Add module kleborate (#711)

* initial commit [ci skip]

* remove todo from the module files [ci skip]

* add a sample test case [ci skip]

* push the latest work [ci skip]

* bump kleborate build

* test passing with the new build for kleborate [ci skip]

* ready for review

* Apply suggestions from code review

Co-authored-by: Robert A. Petit III <robbie.petit@gmail.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
This commit is contained in:
Abhinav Sharma 2021-09-21 21:45:42 +02:00 committed by GitHub
parent 8e9d6cd5e4
commit 77a2895785
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 179 additions and 0 deletions

View file

@ -0,0 +1,68 @@
//
// 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"
}
}
}

39
modules/kleborate/main.nf Normal file
View file

@ -0,0 +1,39 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
options = initOptions(params.options)
process KLEBORATE {
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::kleborate=2.1.0" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/kleborate:2.1.0--pyhdfd78af_1"
} else {
container "quay.io/biocontainers/kleborate:2.1.0--pyhdfd78af_1"
}
input:
tuple val(meta), path(fastas)
output:
tuple val(meta), path("*.txt"), emit: txt
path "*.version.txt" , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
kleborate \\
$options.args \\
--outfile ${prefix}.results.txt \\
--assemblies *.fasta
echo \$(kleborate -v 2>&1) | sed 's/kleborate //;' > ${software}.version.txt
"""
}

View file

@ -0,0 +1,43 @@
name: kleborate
description: Kleborate is a tool to screen genome assemblies of Klebsiella pneumoniae and the Klebsiella pneumoniae species complex (KpSC).
keywords:
- screening assemblies
- Klebsiella pneumoniae
tools:
- kleborate:
description: Screening Klebsiella genome assemblies for MLST, sub-species, and other Klebsiella related genes of interest
homepage: https://github.com/katholt/Kleborate
documentation: https://github.com/katholt/Kleborate/wiki
tool_dev_url: https://github.com/katholt/Kleborate
doi: 10.1038/s41467-021-24448-3
licence: ['GPL v3 or later (GPL v3+)']
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- fastas:
type: files
description: Klebsiella genome assemblies to be screened
pattern: "*.fasta"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
- txt:
type: file
description: Result file generated after screening
pattern: "*.txt"
authors:
- "@abhi18av"
- "@rpetit3"

View file

@ -505,6 +505,10 @@ kallistobustools/ref:
- modules/kallistobustools/ref/**
- tests/modules/kallistobustools/ref/**
kleborate:
- modules/kleborate/**
- tests/modules/kleborate/**
kraken2/kraken2:
- modules/kraken2/kraken2/**
- modules/untar/**

View file

@ -0,0 +1,18 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { KLEBORATE } from '../../../modules/kleborate/main.nf' addParams( options: [:] )
workflow test_kleborate {
input = [
[ id:'test', single_end:false ], // meta map
[ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),
file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true),
file(params.test_data['sarscov2']['illumina']['scaffolds_fasta'], checkIfExists: true)
]
]
KLEBORATE ( input )
}

View file

@ -0,0 +1,7 @@
- name: kleborate
command: nextflow run ./tests/modules/kleborate -entry test_kleborate -c tests/config/nextflow.config
tags:
- kleborate
files:
- path: output/kleborate/test.results.txt
md5sum: b7979a71170736098fb8403cd92748f5