hifiasm copied from fastqc

This commit is contained in:
Sviatoslav Sidorov 2021-03-16 09:54:29 +00:00
parent 74ff11b07b
commit 38b450d0be
3 changed files with 178 additions and 0 deletions

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"
}
}
}

47
software/hifiasm/main.nf Normal file
View file

@ -0,0 +1,47 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
options = initOptions(params.options)
process FASTQC {
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::fastqc=0.11.9" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0"
} else {
container "quay.io/biocontainers/fastqc:0.11.9--0"
}
input:
tuple val(meta), path(reads)
output:
tuple val(meta), path("*.html"), emit: html
tuple val(meta), path("*.zip") , emit: zip
path "*.version.txt" , emit: version
script:
// Add soft-links to original FastQs for consistent naming in pipeline
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}"
if (meta.single_end) {
"""
[ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz
fastqc $options.args --threads $task.cpus ${prefix}.fastq.gz
fastqc --version | sed -e "s/FastQC v//g" > ${software}.version.txt
"""
} else {
"""
[ ! -f ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz
[ ! -f ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz
fastqc $options.args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz
fastqc --version | sed -e "s/FastQC v//g" > ${software}.version.txt
"""
}
}

72
software/hifiasm/meta.yml Normal file
View file

@ -0,0 +1,72 @@
name: fastqc
description: Run FastQC on sequenced reads
keywords:
- quality control
- qc
- adapters
- fastq
tools:
- fastqc:
description: |
FastQC gives general quality metrics about your reads.
It provides information about the quality score distribution
across your reads, the per base sequence content (%A/C/G/T).
You get information about adapter contamination and other
overrepresented sequences.
homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
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 ]
- html:
type: file
description: FastQC report
pattern: "*_{fastqc.html}"
- zip:
type: file
description: FastQC report archive
pattern: "*_{fastqc.zip}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
authors:
- "@drpatelh"
- "@grst"
- "@ewels"
- "@FelixKrueger"