Expansionhunter (#666)

Please enter the commit message for your changes. Lines starting

* adds expansionhunter module

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

modules/expansionhunter/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/expansionhunter/main.nf

@@ -0,0 +1,45 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process EXPANSIONHUNTER {
+    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::expansionhunter=4.0.2" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/expansionhunter:4.0.2--he785bd8_0"
+    } else {
+        container "quay.io/biocontainers/expansionhunter:4.0.2--he785bd8_0"
+    }
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    path fasta
+    path variant_catalog
+
+    output:
+    tuple val(meta), path("*.vcf"), emit: vcf
+    path "*.version.txt"          , emit: version
+
+    script:
+    def software = getSoftwareName(task.process)
+    def prefix   = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def gender = (meta.gender == 'male' || meta.gender == 1 || meta.gender == 'XY') ? "male" : "female"
+    """
+    ExpansionHunter \\
+        $options.args \\
+        --reads $bam \\
+        --output-prefix $prefix \\
+        --reference $fasta \\
+        --variant-catalog $variant_catalog \\
+        --sex $gender
+
+    echo \$(ExpansionHunter --version 2>&1) | sed 's/^.*ExpansionHunter //' > ${software}.version.txt
+    """
+}

modules/expansionhunter/meta.yml

@@ -0,0 +1,50 @@
+name: expansionhunter
+description: write your description here
+keywords:
+  - STR
+  - repeat_expansions
+tools:
+  - expansionhunter:
+      description: A tool for estimating repeat sizes
+      homepage: https://github.com/Illumina/ExpansionHunter
+      documentation: https://github.com/Illumina/ExpansionHunter/blob/master/docs/01_Introduction.md
+      tool_dev_url: None
+      doi: "10.1093/bioinformatics/btz431"
+      licence: ['Apache v2.0']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM/CRAM file
+      pattern: "*.{bam,cram}"
+  - fasta:
+      type: file
+      description: Reference genome
+      pattern: "*.{fa,fasta}"
+  - variant_catalog:
+      type: file
+      description: json file with repeat expansion sites to genotype
+      pattern: "*.{json}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', gender:'female' ]
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+  - vcf:
+      type: file
+      description: VCF with repeat expansions
+      pattern: "*.{vcf}"
+
+authors:
+  - "@jemten"

tests/config/pytest_modules.yml

@@ -270,6 +270,10 @@ ensemblvep:
   - modules/ensemblvep/**
   - tests/modules/ensemblvep/**
 
+expansionhunter:
+  - modules/expansionhunter/**
+  - tests/modules/expansionhunter/**
+
 fastp:
   - modules/fastp/**
   - tests/modules/fastp/**

tests/config/test_data.config

@@ -107,6 +107,7 @@ params {
                 mills_and_1000g_indels_vcf_gz                  = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
                 mills_and_1000g_indels_vcf_gz_tbi              = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
                 index_salmon                                   = "${test_data_dir}/genomics/homo_sapiens/genome/index/salmon"
+                repeat_expansions                              = "${test_data_dir}/genomics/homo_sapiens/genome/loci/repeat_expansions.json"
             }
             'illumina' {
                 test_paired_end_sorted_bam                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam"

tests/modules/expansionhunter/main.nf

@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { EXPANSIONHUNTER } from '../../../modules/expansionhunter/main.nf' addParams( options: [:] )
+
+workflow test_expansionhunter {
+
+    input = [ [ id:'test', gender:'male' ], // 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),
+            ]
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+    variant_catalog = file(params.test_data['homo_sapiens']['genome']['repeat_expansions'], checkIfExists: true)
+
+    EXPANSIONHUNTER ( input, fasta, variant_catalog )
+}

tests/modules/expansionhunter/test.yml

@@ -0,0 +1,7 @@
+- name: expansionhunter test_expansionhunter
+  command: nextflow run tests/modules/expansionhunter -entry test_expansionhunter -c tests/config/nextflow.config
+  tags:
+    - expansionhunter
+  files:
+    - path: output/expansionhunter/test.vcf
+      md5sum: ef6c2101d7bd67211bb5a5a132690e02