${params.test_data_base}/data/generic/unsorted_data/unsorted_text/test.genome"
                     intervals                   = "${params.test_data_base}/data/generic/unsorted_data/unsorted_text/test.bed"
                     numbers_csv                 = "${params.test_data_base}/data/generic/unsorted_data/unsorted_text/test.csv"
-                    }
+                }
             }
         }
         'proteomics' {
@@ -641,7 +639,6 @@ params {
                 mq_contrasts                    = "${params.test_data_base}/data/proteomics/maxquant/MaxQuant_contrasts.csv"
                 mq_proteingroups                = "${params.test_data_base}/data/proteomics/maxquant/MaxQuant_proteinGroups.txt"
                 mq_samplesheet                  = "${params.test_data_base}/data/proteomics/maxquant/MaxQuant_samplesheet.tsv"
-
             }
             'parameter' {
                 maxquant                        = "${params.test_data_base}/data/proteomics/parameter/mqpar.xml"
@@ -672,10 +669,10 @@ params {
                 plant_wga_multicut              = "${params.test_data_base}/data/imaging/ilp/plant_wga.multicut.ilp"
                 plant_wga_pixel_class           = "${params.test_data_base}/data/imaging/ilp/plant_wga.pixel_prob.ilp"
             }
-           'tiff' {
+            'tiff' {
                 mouse_heart_wga                 = "${params.test_data_base}/data/imaging/tiff/mindagap.mouse_heart.wga.tiff"
             }
-           'ome-tiff' {
+            'ome-tiff' {
                 cycif_tonsil_channels   = "${params.test_data_base}/data/imaging/ome-tiff/cycif-tonsil-channels.csv"
                 cycif_tonsil_cycle1     = "${params.test_data_base}/data/imaging/ome-tiff/cycif-tonsil-cycle1.ome.tif"
                 cycif_tonsil_cycle2     = "${params.test_data_base}/data/imaging/ome-tiff/cycif-tonsil-cycle2.ome.tif"
@@ -710,4 +707,17 @@ params {
             }
         }
     }
+
+    'test_data_mskcc' {
+            'bam_files' {
+                test_argos_sample_1_normal_bam                 = "${params.test_data_base_msk}/bam_files/bams/argos_processed/sample_1_normal.chr17.rg.md.abra.printreads.bam"
+                test_argos_sample_1_normal_bam_bai             = "${params.test_data_base_msk}/bam_files/bams/argos_processed/sample_1_normal.chr17.rg.md.abra.printreads.bam.bai"
+                test_argos_sample_1_tumor_bam                  = "${params.test_data_base_msk}/bam_files/bams/argos_processed/sample_1_tumor.chr17.rg.md.abra.printreads.bam"
+                test_argos_sample_1_tumor_bam_bai              = "${params.test_data_base_msk}/bam_files/bams/argos_processed/sample_1_tumor.chr17.rg.md.abra.printreads.bam.bai"
+            }
+            'hg37' {
+                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"
+            }
+    }
 }