Learnreadorientationmodel (#794)

* files for learnreadorientationmodel initialised for first commit

* finished scripts and yml files. test working locally but needs an f1r2 test data on nf-core before it can be submitted

* updated test data location

* versions file updated, test data added

* updated versions file, edited test file

* small formatting update to main.nf

* Update main.nf

* Update test_data.config

* updated tests main.nf

* Update test_data.config

* Apply suggestions from code review

* Update modules/gatk4/learnreadorientationmodel/main.nf

* Update modules/gatk4/learnreadorientationmodel/meta.yml

* fixed tests failing

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

modules/gatk4/learnreadorientationmodel/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+    // Do not publish versions.yml unless running from pytest workflow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/learnreadorientationmodel/main.nf

@@ -0,0 +1,44 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GATK4_LEARNREADORIENTATIONMODEL {
+    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(f1r2)
+
+    output:
+    tuple val(meta), path("*.tar.gz"), emit: artifactprior
+    path "versions.yml"              , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def inputs_list = []
+    f1r2.each() { a -> inputs_list.add(" -I " + a) }
+    """
+    gatk \\
+        LearnReadOrientationModel \\
+        ${inputs_list.join(' ')} \\
+        -O ${prefix}.tar.gz \\
+        $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/learnreadorientationmodel/meta.yml

@@ -0,0 +1,41 @@
+name: gatk4_learnreadorientationmodel
+description: |
+  Uses f1r2 counts collected during mutect2 to Learn the prior probability of read orientation artifacts
+keywords:
+  - gatk4
+  - learnreadorientationmodel
+  - readorientationartifacts
+  - mutect2
+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' ]
+  - f1r2:
+      type: list
+      description: list of f1r2 files to be used as input.
+      pattern: "*.f1r2.tar.gz"
+
+output:
+  - artifactprior:
+      type: file
+      description: file containing artifact-priors to be used by filtermutectcalls
+      pattern: "*.tar.gz"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@GCJMackenzie"

tests/config/pytest_modules.yml

@@ -410,6 +410,10 @@ gatk4/intervallisttools:
   - modules/gatk4/intervallisttools/**
   - tests/modules/gatk4/intervallisttools/**
 
+gatk4/learnreadorientationmodel:
+  - modules/gatk4/learnreadorientationmodel/**
+  - tests/modules/gatk4/learnreadorientationmodel/**
+
 gatk4/markduplicates:
   - modules/gatk4/markduplicates/**
   - tests/modules/gatk4/markduplicates/**

tests/config/test_data.config

@@ -155,6 +155,14 @@ params {
                 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                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
+                
+                test_test2_paired_mutect2_calls_vcf_gz         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz"
+                test_test2_paired_mutect2_calls_vcf_gz_tbi     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi"
+                test_test2_paired_mutect2_calls_vcf_gz_stats   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.stats"
+                test_test2_paired_mutect2_calls_f1r2_tar_gz    = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.f1r2.tar.gz"                                                               
+                test_test2_paired_mutect2_calls_artifact_prior_tar_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired_mutect2_calls.artifact-prior.tar.gz"
+                test_test2_paired_segmentation_table           = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.segmentation.table"
+                test_test2_paired_contamination_table          = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_test2_paired.contamination.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/learnreadorientationmodel/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GATK4_LEARNREADORIENTATIONMODEL } from '../../../../modules/gatk4/learnreadorientationmodel/main.nf' addParams( options: [suffix:'.artifact-prior'] )
+
+workflow test_gatk4_learnreadorientationmodel {
+
+    input = [ [ id:'test' ], // meta map
+              [file(params.test_data['homo_sapiens']['illumina']['test_test2_paired_mutect2_calls_f1r2_tar_gz'], checkIfExists: true)] ]
+
+    GATK4_LEARNREADORIENTATIONMODEL ( input )
+}

tests/modules/gatk4/learnreadorientationmodel/test.yml

@@ -0,0 +1,7 @@
+- name: gatk4 learnreadorientationmodel test_gatk4_learnreadorientationmodel
+  command: nextflow run tests/modules/gatk4/learnreadorientationmodel -entry test_gatk4_learnreadorientationmodel -c tests/config/nextflow.config
+  tags:
+    - gatk4
+    - gatk4/learnreadorientationmodel
+  files:
+    - path: output/gatk4/test.artifact-prior.tar.gz