new module: gatk4/calculatecontamination (#778)

* initiated files for calculate contamination

* pushing local repo to remote

* created script, filled in meta yml, created tests and test yml. local checks passing, needs repo side test data

* added option and tests for outputting optional segmentation file

* saving for test push

* versions updated, test data added

* Update main.nf

* fixed versions info, should report correctly now

* small update to main.nf outputs formatting

* Apply suggestions from code review

* Update test_data.config

* Apply suggestions from code review

Co-authored-by: GCJMackenzie <gavin.mackenzie@nibsc.org>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/gatk4/calculatecontamination/functions.nf

@@ -0,0 +1,78 @@
+//
+//  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()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${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/calculatecontamination/main.nf

@@ -0,0 +1,47 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GATK4_CALCULATECONTAMINATION {
+    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(pileup), path(matched)
+    val segmentout
+
+    output:
+    tuple val(meta), path('*.contamination.table')               , emit: contamination
+    tuple val(meta), path('*.segmentation.table') , optional:true, emit: segmentation
+    path "versions.yml"                                          , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def matched_command = matched ? " -matched ${matched} " : ''
+    def segment_command = segmentout ? " -segments ${prefix}.segmentation.table" : ''
+    """
+    gatk CalculateContamination \\
+        -I $pileup \\
+        $matched_command \\
+        -O ${prefix}.contamination.table \\
+        $segment_command \\
+        $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/calculatecontamination/meta.yml

@@ -0,0 +1,53 @@
+name: gatk4_calculatecontamination
+description: |
+  Calculates the fraction of reads from cross-sample contamination based on summary tables from getpileupsummaries. Output to be used with filtermutectcalls.
+keywords:
+  - gatk4
+  - calculatecontamination
+  - cross-samplecontamination
+  - getpileupsummaries
+  - filtermutectcalls
+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' ]
+  - pileup:
+      type: file
+      description: File containing the pileups summary table of a tumor sample to be used to calculate contamination.
+      pattern: "*.pileups.table"
+  - matched:
+      type: file
+      description: File containing the pileups summary table of a normal sample that matches with the tumor sample specified in pileup argument. This is an optional input.
+      pattern: "*.pileups.table"
+  - segmentout:
+      type: boolean
+      description: specifies whether to output the segmentation table.
+
+output:
+  - contamination:
+      type: file
+      description: File containing the contamination table.
+      pattern: "*.contamination.table"
+  - segmentation:
+      type: file
+      description: optional output table containing segmentation of tumor minor allele fractions.
+      pattern: "*.segmentation.table"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@GCJMackenzie"

tests/config/pytest_modules.yml

@@ -386,6 +386,10 @@ gatk4/bedtointervallist:
   - modules/gatk4/bedtointervallist/**
   - tests/modules/gatk4/bedtointervallist/**
 
+gatk4/calculatecontamination:
+  - modules/gatk4/calculatecontamination/**
+  - tests/modules/gatk4/calculatecontamination/**
+
 gatk4/createsequencedictionary:
   - modules/gatk4/createsequencedictionary/**
   - tests/modules/gatk4/createsequencedictionary/**

tests/config/test_data.config

@@ -153,6 +153,8 @@ params {
 
                 test_baserecalibrator_table                    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table"
                 test2_baserecalibrator_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
+                test_pileups_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
+                test2_pileups_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
 
                 test_genome_vcf                                = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf"
                 test_genome_vcf_gz                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gvcf/test.genome.vcf.gz"

tests/modules/gatk4/calculatecontamination/main.nf

@@ -0,0 +1,38 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_CALCULATECONTAMINATION } from '../../../../modules/gatk4/calculatecontamination/main.nf' addParams( options: [:] )
+
+workflow test_gatk4_calculatecontamination_tumor_only {
+
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test2_pileups_table'], checkIfExists: true),
+              [] ]
+
+    segmentout = false
+
+    GATK4_CALCULATECONTAMINATION ( input, segmentout )
+}
+
+workflow test_gatk4_calculatecontamination_matched_pair {
+
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test2_pileups_table'], checkIfExists: true),
+              file(params.test_data['homo_sapiens']['illumina']['test_pileups_table'], checkIfExists: true) ]
+
+    segmentout = false
+
+    GATK4_CALCULATECONTAMINATION ( input, segmentout )
+}
+
+workflow test_gatk4_calculatecontamination_segmentation {
+
+    input = [ [ id:'test' ], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test2_pileups_table'], checkIfExists: true),
+              file(params.test_data['homo_sapiens']['illumina']['test_pileups_table'], checkIfExists: true) ]
+
+    segmentout = true
+
+    GATK4_CALCULATECONTAMINATION ( input, segmentout )
+}

tests/modules/gatk4/calculatecontamination/test.yml

@@ -0,0 +1,28 @@
+- name: gatk4 calculatecontamination test_gatk4_calculatecontamination_tumor_only
+  command: nextflow run tests/modules/gatk4/calculatecontamination -entry test_gatk4_calculatecontamination_tumor_only -c tests/config/nextflow.config
+  tags:
+    - gatk4/calculatecontamination
+    - gatk4
+  files:
+    - path: output/gatk4/test.contamination.table
+      md5sum: ff348a26dd09404239a7ed0da7d98874
+
+- name: gatk4 calculatecontamination test_gatk4_calculatecontamination_matched_pair
+  command: nextflow run tests/modules/gatk4/calculatecontamination -entry test_gatk4_calculatecontamination_matched_pair -c tests/config/nextflow.config
+  tags:
+    - gatk4/calculatecontamination
+    - gatk4
+  files:
+    - path: output/gatk4/test.contamination.table
+      md5sum: ff348a26dd09404239a7ed0da7d98874
+
+- name: gatk4 calculatecontamination test_gatk4_calculatecontamination_segmentation
+  command: nextflow run tests/modules/gatk4/calculatecontamination -entry test_gatk4_calculatecontamination_segmentation -c tests/config/nextflow.config
+  tags:
+    - gatk4/calculatecontamination
+    - gatk4
+  files:
+    - path: output/gatk4/test.contamination.table
+      md5sum: ff348a26dd09404239a7ed0da7d98874
+    - path: output/gatk4/test.segmentation.table
+      md5sum: 478cb4f69ec001944b9cd0e7e4de01ef