Purecn/run

modules/nf-core/purecn/run/main.nf

@@ -0,0 +1,111 @@
+process PURECN_RUN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    // WARN: Version information not provided by tool on CLI. Please update version string below when bumping container versions.
+    conda "bioconda::bioconductor-purecn=2.4.0 bioconda::bioconductor-txdb.hsapiens.ucsc.hg38.knowngene=3.16.0 bioconductor-txdb.hsapiens.ucsc.hg19.knowngene=3.2.2 bioconda::bioconductor-org.hs.eg.db=3.16.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-582ac26068889091d5e798347c637f8208d77a71:a29c64a63498b1ee8b192521fdf6ed3c65506994-0':
+        'biocontainers/mulled-v2-582ac26068889091d5e798347c637f8208d77a71:a29c64a63498b1ee8b192521fdf6ed3c65506994-0' }"
+
+    input:
+    tuple val(meta), path(intervals), path(coverage), path(vcf)
+    path normal_db
+    val genome
+
+    output:
+    tuple val(meta), path("*.csv")                             , emit: csv
+    tuple val(meta), path("*_variants.csv")                    , emit: variants_csv
+    tuple val(meta), path("*.pdf")                             , emit: pdf
+    tuple val(meta), path("*.rds")                             , emit: rds
+    tuple val(meta), path("*_amplification_pvalues.csv")       , emit: amplification_pvalues_csv
+    tuple val(meta), path("*_chromosomes.pdf")                 , emit: chr_pdf
+    tuple val(meta), path("*_dnacopy.seg")                     , emit: seg
+    tuple val(meta), path("*_genes.csv")                       , emit: genes_csv
+    tuple val(meta), path("*_local_optima.pdf")                , emit: local_optima_pdf
+    tuple val(meta), path("*.log")                             , emit: log
+    tuple val(meta), path("*_loh.vcf")                         , emit: loh_vcf
+    tuple val(meta), path("*_loh.vcf.gz")                      , emit: loh_vcf_gz
+    tuple val(meta), path("*_loh.vcf.gz.tbi")                  , emit: loh_vcf_tbi
+    tuple val(meta), path("*_loh.csv")                         , emit: loh_csv
+    tuple val(meta), path("*_loh-effects-stats.csv")           , emit: loh_stats_csv
+    tuple val(meta), path("*_loh-effects-stats.genes.txt")     , emit: loh_effects_txt
+    tuple val(meta), path("*_loh-effects-stats.html")          , emit: loh_effects_html
+    tuple val(meta), path("*_loh-effects.vcf.gz")              , emit: loh_effects_vcf
+    tuple val(meta), path("*_loh-effects.vcf.gz.tbi")          , emit: loh_effects_tbi
+    tuple val(meta), path("*_loh-summary.yaml")                , emit: loh_summary_yaml
+    tuple val(meta), path("*_loh-effects.csv")                 , emit: loh_effects_csv
+    tuple val(meta), path("*_segmentation.pdf")                , emit: segmentation_pdf
+    tuple val(meta), path("*_sort_coverage_loess.png")         , emit: sort_coverage_loess_png
+    tuple val(meta), path("*_sort_coverage_loess_qc.txt")      , emit: sort_coverage_loess_qc_txt
+    tuple val(meta), path("*_sort_coverage_loess.txt.gz")      , emit: sort_coverage_loess_txt_gz
+    tuple val(meta), path("*_sort_coverage.txt.gz")            , emit: sort_coverage_txt_gz
+    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}"
+    def VERSION = '2.4.0' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+
+    """
+    library_path=\$(Rscript -e 'cat(.libPaths(), sep = "\\n")')
+    Rscript "\$library_path"/PureCN/extdata/PureCN.R \\
+        --out ./ \\
+        --tumor ${coverage} \\
+        --sampleid ${prefix} \\
+        --vcf ${vcf} \\
+        --normaldb ${normal_db} \\
+        --intervals ${intervals} \\
+        --genome ${genome} \\
+        --parallel \\
+        --cores ${task.cpus} \\
+        --stats-file ${prefix}_stats.txt \\
+        ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        purecn: ${VERSION}
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '2.4.0' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+
+    """
+    touch ${prefix}.csv
+    touch ${prefix}_variants.csv
+    touch ${prefix}.pdf
+    touch ${prefix}.rds
+    touch ${prefix}_amplification_pvalues.csv
+    touch ${prefix}_chromosomes.pdf
+    touch ${prefix}_dnacopy.seg
+    touch ${prefix}_genes.csv
+    touch ${prefix}_local_optima.pdf
+    touch ${prefix}.log
+    touch ${prefix}_loh.vcf
+    touch ${prefix}_loh.vcf.gz
+    touch ${prefix}_loh.vcf.gz.tbi
+    touch ${prefix}_loh.csv
+    touch ${prefix}_loh-effects-stats.csv
+    touch ${prefix}_loh-effects-stats.genes.txt
+    touch ${prefix}_loh-effects-stats.html
+    touch ${prefix}_loh-effects.vcf.gz
+    touch ${prefix}_loh-effects.vcf.gz.tbi
+    touch ${prefix}_loh-summary.yaml
+    touch ${prefix}_loh-effects.csv
+    touch ${prefix}_segmentation.pdf
+    touch ${prefix}_sort_coverage_loess.png
+    touch ${prefix}_sort_coverage_loess_qc.txt
+    touch ${prefix}_sort_coverage_loess.txt.gz
+    touch ${prefix}_sort_coverage.txt.gz
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        purecn: ${VERSION}
+    END_VERSIONS
+    """
+}

modules/nf-core/purecn/run/meta.yml

@@ -0,0 +1,185 @@
+name: "purecn_run"
+description: Run PureCN workflow to normalize, segment and determine purity and ploidy
+keywords:
+  - copy number alteration calling
+  - hybrid capture sequencing
+  - targeted sequencing
+  - DNA sequencing
+tools:
+  - "purecn":
+      description: "Copy number calling and SNV classification using targeted short read sequencing"
+      homepage: "https://bioconductor.org/packages/release/bioc/html/PureCN.html"
+      documentation: "https://bioconductor.org/packages/release/bioc/html/PureCN.html"
+      tool_dev_url: "https://github.com/lima1/PureCN"
+      doi: "10.1186/s13029-016-0060-z"
+      licence: "Artistic-2.0"
+      args_id: "$args"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - intervals:
+      type: file
+      description: |
+        BED file of target intervals, generated from IntervalFile.R
+      pattern: "{*.bed,*.txt}"
+  - coverage:
+      type: file
+      description: Coverage file generated from Coverage.R
+      pattern: "*.txt"
+  - vcf:
+      type: file
+      description: |
+        Normal panel in VCF format, used to calculate mapping bias
+      pattern: "*.vcf.gz"
+  - normaldb:
+      type: file
+      description: |
+        Normal panel in RDS format, generated from NormalDB.R
+      pattern: "*.rds"
+  - genome:
+      type: string
+      description: Genome build
+
+output:
+  - csv:
+      type: file
+      description: |
+        CSV file containing copy number calls
+      pattern: "*.csv"
+  - variants_csv:
+      type: file
+      description: |
+        CSV file containing SNV calls
+      pattern: "*_variants.csv"
+  - pdf:
+      type: file
+      description: |
+        PDF file containing copy number plots
+      pattern: "*.pdf"
+  - rds:
+      type: file
+      description: |
+        RDS file containing copy number calls
+      pattern: "*.rds"
+  - amplification_pvalues_csv:
+      type: file
+      description: |
+        CSV file containing amplification p-values
+      pattern: "*_amplification_pvalues.csv"
+  - chr_pdf:
+      type: file
+      description: |
+        PDF file containing chromosome plots
+      pattern: "*_chromosomes.pdf"
+  - seg:
+      type: file
+      description: |
+        Segmentation file generated from DNAcopy.R
+      pattern: "*_dnacopy.seg"
+  - genes_csv:
+      type: file
+      description: |
+        CSV file containing gene copy number calls
+      pattern: "*_genes.csv"
+  - local_optima_pdf:
+      type: file
+      description: |
+        PDF file containing local optima plots
+      pattern: "*_local_optima.pdf"
+  - log:
+      type: file
+      description: |
+        Log file
+      pattern: "*.log"
+  - loh_vcf:
+      type: file
+      description: |
+        VCF file containing LOH calls
+      pattern: "*_loh.vcf"
+  - loh_vcf_gz:
+      type: file
+      description: |
+        GZipped VCF file containing LOH calls
+      pattern: "*_loh.vcf.gz"
+  - loh_vcf_tbi:
+      type: file
+      description: |
+        Tabix index file for LOH VCF
+      pattern: "*_loh.vcf.gz.tbi"
+  - loh_csv:
+      type: file
+      description: |
+        CSV file containing LOH calls
+      pattern: "*_loh.csv"
+  - loh_stats_csv:
+      type: file
+      description: |
+        CSV file containing LOH statistics
+      pattern: "*_loh-effects-stats.csv"
+  - loh_effects_txt:
+      type: file
+      description: |
+        TXT file containing LOH effects
+      pattern: "*_loh-effects-stats.genes.txt"
+  - loh_effects_html:
+      type: file
+      description: |
+        HTML file containing LOH effects
+      pattern: "*_loh-effects-stats.html"
+  - loh_effects_vcf:
+      type: file
+      description: |
+        VCF file containing LOH effects
+      pattern: "*_loh-effects.vcf.gz"
+  - loh_effects_tbi:
+      type: file
+      description: |
+        Tabix index file for LOH effects VCF
+      pattern: "*_loh-effects.vcf.gz.tbi"
+  - loh_summary_yaml:
+      type: file
+      description: |
+        YAML file containing LOH summary
+      pattern: "*_loh-summary.yaml"
+  - loh_effects_csv:
+      type: file
+      description: |
+        CSV file containing LOH effects
+      pattern: "*_loh-effects.csv"
+  - segmentation_pdf:
+      type: file
+      description: |
+        PDF file containing segmentation plots
+      pattern: "*_segmentation.pdf"
+  - sort_coverage_loess_png:
+      type: file
+      description: |
+        PNG file containing sort coverage loess plots
+      pattern: "*_sort-coverage-loess.png"
+  - sort_coverage_loess_qc_txt:
+      type: file
+      description: |
+        TXT file containing sort coverage loess QC
+      pattern: "*_sort-coverage-loess.qc.txt"
+  - sort_coverage_loess_txt_gz:
+      type: file
+      description: |
+        GZipped TXT file containing sort coverage loess
+      pattern: "*_sort-coverage-loess.txt.gz"
+  - sort_coverage_txt_gz:
+      type: file
+      description: |
+        GZipped TXT file containing sort coverage
+      pattern: "*_sort-coverage.txt.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@aldosr"
+  - "@lbeltrame"

tests/config/pytest_modules.yml

@@ -2867,6 +2867,10 @@ purecn/normaldb:
   - modules/nf-core/purecn/normaldb/**
   - tests/modules/nf-core/purecn/normaldb/**
 
+purecn/run:
+  - modules/nf-core/purecn/run/**
+  - tests/modules/nf-core/purecn/run/**
+
 purgedups/calcuts:
   - modules/nf-core/purgedups/calcuts/**
   - tests/modules/nf-core/purgedups/calcuts/**

tests/modules/nf-core/purecn/run/main.nf

@@ -0,0 +1,38 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PURECN_RUN } from '../../../../../modules/nf-core/purecn/run/main.nf'
+
+process STUB_PURECN_RUN {
+    output:
+    path("*.txt")                , emit: intervals
+    path("*.txt")                , emit: coverage
+    path("*.vcf.gz")             , emit: vcf
+    path("*.rds")                , emit: normal_db
+
+    stub:
+    """
+    touch interval_file.txt
+    touch coverage.txt
+    touch test.vcf.gz
+    touch normal_db.rds
+    """
+}
+
+workflow test_purecn_run {
+
+    STUB_PURECN_RUN()
+
+    input = [
+        [ id:'test'],
+        file("interval_file.txt"),
+        file("coverage.txt"),
+        file("test.vcf.gz")
+    ]
+
+    normal_db = file("normal_db.rds")
+    genome = "hg38"
+
+    PURECN_RUN ( input, normal_db, genome )
+}

tests/modules/nf-core/purecn/run/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}

tests/modules/nf-core/purecn/run/test.yml

@@ -0,0 +1,33 @@
+- name: purecn run
+  command: nextflow run ./tests/modules/nf-core/purecn/run -entry test_purecn_run -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/purecn/run/nextflow.config -stub-run
+  tags:
+    - purecn
+    - purecn/run
+  files:
+    - path: output/purecn/test.csv
+    - path: output/purecn/test_variants.csv
+    - path: output/purecn/test.pdf
+    - path: output/purecn/test.rds
+    - path: output/purecn/test_amplification_pvalues.csv
+    - path: output/purecn/test_chromosomes.pdf
+    - path: output/purecn/test_dnacopy.seg
+    - path: output/purecn/test_genes.csv
+    - path: output/purecn/test_local_optima.pdf
+    - path: output/purecn/test.log
+    - path: output/purecn/test_loh.vcf
+    - path: output/purecn/test_loh.vcf.gz
+    - path: output/purecn/test_loh.vcf.gz.tbi
+    - path: output/purecn/test_loh.csv
+    - path: output/purecn/test_loh-effects-stats.csv
+    - path: output/purecn/test_loh-effects-stats.genes.txt
+    - path: output/purecn/test_loh-effects-stats.html
+    - path: output/purecn/test_loh-effects.vcf.gz
+    - path: output/purecn/test_loh-effects.vcf.gz.tbi
+    - path: output/purecn/test_loh-summary.yaml
+    - path: output/purecn/test_loh-effects.csv
+    - path: output/purecn/test_segmentation.pdf
+    - path: output/purecn/test_sort_coverage_loess.png
+    - path: output/purecn/test_sort_coverage_loess_qc.txt
+    - path: output/purecn/test_sort_coverage_loess.txt.gz
+    - path: output/purecn/test_sort_coverage.txt.gz
+    - path: output/purecn/versions.yml