Add module: dedup (#907)

* Specify more guidelines on input channels

* Linting

* Updates based on code review

* Update README.md

* Fix broken sentence

* feat: add megahit module, currently decompressed output

* Update main.nf

* Update tests/modules/megahit/test.yml

Co-authored-by: Maxime Borry <maxibor@users.noreply.github.com>

* Apply suggestions from code review

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

* feat: compress all outputs, remove md5sums due to gz stochasicity

* fix: wrong conda channel for pigz

* fix: broken singleend tests and update meta.yml

* Missed one

* Apply suggestions from code review

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

* fix: pigz formatting

* Apply suggestions from code review

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

* Apply suggestions from code review

* Add dedup (tests and version not working)

* Fix dedup and tests

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
Co-authored-by: Maxime Borry <maxibor@users.noreply.github.com>
This commit is contained in:
James A. Fellows Yates 2021-10-28 12:10:21 +02:00 committed by GitHub
parent a0bc08732c
commit e27553b989
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 215 additions and 0 deletions

View file

@ -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"
}
}

47
modules/dedup/main.nf Normal file
View file

@ -0,0 +1,47 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
params.options = [:]
options = initOptions(params.options)
process DEDUP {
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::dedup=0.12.8" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/dedup:0.12.8--hdfd78af_1"
} else {
container "quay.io/biocontainers/dedup:0.12.8--hdfd78af_1"
}
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path("*_rmdup.bam"), emit: bam // _rmdup is hardcoded output from dedup
tuple val(meta), path("*.json") , emit: json
tuple val(meta), path("*.hist") , emit: hist
tuple val(meta), path("*log") , emit: log
path "versions.yml" , emit: versions
script:
prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
dedup \\
-Xmx${task.memory.toGiga()}g \\
-i $bam \\
-o . \\
$options.args
cat <<-END_VERSIONS > versions.yml
${getProcessName(task.process)}:
${getSoftwareName(task.process)}: \$( echo \$(dedup --version 2>&1) | tail -n 1 | sed 's/.* v//')
END_VERSIONS
"""
}

60
modules/dedup/meta.yml Normal file
View file

@ -0,0 +1,60 @@
name: dedup
description: DeDup is a tool for read deduplication in paired-end read merging (e.g. for ancient DNA experiments).
keywords:
- dedup
- deduplication
- pcr duplicates
- ancient DNA
- paired-end
- bam
tools:
- dedup:
description: DeDup is a tool for read deduplication in paired-end read merging (e.g. for ancient DNA experiments).
homepage: https://github.com/apeltzer/DeDup
documentation: https://dedup.readthedocs.io/en/latest/
tool_dev_url: https://github.com/apeltzer/DeDup
doi: "10.1186/s13059-016-0918-z"
licence: ['GPL v3']
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: BAM/SAM file
pattern: "*.{bam,sam}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- bam:
type: file
description: Deduplicated BAM file
pattern: "*_rmdup.bam"
- json:
type: file
description: JSON file for MultiQC
pattern: "*.json"
- hist:
type: file
description: Histogram data of amount of deduplication
pattern: "*.hist"
- log:
type: file
description: Dedup log information
pattern: "*log"
authors:
- "@jfy133"

View file

@ -294,6 +294,10 @@ damageprofiler:
- modules/damageprofiler/**
- tests/modules/damageprofiler/**
dedup:
- modules/dedup/**
- tests/modules/dedup/**
deeptools/computematrix:
- modules/deeptools/computematrix/**
- tests/modules/deeptools/computematrix/**

View file

@ -0,0 +1,13 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { DEDUP } from '../../../modules/dedup/main.nf' addParams( options: [args: "-m"] )
workflow test_dedup {
input = [ [ id:'test', single_end:false ], // meta map
file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ]
DEDUP ( input )
}

View file

@ -0,0 +1,13 @@
- name: dedup test_dedup
command: nextflow run tests/modules/dedup -entry test_dedup -c tests/config/nextflow.config
tags:
- dedup
files:
- path: output/dedup/test.paired_end.dedup.json
md5sum: 2def0b54aba1fafa21b274f260de1b6f
- path: output/dedup/test.paired_end.hist
md5sum: df3492273a1db0d8152e35d9d5e38aa6
- path: output/dedup/test.paired_end.log
md5sum: 4b8855bd63b2f4b37da4cfb17e61fb00
- path: output/dedup/test.paired_end_rmdup.bam
md5sum: 8b0408fe3e258989095303a47e5b5061