Intervallisttools (#491)

* added intervallisttools module

* add intervallisttools module

* arguments are now supplied using options.args

* removed java heapsize settings

* changes in main.nf and it is tested

* comment added

* Update software/gatk4/intervallisttools/meta.yml

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

* Update tests/software/gatk4/intervallisttools/test.yml

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

* review comment on tags in bedtointerval

* modified the test to get input from bedtointerval module

* Update software/gatk4/intervallisttools/meta.yml

* Apply suggestions from code review

Co-authored-by: Kevin Menden <kevin.menden@live.com>

* Apply suggestions from code review

* Update tests/config/pytest_software.yml

Co-authored-by: Kevin Menden <kevin.menden@live.com>

* Apply suggestions from code review

* Apply suggestions from code review

Co-authored-by: @praveenraj2018 <praveen.raj.somarajan@ki.se>
Co-authored-by: Maxime U. Garcia <maxime.garcia@scilifelab.se>
Co-authored-by: Kevin Menden <kevin.menden@live.com>

software/gatk4/intervallisttools/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/intervallisttools/main.nf

@@ -0,0 +1,53 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GATK4_INTERVALLISTTOOLS {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${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--hdfd78af_1"
+    } else {
+        container "quay.io/biocontainers/gatk4:4.2.0.0--hdfd78af_1"
+    }
+
+    input:
+    tuple val(meta), path(interval_list)
+
+    output:
+    tuple val(meta), path("*_split/*/*.interval_list"), emit: interval_list
+    path "*.version.txt"          , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    """
+
+    mkdir ${prefix}_split
+
+    gatk \\
+    IntervalListTools \\
+    -I ${interval_list} \\
+    -O ${prefix}_split \\
+    $options.args
+
+    python3 <<CODE
+    import glob, os
+    # The following python code snippet rename the output files into different name to avoid overwriting or name conflict
+    intervals = sorted(glob.glob("*_split/*/*.interval_list"))
+    for i, interval in enumerate(intervals):
+        (directory, filename) = os.path.split(interval)
+        newName = os.path.join(directory, str(i + 1) + filename)
+        os.rename(interval, newName)
+    CODE
+
+    gatk --version | grep Picard | sed "s/Picard Version: //g" > ${software}.version.txt
+    """
+}

software/gatk4/intervallisttools/meta.yml

@@ -0,0 +1,46 @@
+name: gatk4_intervallisttools
+
+description: Splits the interval list file into unique, equally-sized interval files and place it under a directory
+keywords:
+  - sort
+  - bed
+  - interval list
+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', single_end:false ]
+
+  - interval_list:
+      type: file
+      description: Interval list file
+      pattern: "*.interval_list"
+
+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}"
+  - interval_list:
+      type: file
+      description: Interval list files
+      pattern: "*.interval_list"
+
+authors:
+  - "@praveenraj2018"

tests/config/pytest_software.yml

@@ -290,6 +290,10 @@ gatk4/variantfiltration:
   - software/gatk4/variantfiltration/**
   - tests/software/gatk4/variantfiltration/**
 
+gatk4/intervallisttools:
+  - software/gatk4/intervallisttools/**
+  - tests/software/gatk4/intervallisttools/**
+
 gffread:
   - software/gffread/**
   - tests/software/gffread/**

tests/software/gatk4/intervallisttools/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+test_options = ['args': '--SCATTER_COUNT 6 --SUBDIVISION_MODE BALANCING_WITHOUT_INTERVAL_SUBDIVISION_WITH_OVERFLOW --UNIQUE true --SORT true']
+include { GATK4_BEDTOINTERVALLIST } from '../../../../software/gatk4/bedtointervallist/main.nf' addParams( options: [:] )
+include { GATK4_INTERVALLISTTOOLS as INTERVALLISTTOOLS } from '../../../../software/gatk4/intervallisttools/main.nf' addParams( options: test_options )
+
+workflow test_gatk4_intervallisttools {
+
+    input = [ [ id:'test' ], [ file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true) ]]
+    dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true)
+
+    GATK4_BEDTOINTERVALLIST ( input, dict )
+    INTERVALLISTTOOLS ( GATK4_BEDTOINTERVALLIST.out.interval_list )
+}

tests/software/gatk4/intervallisttools/test.yml

@@ -0,0 +1,16 @@
+- name: gatk4 intervallisttools test_gatk4_intervallisttools
+  command: nextflow run tests/software/gatk4/intervallisttools -entry test_gatk4_intervallisttools -c tests/config/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/intervallisttools
+  files:
+    - path: output/gatk4/test.interval_list
+      md5sum: e51101c9357fb2d59fd30e370eefa39c
+    - path: output/intervallisttools/test_split/temp_0001_of_6/1scattered.interval_list
+      md5sum: b8ba8a387200df76a0d1c577626dc265
+    - path: output/intervallisttools/test_split/temp_0002_of_6/2scattered.interval_list
+      md5sum: 0728d164666d9264ef442a493e008dee
+    - path: output/intervallisttools/test_split/temp_0003_of_6/3scattered.interval_list
+      md5sum: 55da0f3c69504148f4e7002a0e072cfe
+    - path: output/intervallisttools/test_split/temp_0004_of_6/4scattered.interval_list
+      md5sum: d29ca4447f32547f2936567fa902796a