gatk4 markduplicates (#356)

* new module gatk4/markduplicates

* add tests

* add gatk4_markduplicates entry in pytest_software.yml

* Update software/gatk4/markduplicates/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/gatk4/markduplicates/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/gatk4/markduplicates/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update software/gatk4/markduplicates/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/gatk4/markduplicates/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Update tests/software/gatk4/markduplicates/main.nf

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* Apply suggestions from code review

* Fix EC lint

* Update md5sum

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

software/gatk4/markduplicates/functions.nf

@@ -0,0 +1,60 @@
+/*
+ * -----------------------------------------------------
+ *  Utility functions used in nf-core DSL2 module files
+ * -----------------------------------------------------
+ */
+
+/*
+ * Extract name of software tool from process name using $task.process
+ */
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+/*
+ * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+ */
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args          = args.args ?: ''
+    options.args2         = args.args2 ?: ''
+    options.args3         = args.args3 ?: ''
+    options.publish_by_id = args.publish_by_id ?: false
+    options.publish_dir   = args.publish_dir ?: ''
+    options.publish_files = args.publish_files
+    options.suffix        = args.suffix ?: ''
+    return options
+}
+
+/*
+ * Tidy up and join elements of a list to return a path string
+ */
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }  // Remove empty entries
+    paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+/*
+ * Function to save/publish module results
+ */
+def saveFiles(Map args) {
+    if (!args.filename.endsWith('.version.txt')) {
+        def ioptions = initOptions(args.options)
+        def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+        if (ioptions.publish_by_id) {
+            path_list.add(args.publish_id)
+        }
+        if (ioptions.publish_files instanceof Map) {
+            for (ext in ioptions.publish_files) {
+                if (args.filename.endsWith(ext.key)) {
+                    def ext_list = path_list.collect()
+                    ext_list.add(ext.value)
+                    return "${getPathFromList(ext_list)}/$args.filename"
+                }
+            }
+        } else if (ioptions.publish_files == null) {
+            return "${getPathFromList(path_list)}/$args.filename"
+        }
+    }
+}

software/gatk4/markduplicates/main.nf

@@ -0,0 +1,44 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GATK4_MARKDUPLICATES {
+    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), publish_id: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)
+
+    output:
+    tuple val(meta), path("*.bam")    , emit: bam
+    tuple val(meta), path("*.metrics"), emit: metrics
+    path "*.version.txt"              , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+    gatk MarkDuplicates \\
+        --INPUT $bam \\
+        --METRICS_FILE ${prefix}.metrics \\
+        --TMP_DIR . \\
+        --ASSUME_SORT_ORDER coordinate \\
+        --CREATE_INDEX true \\
+        --OUTPUT ${prefix}.bam \\
+        $options.args
+
+    gatk --version | grep Picard | sed "s/Picard Version: //g" > ${software}.version.txt
+    """
+}

software/gatk4/markduplicates/meta.yml

@@ -0,0 +1,49 @@
+name: gatk4_markduplicates
+description: This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.
+keywords:
+  - markduplicates
+  - bam
+  - sort
+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/articles/360037052812-MarkDuplicates-Picard-
+      tool_dev_url: https://github.com/broadinstitute/gatk
+      doi: 10.1158/1538-7445.AM2017-3590
+      licence: ['BSD-3-clause']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: Sorted BAM file
+      pattern: "*.{bam}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - bam:
+      type: file
+      description: Marked duplicates BAM file
+      pattern: "*.{bam}"
+  - metrics:
+      type: file
+      description: Duplicate metrics file generated by GATK
+      pattern: "*.{metrics.txt}"
+
+authors:
+  - "@ajodeh-juma"

tests/config/pytest_software.yml

@@ -198,6 +198,9 @@ gatk4_createsequencedictionary:
   - software/gatk4/createsequencedictionary/**
   - tests/software/gatk4/createsequencedictionary/**
 
+gatk4_markduplicates:
+  - software/gatk4/markduplicates/**
+  - tests/software/gatk4/markduplicates/**
 gatk4_fastqtosam:
   - software/gatk4/fastqtosam/**
   - tests/software/gatk4/fastqtosam/**
@@ -252,7 +255,7 @@ hisat2_build:
 hisat2_extractsplicesites:
   - software/hisat2/extractsplicesites/**
   - tests/software/hisat2/extractsplicesites/**
-  
+
 homer_annotatepeaks:
   - software/homer/annotatepeaks/**
   - tests/software/homer/annotatepeaks/**

tests/software/gatk4/markduplicates/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_MARKDUPLICATES } from '../../../../software/gatk4/markduplicates/main.nf' addParams( options: [:] )
+
+workflow test_gatk4_markduplicates {
+    input = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+            ]
+
+    GATK4_MARKDUPLICATES ( input )
+}

tests/software/gatk4/markduplicates/test.yml

@@ -0,0 +1,8 @@
+- name: gatk4 markduplicates test_gatk4_markduplicates
+  command: nextflow run tests/software/gatk4/markduplicates -entry test_gatk4_markduplicates -c tests/config/nextflow.config
+  tags:
+    - gatk4
+    - gatk4_markduplicates
+  files:
+    - path: output/gatk4/test.bam
+      md5sum: b58d47345e3ce5825c0641c9d6e6cb7a