Purecn/run

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

@@ -0,0 +1,100 @@
+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':
+        'quay.io/biocontainers/mulled-v2-582ac26068889091d5e798347c637f8208d77a71:a29c64a63498b1ee8b192521fdf6ed3c65506994-0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+    path tumor_coverage
+    path normal_coverage
+    path normal_db
+    path intervals
+    path mapping_bias
+    path blacklist
+    val genome
+    val segmentation_function
+    val model_type
+    val seed_val
+
+    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: 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("*-purecn-lohsummary.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 normal_cov = normal_coverage ? "--fun-segmentation ${normal_coverage}" : ""
+    def segmentation = segmentation_function ? "--fun-segmentation ${segmentation_function}" : ""
+    def map_bias = mapping_bias ? "--mapping-bias-file ${mapping_bias}" : ""
+    def model = model_type ? "--model ${model_type}" : ""
+    def blacklist = snp_blacklist ? "--snp-blacklist ${snp_blacklist}" : ""
+    def seed = seed_val ? "--seed ${seed_val}" : ""
+    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.R \\
+        --out ./ \\
+        --tumor ${tumor_coverage} \\
+        --normal ${normal_cov} \\
+        --sampleid ${prefix} \\
+        --vcf ${vcf} \\
+        --normaldb ${normal_db} \\
+        --intervals ${intervals} \\
+        --genome ${genome} \\
+        --stats-file ${prefix}_stats.txt \\
+        ${segmentation} \\
+        ${map_bias} \\
+        ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        purecn: ${VERSION}
+    END_VERSIONS
+    """
+
+    stub:
+
+    //TODO add STUB
+
+    """
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        purecn: ${VERSION}
+    END_VERSIONS
+    """
+}

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

@@ -0,0 +1,50 @@
+name: "purecn_run"
+description: run PureCN to normalize, segment and determine purity and ploidy
+keywords:
+  - copy number alteration calling
+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"
+
+## TODO nf-core: Add a description of all of the variables used as input
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  #
+  ## TODO nf-core: Delete / customise this example input
+  - bam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+## 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:'test', 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:
+  - "@aldosr"
+  - "@lbeltrame"

tests/config/pytest_modules.yml

@@ -2779,6 +2779,10 @@ prokka:
   - modules/nf-core/prokka/**
   - tests/modules/nf-core/prokka/**
 
+purecn/run:
+  - modules/nf-core/purecn/run/**
+  - tests/modules/nf-core/purecn/run/**
+
 purecn/normaldb:
   - modules/nf-core/purecn/normaldb/**
   - tests/modules/nf-core/purecn/normaldb/**

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

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PURECN_RUN } from '../../../../../modules/nf-core/purecn/run/main.nf'
+
+workflow test_purecn_run {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    PURECN_RUN ( input )
+}

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 +1,12 @@
+## TODO nf-core: Please run the following command to build this file:
+#                nf-core modules create-test-yml purecn/run
+- 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
+  tags:
+    - "purecn"
+    - "purecn/run"
+  files:
+    - path: "output/purecn/test.bam"
+      md5sum: e667c7caad0bc4b7ac383fd023c654fc
+    - path: "output/purecn/versions.yml"
+      md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b