Getpileupsummaries (#689)

* first commit, added template files for new module

* created getpileupsummaries script, tests and both yml files

* fixed typo in meta.yml

* Update modules/gatk4/getpileupsummaries/meta.yml

changed gz_tbi to gz.tbi as suggested

Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>

Co-authored-by: GCJMackenzie <gavin.mackenzie@nibsc.org>
Co-authored-by: Maxime U. Garcia <max.u.garcia@gmail.com>
Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>

modules/gatk4/getpileupsummaries/functions.nf

@@ -0,0 +1,68 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions  = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_meta) {
+            def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+            for (key in key_list) {
+                if (args.meta && key instanceof String) {
+                    def path = key
+                    if (args.meta.containsKey(key)) {
+                        path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                    }
+                    path = path instanceof String ? path : ''
+                    path_list.add(path)
+                }
+            }
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

modules/gatk4/getpileupsummaries/main.nf

@@ -0,0 +1,48 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GATK4_GETPILEUPSUMMARIES {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.0.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/gatk4:4.2.0.0--0"
+    } else {
+        container "quay.io/biocontainers/gatk4:4.2.0.0--0"
+    }
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    path variants
+    path variants_idx
+    path sites
+
+    output:
+    tuple val(meta), path('*.pileups.table'), emit: table
+    path '*.version.txt'          , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def sitesCommand = ''
+
+    sitesCommand = sites ? " -L ${sites} " : " -L ${variants} "
+
+    """
+    gatk GetPileupSummaries \\
+        -I $bam \\
+        -V $variants \\
+        $sitesCommand \\
+        -O ${prefix}.pileups.table \\
+        $options.args
+
+    echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//' > ${software}.version.txt
+    """
+}

modules/gatk4/getpileupsummaries/meta.yml

@@ -0,0 +1,57 @@
+name: gatk4_getpileupsummaries
+description: |
+  Summarizes counts of reads that support reference, alternate and other alleles for given sites. Results can be used with CalculateContamination. Requires a common germline variant sites file, such as from gnomAD.
+keywords:
+  - gatk4
+  - getpileupsumaries
+  - readcountssummary
+  - germlinevariantsites
+tools:
+  - gatk4:
+      description: |
+        Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
+        with a primary focus on variant discovery and genotyping. Its powerful processing engine
+        and high-performance computing features make it capable of taking on projects of any size.
+      homepage: https://gatk.broadinstitute.org/hc/en-us
+      documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
+      doi: 10.1158/1538-7445.AM2017-3590
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - bam:
+      type: file
+      description: BAM file to be summarised.
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: BAM file index.
+      pattern: "*.bam.bai"
+  - variants:
+      type: file
+      description: Population vcf of germline sequencing, containing allele fractions. Is also used as sites file if no separate sites file is specified.
+      pattern: "*.vcf.gz"
+  - variants_idx:
+      type: file
+      description: Index file for the germline resource.
+      pattern: "*.vcf.gz.tbi"
+  - sites:
+      type: file
+      description: File containing specified sites to be used for the summary. If this option is not specified, variants file is used instead automatically.
+      pattern: "*.interval_list"
+
+output:
+  - pileup:
+      type: file
+      description: File containing the pileup summary table.
+      pattern: "*.pileups.table"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.version.txt"
+
+authors:
+  - "@GCJMackenzie"

tests/config/pytest_modules.yml

@@ -334,6 +334,10 @@ gatk4/fastqtosam:
   - modules/gatk4/fastqtosam/**
   - tests/modules/gatk4/fastqtosam/**
 
+gatk4/getpileupsummaries:
+  - modules/gatk4/getpileupsummaries/**
+  - tests/modules/gatk4/getpileupsummaries/**
+
 gatk4/haplotypecaller:
   - modules/gatk4/haplotypecaller/**
   - tests/modules/gatk4/haplotypecaller/**

tests/modules/gatk4/getpileupsummaries/main.nf

@@ -0,0 +1,31 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_GETPILEUPSUMMARIES } from '../../../../modules/gatk4/getpileupsummaries/main.nf' addParams( options: [:] )
+
+workflow test_gatk4_getpileupsummaries_just_variants {
+
+    input = [ [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true) ,
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true) ]
+
+    variants = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_vcf_gz'], checkIfExists: true)
+    variants_idx = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_vcf_gz_tbi'], checkIfExists: true)
+    sites = []
+
+    GATK4_GETPILEUPSUMMARIES ( input , variants , variants_idx , sites )
+}
+
+workflow test_gatk4_getpileupsummaries_separate_sites {
+
+    input = [ [ id:'test' ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam'], checkIfExists: true) ,
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_bam_bai'], checkIfExists: true) ]
+
+    variants = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_vcf_gz'], checkIfExists: true)
+    variants_idx = file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_vcf_gz_tbi'], checkIfExists: true)
+    sites = file( "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.interval_list" , checkIfExists: true)
+
+    GATK4_GETPILEUPSUMMARIES ( input , variants , variants_idx , sites )
+}

tests/modules/gatk4/getpileupsummaries/test.yml

@@ -0,0 +1,17 @@
+- name: gatk4 getpileupsummaries test_gatk4_getpileupsummaries_just_variants
+  command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_just_variants -c tests/config/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/getpileupsummaries
+  files:
+    - path: output/gatk4/test.pileups.table
+      md5sum: 00f92a8f7282d6129f1aca04e2c7d968
+
+- name: gatk4 getpileupsummaries test_gatk4_getpileupsummaries_separate_sites
+  command: nextflow run tests/modules/gatk4/getpileupsummaries -entry test_gatk4_getpileupsummaries_separate_sites -c tests/config/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/getpileupsummaries
+  files:
+    - path: output/gatk4/test.pileups.table
+      md5sum: 00f92a8f7282d6129f1aca04e2c7d968