refactored quast module

This commit is contained in:
kevinmenden 2021-02-01 13:13:21 +01:00
parent 956bf22a58
commit b5298f94d8
7 changed files with 31 additions and 172 deletions

View file

@ -21,7 +21,9 @@ process QUAST {
input: input:
path consensus path consensus
path fasta path fasta
val use_fasta
path gff path gff
val use_gff
output: output:
path "${prefix}" , emit: results path "${prefix}" , emit: results
@ -29,14 +31,15 @@ process QUAST {
path '*.version.txt', emit: version path '*.version.txt', emit: version
script: script:
def software = getSoftwareName(task.process) def software = getSoftwareName(task.process)
prefix = options.suffix ?: software prefix = options.suffix ?: software
def features = params.gff ? "--features $gff" : '' def features = use_gff ? "--features $gff" : ''
def reference = use_fasta ? "-r $fasta" : ''
""" """
quast.py \\ quast.py \\
--output-dir $prefix \\ --output-dir $prefix \\
-r $fasta \\ ${reference} \\
$features \\ ${features} \\
--threads $task.cpus \\ --threads $task.cpus \\
$options.args \\ $options.args \\
${consensus.join(' ')} ${consensus.join(' ')}

View file

@ -1,4 +1,4 @@
name: quast_reference name: quast
description: Quality Assessment Tool for Genome Assemblies description: Quality Assessment Tool for Genome Assemblies
keywords: keywords:
- quast - quast
@ -40,10 +40,16 @@ input:
- fasta: - fasta:
type: file type: file
description: | description: |
The genome assembly to be evaluated The genome assembly to be evaluated. Has to contain at least a non-empty string dummy value.
- use_fasta:
type: boolean
description: Whether to use a fasta reference
- gff: - gff:
type: file type: file
description: The genome GFF file description: The genome GFF file. Has to contain at least a non-empty string dummy value.
- use_gff:
type: boolean
description: Whether to use a gff reference
output: output:
- quast: - quast:

View file

@ -1,41 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process QUAST {
tag "$fasta"
label 'process_medium'
publishDir "${params.outdir}",
mode: params.publish_dir_mode,
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:'') }
conda (params.enable_conda ? 'bioconda::quast=5.0.2' : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container 'https://depot.galaxyproject.org/singularity/quast:5.0.2--py37pl526hb5aa323_2'
} else {
container 'quay.io/biocontainers/quast:5.0.2--py37pl526hb5aa323_2'
}
input:
path consensus
output:
path "${prefix}" , emit: results
path '*.tsv' , emit: tsv
path '*.version.txt', emit: version
script:
def software = getSoftwareName(task.process)
prefix = options.suffix ?: software
"""
quast.py \\
--output-dir $prefix \\
--threads $task.cpus \\
$options.args \\
$consensus
ln -s ${prefix}/report.tsv
echo \$(quast.py --version 2>&1) | sed 's/^.*QUAST v//; s/ .*\$//' > ${software}.version.txt
"""
}

View file

@ -1,55 +0,0 @@
name: quast
description: Quality Assessment Tool for Genome Assemblies
keywords:
- quast
- assembly
- quality
tools:
- quast:
description: |
QUAST calculates quality metrics for genome assemblies
homepage: http://bioinf.spbau.ru/quast
doi:
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:
- consensus:
type: file
description: |
Fasta file containing the assembly of interest
output:
- results:
type: file
description: The lineage report
pattern: "{prefix}.lineage_report.csv"
- tsv:
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
authors:
- "@drpatelh"
- "@kevinmenden"

View file

@ -1,59 +0,0 @@
/*
* -----------------------------------------------------
* 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"
}
}
}

View file

@ -2,19 +2,24 @@
nextflow.enable.dsl = 2 nextflow.enable.dsl = 2
include { QUAST as QUAST_NOREF } from '../../../software/quast/quast_noref/main.nf' addParams(options: [:]) include { QUAST } from '../../../software/quast/main.nf' addParams(options: [:])
include { QUAST as QUAST_REF } from '../../../software/quast/quast_ref/main.nf' addParams(options: [:])
workflow test_quast_noref {
consensus = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.fna", checkIfExists: true)
QUAST_NOREF( consensus )
}
workflow test_quast_ref { workflow test_quast_ref {
consensus = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_cds_from_genomic.fna", checkIfExists: true) consensus = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_cds_from_genomic.fna", checkIfExists: true)
gff = file("${launchDir}/tests/data/gff/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.gtf", checkIfExists: true) gff = file("${launchDir}/tests/data/gff/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.gtf", checkIfExists: true)
fasta = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.fna", checkIfExists: true) fasta = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.fna", checkIfExists: true)
def use_fasta = true
def use_gtf = true
QUAST_REF( consensus, fasta, gff ) QUAST( consensus, fasta, use_fasta, gff, use_gtf)
}
workflow test_quast_noref {
consensus = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_cds_from_genomic.fna", checkIfExists: true)
gff = file('gff_dummy')
fasta = file('fasta_dummy')
def use_fasta = false
def use_gtf = false
QUAST( consensus, fasta, use_fasta, gff, use_gtf)
} }