New last/lastdb module to index sequences before alignment. (#476)

* New last/lastdb module to index sequences before alignment.

The `lastdb` command creates a sequence index for the LAST aligner
(https://gitlab.com/mcfrith/last). Input can be in FASTA or FASTQ
format, and compression is handled automagically.  DNA or protein
sequences can be indexed.

The sequence index is a collection of files sharing the same basename.
This module sets the basename to the sample identifier (`$meta.id`) and
creates the index in a directory always called `lastdb`.  The module's
output channel then conveys a copy of the metadata and the path to the
`lastdb` directory.

Other modules will follow (see Issue #464).  The LAST aligner can align
proteins to proteins, DNA to DNA and can translate DNA align to
proteins.

* Remove trailing whitespace.

* Apply suggestions from code review

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

* Update as suggested in PR.

* Attempt to pass linting.

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

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
This commit is contained in:
Charles Plessy 2021-05-02 19:36:31 +09:00 committed by GitHub
parent f9433639cf
commit 16d20a7cc4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 220 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 +1,41 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
options = initOptions(params.options)
process LAST_LASTDB {
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), 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(fastx)
output:
tuple val(meta), path("lastdb"), emit: index
path "*.version.txt" , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
mkdir lastdb
lastdb \\
$options.args \\
-P $task.cpus \\
lastdb/${prefix} \\
$fastx
echo \$(lastdb --version 2>&1) | sed 's/lastdb //' > ${software}.version.txt
"""
}

View file

@ -0,0 +1,41 @@
name: last_lastdb
description: Prepare sequences for subsequent alignment with lastal.
keywords:
- LAST
- index
- fasta
- fastq
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/lastdb.rst
tool_dev_url: https://gitlab.com/mcfrith/last
doi: ""
licence: ['GPL-3.0-or-later']
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- fastx:
type: file
description: >
Sequence file in FASTA or FASTQ format.
May be compressed with gzip.
pattern: "*.{fasta,fasta.gz,fastq,fastq.gz}"
output:
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
- index:
type: directory
description: directory containing the files of the LAST index
pattern: "lastdb/"
authors:
- "@charles-plessy"

View file

@ -350,6 +350,10 @@ kraken2/run:
- software/untar/**
- tests/software/kraken2/run/**
last/lastdb:
- software/last/lastdb/**
- tests/software/last/lastdb/**
mash/sketch:
- software/mash/sketch/**
- tests/software/mash/sketch/**

View file

@ -0,0 +1,23 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { LAST_LASTDB } from '../../../../software/last/lastdb/main.nf' addParams( options: ['args': '-Q0'] )
workflow test_last_lastdb {
input = [ [ id:'test' ], // meta map
file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
]
LAST_LASTDB ( input )
}
workflow test_last_lastdb_gzipped_input {
input = [ [ id:'test' ], // meta map
file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
]
LAST_LASTDB ( input )
}

View file

@ -0,0 +1,41 @@
- name: last lastdb test_last_lastdb
command: nextflow run tests/software/last/lastdb -entry test_last_lastdb -c tests/config/nextflow.config
tags:
- last
- last/lastdb
files:
- path: output/last/lastdb/test.bck
md5sum: 5519879b9b6c4d1fc508da7f17f88f2e
- path: output/last/lastdb/test.des
md5sum: 3a9ea6d336e113a74d7fdca5e7b623fc
- path: output/last/lastdb/test.prj
md5sum: 489715f14b0fea6273822696e72357f9
- path: output/last/lastdb/test.sds
md5sum: 2cd381f4f8a9c52cfcd323a2863eccb2
- path: output/last/lastdb/test.ssp
md5sum: 4137fb6fe9df2b3d78d5b960390aac7b
- path: output/last/lastdb/test.suf
md5sum: 1895efa8653e8e9bd3605cff0408ed33
- path: output/last/lastdb/test.tis
md5sum: b7c40f06b1309dc6f37849eeb86dfd22
- name: last lastdb test_last_lastdb_gzipped_input
command: nextflow run tests/software/last/lastdb -entry test_last_lastdb_gzipped_input -c tests/config/nextflow.config
tags:
- last
- last/lastdb
files:
- path: output/last/lastdb/test.bck
md5sum: 8692b1229b1fff1c2d39c4c610ff842b
- path: output/last/lastdb/test.des
md5sum: 26ab49015cc572172b9efa50fc5190bc
- path: output/last/lastdb/test.prj
md5sum: a302beb8b8b884d8450055ede61e973b
- path: output/last/lastdb/test.sds
md5sum: cad9927d4bd161257e98165ad755d8e4
- path: output/last/lastdb/test.ssp
md5sum: 574c8a080247c2af9b5c46ff70936186
- path: output/last/lastdb/test.suf
md5sum: 8c406111b398631e51ca79d99b0ee897
- path: output/last/lastdb/test.tis
md5sum: d57a3a5f7e3e036807356c15bd3aad97