New module last/postmask to filter alignment files (#526)

The `last-postmask` tool distributed with [LAST](https://gitlab.com/mcfrith/last)
filters alignments in a MAF file to remove those with too many masked
(lower-case) positions compared with their score.

As other filter modules like `last/split`, its output file risks to
overwrite its input file as their names are constructed from the sample
ID when multiple filters are chained in the pipeline.  I added a check
that gives a clearer error message in this case.  Please let me know
what you think about; I can add this test to the existing LAST modules
as well.

This new module is part of the work discribed in Issue #464. During this
development, we fix the version of LAST to 1219 to ensure consistency.
We will upgrade it later.
This commit is contained in:
Charles Plessy 2021-06-08 18:14:08 +09:00 committed by GitHub
parent f7ebc2fc48
commit ca321ce69d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 172 additions and 0 deletions

View file

@ -0,0 +1,70 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.args3 = args.args3 ?: ''
options.publish_by_meta = args.publish_by_meta ?: []
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_meta) {
def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
for (key in key_list) {
if (args.meta && key instanceof String) {
def path = key
if (args.meta.containsKey(key)) {
path = args.meta[key] instanceof Boolean ? "${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"
}
}
}

View file

@ -0,0 +1,38 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
options = initOptions(params.options)
process LAST_POSTMASK {
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::last=1219" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/last:1219--h2e03b76_0"
} else {
container "quay.io/biocontainers/last:1219--h2e03b76_0"
}
input:
tuple val(meta), path(maf)
output:
tuple val(meta), path("*.maf.gz"), emit: maf
path "*.version.txt" , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
if( "$maf" == "${prefix}.maf.gz" ) error "Input and output names are the same, use the suffix option to disambiguate"
"""
zcat $maf | last-postmask $options.args | gzip --no-name > ${prefix}.maf.gz
# last-postmask does not have a --version option
echo \$(lastal --version 2>&1) | sed 's/lastal //' > ${software}.version.txt
"""
}

View file

@ -0,0 +1,39 @@
name: last_postmask
description: Post-alignment masking
keywords:
- LAST
- mask
- alignment
- MAF
tools:
- last:
description: LAST finds & aligns related regions of sequences.
homepage: https://gitlab.com/mcfrith/last
documentation: https://gitlab.com/mcfrith/last/-/blob/main/doc/last-postmask.rst
tool_dev_url: https://gitlab.com/mcfrith/last
doi: "10.1371/journal.pone.0028819"
licence: ['GPL-3.0-or-later']
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- maf:
type: file
description: Multiple Aligment Format (MAF) file, compressed with gzip
pattern: "*.{maf.gz}"
output:
- maf:
type: file
description: Multiple Aligment Format (MAF) file, compressed with gzip
pattern: "*.{maf.gz}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
authors:
- "@charles-plessy"

View file

@ -394,6 +394,10 @@ last/mafswap:
- software/last/mafswap/** - software/last/mafswap/**
- tests/software/last/mafswap/** - tests/software/last/mafswap/**
last/postmask:
- software/last/postmask/**
- tests/software/last/postmask/**
last/split: last/split:
- software/last/split/** - software/last/split/**
- tests/software/last/split/** - tests/software/last/split/**

View file

@ -0,0 +1,13 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { LAST_POSTMASK } from '../../../../software/last/postmask/main.nf' addParams( options: [suffix:'.postmask'] )
workflow test_last_postmask {
input = [ [ id:'contigs.genome' ], // meta map
file(params.test_data['sarscov2']['genome']['contigs_genome_maf_gz'], checkIfExists: true) ]
LAST_POSTMASK ( input )
}

View file

@ -0,0 +1,8 @@
- name: last postmask test_last_postmask
command: nextflow run tests/software/last/postmask -entry test_last_postmask -c tests/config/nextflow.config
tags:
- last
- last/postmask
files:
- path: output/last/contigs.genome.postmask.maf.gz
md5sum: 3a0f42e76da9549748983ac4d7ff7473