New module: genrich (#877)

* Add genrich module * Rearrange genrich module from genrich/genrich to genrich * Remove copy/paste code * Fix meta.yml * Implement save_duplicates independently of -r opt
2024-12-31 03:32:10 -05:00 · 2021-10-22 12:22:02 +02:00 · 2021-10-22 12:22:02 +02:00 · 32f6191aca
commit 32f6191aca
parent 4ed5e4eff3
7 changed files with 307 additions and 0 deletions
--- a/modules/genrich/functions.nf
+++ b/modules/genrich/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+    // Do not publish versions.yml unless running from pytest workflow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)}/$args.filename"
+    }
+}
--- a/modules/genrich/main.nf
+++ b/modules/genrich/main.nf
@ -0,0 +1,69 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GENRICH {
+    tag "$meta.id"
+    label 'process_high'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::genrich=0.6.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/genrich:0.6.1--h5bf99c6_1"
+    } else {
+        container "quay.io/biocontainers/genrich:0.6.1--h5bf99c6_1"
+    }
+
+    input:
+    tuple val(meta), path(treatment_bam)
+    path  control_bam
+    path  blacklist_bed
+
+    output:
+    tuple val(meta), path("*narrowPeak")                     , emit: peaks
+    tuple val(meta), path("*pvalues.bedGraph"), optional:true, emit: bedgraph_pvalues
+    tuple val(meta), path("*pileup.bedGraph") , optional:true, emit: bedgraph_pileup
+    tuple val(meta), path("*intervals.bed")   , optional:true, emit: bed_intervals
+    tuple val(meta), path("*duplicates.txt")  , optional:true, emit: duplicates
+    path "versions.yml"                                      , emit: versions
+
+    script:
+    def prefix     = options.suffix              ? "${meta.id}${options.suffix}"   : "${meta.id}"
+    def control    = params.control_bam          ? "-c $control_bam"               : ''
+    def pvalues    = params.pvalues              ? "-f ${prefix}.pvalues.bedGraph" : ""
+    def pileup     = params.pileup               ? "-k ${prefix}.pileup.bedGraph"  : ""
+    def bed        = params.bed                  ? "-b ${prefix}.intervals.bed"    : ""
+    def blacklist  = params.blacklist_bed        ? "-E $blacklist_bed"             : ""
+    def duplicates = ""
+    if (params.save_duplicates) {
+        if (options.args.contains('-r')) {
+            duplicates = "-R ${prefix}.duplicates.txt"
+        } else {
+            log.info '[Genrich] Duplicates can only be saved if they are filtered, defaulting to -r option (Remove PCR duplicates).'
+            duplicates = "-r -R ${prefix}.duplicates.txt"
+        }
+    }
+    """
+    Genrich \\
+        -t $treatment_bam \\
+        $options.args \\
+        $control \\
+        $blacklist \\
+        -o ${prefix}.narrowPeak \\
+        $pvalues \\
+        $pileup \\
+        $bed \\
+        $duplicates \\
+        $blacklist \\
+        $control
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(Genrich --version 2>&1) | sed 's/^Genrich, version //; s/ .*\$//')
+    END_VERSIONS
+    """
+}
--- a/modules/genrich/meta.yml
+++ b/modules/genrich/meta.yml
@ -0,0 +1,71 @@
+name: genrich
+description: Peak-calling for ChIP-seq and ATAC-seq enrichment experiments
+keywords:
+  - peak-calling
+  - ChIP-seq
+  - ATAC-seq
+tools:
+  - genrich:
+      description: |
+        Genrich is a peak-caller for genomic enrichment assays (e.g. ChIP-seq, ATAC-seq).
+        It analyzes alignment files generated following the assay and produces a file
+        detailing peaks of significant enrichment.
+      homepage: https://github.com/jsh58/Genrich
+      documentation: https://github.com/jsh58/Genrich#readme
+      tool_dev_url: https://github.com/jsh58/Genrich
+      doi: ""
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - treatment_bam:
+      type: file
+      description: Coordinate sorted BAM/SAM file from treatment sample
+      pattern: "*.{bam,sam}"
+  - control_bam:
+      type: file
+      description: Coordinate sorted BAM/SAM file from control sample
+      pattern: "*.{bam,sam}"
+  - blacklist_bed:
+      type: file
+      description: Bed file containing genomic intervals to exclude from the analysis
+      pattern: "*.{bed}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - peaks:
+      type: file
+      description: Output file is in ENCODE narrowPeak format
+      pattern: "*.{narrowPeak}"
+  - bedgraph_pvalues:
+      type: file
+      description: bedGraph file containing p/q values
+      pattern: "*.{pvalues.bedGraph}"
+  - bedgraph_pileup:
+      type: file
+      description: bedGraph file containing pileups and p-values
+      pattern: "*.{pileup.bedGraph}"
+  - bed_intervals:
+      type: file
+      description: Bed file containing annotated intervals
+      pattern: "*.{intervals.bed}"
+  - duplicates:
+      type: file
+      description: Text output file containing intervals corresponding to PCR duplicates
+      pattern: "*.{intervals.txt}"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@JoseEspinosa"
+
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@ -466,6 +466,10 @@ genmap/mappability:
  - modules/genmap/mappability/**
  - tests/modules/genmap/mappability/**

+genrich:
+  - modules/genrich/**
+  - tests/modules/genrich/**
+
 gffread:
  - modules/gffread/**
  - tests/modules/gffread/**
--- a/tests/config/test_data.config
+++ b/tests/config/test_data.config
@ -123,6 +123,7 @@ params {
            'illumina' {
                test_paired_end_sorted_bam                              = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam"
                test_paired_end_sorted_bam_bai                          = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam.bai"
+                test_paired_end_name_sorted_bam                         = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.name.sorted.bam"
                test_paired_end_markduplicates_sorted_bam               = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.markduplicates.sorted.bam"
                test_paired_end_markduplicates_sorted_bam_bai           = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.markduplicates.sorted.bam.bai"
                test_paired_end_markduplicates_sorted_referencesn_txt   = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test.paired_end.markduplicates.sorted.referencesn.txt"
@ -137,6 +138,7 @@ params {

                test2_paired_end_sorted_bam                    = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam"
                test2_paired_end_sorted_bam_bai                = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam.bai"
+                test2_paired_end_name_sorted_bam               = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.name.sorted.bam"
                test2_paired_end_markduplicates_sorted_bam     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam"
                test2_paired_end_markduplicates_sorted_bam_bai = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.markduplicates.sorted.bam.bai"
                test2_paired_end_recalibrated_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test2.paired_end.recalibrated.sorted.bam"
--- a/tests/modules/genrich/main.nf
+++ b/tests/modules/genrich/main.nf
@ -0,0 +1,44 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GENRICH } from '../../../modules/genrich/main.nf' addParams( control_bam: false, pvalues: false, pileup:false, bed:false, blacklist_bed:false, save_duplicates:false, options: ["args": "-p 0.1"] )
+include { GENRICH as GENRICH_BLACKLIST   } from '../../../modules/genrich/main.nf' addParams( control_bam: false, pvalues: false, pileup:false, bed:false, blacklist_bed:true, save_duplicates:false, options: ["args": "-p 0.1"] )
+include { GENRICH as GENRICH_ALL_OUTPUTS } from '../../../modules/genrich/main.nf' addParams( control_bam: false, pvalues: true, pileup:true, bed:true, blacklist_bed:false, save_duplicates:true, options: ["args": "-r -p 0.1"] )
+include { GENRICH as GENRICH_ATACSEQ     } from '../../../modules/genrich/main.nf' addParams( control_bam: false, pvalues: false, pileup:false, bed:false, blacklist_bed:false, save_duplicates:false, options: ["args": "-j -p 0.1"] )
+
+workflow test_genrich {
+    input     = [ [ id:'test', single_end:false ], // meta map
+                  [ file( params.test_data['homo_sapiens']['illumina']['test_paired_end_name_sorted_bam'], checkIfExists: true) ]]
+    control   = [ ]
+    blacklist = [ ]
+
+    GENRICH ( input, control, blacklist )
+}
+
+workflow test_genrich_ctrl {
+    input     = [ [ id:'test', single_end:false ], // meta map
+                  [ file( params.test_data['homo_sapiens']['illumina']['test_paired_end_name_sorted_bam'], checkIfExists: true) ]]
+    control   = [ file( params.test_data['homo_sapiens']['illumina']['test2_paired_end_name_sorted_bam'], checkIfExists: true) ]
+    blacklist = [ ]
+
+    GENRICH ( input, control, blacklist )
+}
+
+workflow test_genrich_all_outputs {
+    input     = [ [ id:'test', single_end:false ], // meta map
+                  [ file( params.test_data['homo_sapiens']['illumina']['test_paired_end_name_sorted_bam'], checkIfExists: true) ]]
+    control   = [ file( params.test_data['homo_sapiens']['illumina']['test2_paired_end_name_sorted_bam'], checkIfExists: true) ]
+    blacklist = [ ]
+
+    GENRICH_ALL_OUTPUTS ( input, control, blacklist )
+}
+
+workflow test_genrich_atacseq {
+    input     = [ [ id:'test', single_end:false ], // meta map
+                  [ file( params.test_data['homo_sapiens']['illumina']['test_paired_end_name_sorted_bam'], checkIfExists: true) ]]
+    control   = [ file( params.test_data['homo_sapiens']['illumina']['test2_paired_end_name_sorted_bam'], checkIfExists: true) ]
+    blacklist = [ ]
+
+    GENRICH_ATACSEQ ( input, control, blacklist )
+}
--- a/tests/modules/genrich/test.yml
+++ b/tests/modules/genrich/test.yml
@ -0,0 +1,39 @@
+- name: genrich test_genrich
+  command: nextflow run tests/modules/genrich -entry test_genrich -c tests/config/nextflow.config
+  tags:
+    - genrich
+  files:
+    - path: output/genrich/test.narrowPeak
+      md5sum: 6afabdd3f691c7c84c66ff8a23984681
+
+- name: genrich test_genrich_ctrl
+  command: nextflow run tests/modules/genrich -entry test_genrich_ctrl -c tests/config/nextflow.config
+  tags:
+    - genrich
+  files:
+    - path: output/genrich/test.narrowPeak
+      md5sum: 6afabdd3f691c7c84c66ff8a23984681
+
+- name: genrich test_genrich_all_outputs
+  command: nextflow run tests/modules/genrich -entry test_genrich_all_outputs -c tests/config/nextflow.config
+  tags:
+    - genrich
+  files:
+    - path: output/genrich/test.duplicates.txt
+      md5sum: a92893f905fd8b3751bc6a960fbfe7ba
+    - path: output/genrich/test.intervals.bed
+      md5sum: 52edf47e6641c0cc03f9cca7324f7eaa
+    - path: output/genrich/test.narrowPeak
+      md5sum: e45eb7d000387975050c2e85c164e5be
+    - path: output/genrich/test.pileup.bedGraph
+      md5sum: e4f7fa664cd4ed2cf3a1a3a9eb415e71
+    - path: output/genrich/test.pvalues.bedGraph
+      md5sum: 564859953704983393d4b7d6317060cd
+
+- name: genrich test_genrich_atacseq
+  command: nextflow run tests/modules/genrich -entry test_genrich_atacseq -c tests/config/nextflow.config
+  tags:
+    - genrich
+  files:
+    - path: output/genrich/test.narrowPeak
+      md5sum: ddea556b820f8be3695ffdf6c6f70aff