Add module kallisto/index (#357)

* add kallisto index module

* update kallisto module

* add kallisto module tests

* update kallisto index test.yml

* update test data paths

* fix version

* fix kallisto index test yml

* remove TODOs

* Update software/kallisto/index/main.nf

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

* Update software/kallisto/index/main.nf

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

* output folder instead

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
This commit is contained in:
Gisela Gabernet 2021-03-24 13:25:39 +01:00 committed by GitHub
parent acb1a12a56
commit 22eaefe583
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 155 additions and 0 deletions

View file

@ -0,0 +1,60 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.args3 = args.args3 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

View file

@ -0,0 +1,39 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
options = initOptions(params.options)
process KALLISTO_INDEX {
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::kallisto=0.46.2" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/kallisto:0.46.2--h4f7b962_1"
} else {
container "quay.io/biocontainers/kallisto:0.46.2--h4f7b962_1"
}
input:
path fasta
output:
path "kallisto" , emit: idx
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
"""
kallisto \\
index \\
$options.args \\
-i kallisto \\
$fasta
echo \$(kallisto 2>&1) | sed 's/^kallisto //; s/Usage.*\$//' > ${software}.version.txt
"""
}

View file

@ -0,0 +1,31 @@
name: kallisto_index
description: write your description here
keywords:
- sort
tools:
- kallisto:
description: Quantifying abundances of transcripts from bulk and single-cell RNA-Seq data, or more generally of target sequences using high-throughput sequencing reads.
homepage: https://pachterlab.github.io/kallisto/
documentation: https://pachterlab.github.io/kallisto/manual
tool_dev_url: https://github.com/pachterlab/kallisto
doi: ""
licence: ['BSD_2_clause']
input:
- fasta:
type: file
description: genome fasta file
pattern: "*.{fasta}"
output:
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
- idx:
type: index
description: Kallisto genome index
pattern: "*.idx"
authors:
- "@ggabernet"

View file

@ -250,6 +250,10 @@ ivar_variants:
- software/ivar/variants/**
- tests/software/ivar/variants/**
kallisto_index:
- software/kallisto/index/**
- tests/software/kallisto/index/**
kraken2_run:
- software/kraken2/run/**
- tests/software/kraken2/run/**

View file

@ -0,0 +1,13 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { KALLISTO_INDEX } from '../../../../software/kallisto/index/main.nf' addParams( options: [:] )
workflow test_kallisto_index {
def input = []
input = file("${launchDir}/tests/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
KALLISTO_INDEX ( input )
}

View file

@ -0,0 +1,8 @@
- name: kallisto index test_kallisto_index
command: nextflow run tests/software/kallisto/index -entry test_kallisto_index -c tests/config/nextflow.config
tags:
- kallisto
- kallisto_index
files:
- path: output/kallisto/kallisto
md5sum: bf8a58d329dddc96f0c32f7823bc0310