Merge pull request #123 from KevinMenden/cutadapt-module

Added cutadapt module
This commit is contained in:
Harshil Patel 2021-01-29 11:47:21 +00:00 committed by GitHub
commit adfb38aa62
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 255 additions and 0 deletions

40
.github/workflows/cutadapt.yml vendored Normal file
View file

@ -0,0 +1,40 @@
name: cutadapt
on:
push:
paths:
- software/cutadapt/**
- .github/workflows/cutadapt.yml
- tests/software/cutadapt/**
pull_request:
paths:
- software/cutadapt/**
- .github/workflows/cutadapt.yml
- tests/software/cutadapt/**
jobs:
ci_test:
runs-on: ubuntu-latest
strategy:
matrix:
nxf_version: [20.11.0-edge]
env:
NXF_ANSI_LOG: false
steps:
- uses: actions/checkout@v2
- name: Install Nextflow
env:
NXF_VER: ${{ matrix.nxf_version }}
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: "3.x"
- name: Install dependencies
run: python -m pip install --upgrade pip pytest-workflow
# Test the module
- run: pytest --tag cutadapt --symlink --wt 2

View file

@ -0,0 +1,59 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

42
software/cutadapt/main.nf Normal file
View file

@ -0,0 +1,42 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process CUTADAPT {
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), publish_id:meta.id) }
conda (params.enable_conda ? 'bioconda::cutadapt:3.2' : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container 'https://depot.galaxyproject.org/singularity/cutadapt:3.2--py38h0213d0e_0'
} else {
container 'quay.io/biocontainers/cutadapt:3.2--py38h0213d0e_0'
}
input:
tuple val(meta), path(reads)
output:
tuple val(meta), path('*.trim.fastq.gz'), emit: reads
tuple val(meta), path('*.log') , emit: log
path '*.version.txt' , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
def trimmed = meta.single_end ? "-o ${prefix}.trim.fastq.gz" : "-o ${prefix}_1.trim.fastq.gz -p ${prefix}_2.trim.fastq.gz"
"""
cutadapt \\
--cores $task.cpus \\
$options.args \\
$trimmed \\
$reads \\
> ${prefix}.cutadapt.log
echo \$(cutadapt --version) > ${software}.version.txt
"""
}

View file

@ -0,0 +1,66 @@
name: cutadapt
description: Perform adapter/quality trimming on sequencing reads
keywords:
- trimming
- adapter trimming
- adapters
- quality trimming
tools:
- cuatadapt:
description: |
Cutadapt finds and removes adapter sequences, primers, poly-A tails and other types of unwanted sequence from your high-throughput sequencing reads.
documentation: https://cutadapt.readthedocs.io/en/stable/index.html
doi: DOI:10.14806/ej.17.1.200
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
- singularity_pull_docker_container:
type: boolean
description: |
Instead of directly downloading Singularity images for use with Singularity,
force the workflow to pull and convert Docker containers instead.
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- reads:
type: file
description: |
List of input FastQ files of size 1 and 2 for single-end and paired-end data,
respectively.
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- reads:
type: file
description: The trimmed/modified fastq reads
pattern: "*fastq.gz"
- log:
type: file
description: cuatadapt log file
pattern: "*cutadapt.log"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
authors:
- "@drpatelh"
- "@kevinmenden"

View file

@ -0,0 +1,30 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { CUTADAPT } from '../../../software/cutadapt/main.nf' addParams( options: [ args:'-q 25' ] )
/*
* Test with single-end data
*/
workflow test_cutadapt_se {
def input = []
input = [ [ id:'test', single_end:true ], // meta map
[ file("${launchDir}/tests/data/fastq/rna/test_single_end.fastq.gz", checkIfExists: true) ] ]
CUTADAPT( input )
}
/*
* Test with paired-end data
*/
workflow test_cutadapt_pe {
def input = []
input = [ [ id:'test', single_end:false ], // meta map
[ file("${launchDir}/tests/data/fastq/rna/test_R1.fastq.gz", checkIfExists: true),
file("${launchDir}/tests/data/fastq/rna/test_R2.fastq.gz", checkIfExists: true) ] ]
CUTADAPT( input )
}

View file

@ -0,0 +1,18 @@
- name: Run cutadapt single-end test workflow
command: nextflow run ./tests/software/cutadapt -profile docker -entry test_cutadapt_se -c tests/config/nextflow.config
tags:
- cutadapt
- cutadapt_se
files:
- path: ./output/cutadapt/test.cutadapt.log
- path: ./output/cutadapt/test.trim.fastq.gz
- name: Run cutadapt paired-end test workflow
command: nextflow run ./tests/software/cutadapt -profile docker -entry test_cutadapt_pe -c tests/config/nextflow.config
tags:
- cutadapt
- cutadapt_pe
files:
- path: ./output/cutadapt/test.cutadapt.log
- path: ./output/cutadapt/test_1.trim.fastq.gz
- path: ./output/cutadapt/test_2.trim.fastq.gz