New module: pbbam/pbmerge (#752)

* 👌 IMPROVE: Add some pacbio test files

* 📦 NEW: Add pbbam/pbmerge module

* 🐛 FIX: Add optional arguments to command line

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update test data config and test script

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Add some pacbio test files

* 📦 NEW: Add pbbam/pbmerge module

* 🐛 FIX: Add optional arguments to command line

* 👌 IMPROVE: Update to last templates version

* 👌 IMPROVE: Update module to last template version

* 👌 IMPROVE: Update test data config and test script

* 👌 IMPROVE: Remove useless index + Fix Typos

* 👌 IMPROVE: Update and clean code

* 🐛 FIX: Update module path in test

* 🐛 FIX: Add missing () + correct module path in test

* 👌 IMPROVE: Update pbmerge from version 1.6.0 to 1.7.0

* 👌 IMPROVE: Change output filename suffix for something more generic

* 🐛 Update test.yml

* Apply suggestions from code review

* Update tests/modules/pbbam/pbmerge/test.yml

* Update tests/modules/pbbam/pbmerge/main.nf

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>
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:
Sébastien Guizard 2021-10-05 23:16:45 +01:00 committed by GitHub
parent aa32a8a72e
commit bcf2681b03
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 198 additions and 0 deletions

View file

@ -0,0 +1,78 @@
//
// 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()
}
//
// Extract name of module from process name using $task.process
//
def getProcessName(task_process) {
return task_process.tokenize(':')[-1]
}
//
// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
//
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.args3 = args.args3 ?: ''
options.publish_by_meta = args.publish_by_meta ?: []
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
//
// Tidy up and join elements of a list to return a path string
//
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
//
// Function to save/publish module results
//
def saveFiles(Map args) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
// Do not publish versions.yml unless running from pytest workflow
if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
return null
}
if (ioptions.publish_by_meta) {
def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
for (key in key_list) {
if (args.meta && key instanceof String) {
def path = key
if (args.meta.containsKey(key)) {
path = args.meta[key] instanceof Boolean ? "${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 +1,42 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
params.options = [:]
options = initOptions(params.options)
process PBBAM_PBMERGE {
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::pbbam=1.7.0" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/pbbam:1.7.0--h058f120_1"
} else {
container "quay.io/biocontainers/pbbam:1.7.0--h058f120_1"
}
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path("*.bam"), emit: bam
tuple val(meta), path("*.pbi"), emit: pbi
path "versions.yml" , emit: versions
script:
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
pbmerge \\
-o ${prefix}.bam \\
$options.args \\
*.bam
cat <<-END_VERSIONS > versions.yml
${getProcessName(task.process)}:
pbbam/pbmerge: \$( pbmerge --version|sed 's/pbmerge //' )
END_VERSIONS
"""
}

View file

@ -0,0 +1,46 @@
name: pbbam_pbmerge
description: The pbbam software package provides components to create, query, & edit PacBio BAM files and associated indices. These components include a core C++ library, bindings for additional languages, and command-line utilities.
keywords:
- pbbam
- pbbam/pbmerge
tools:
- pbbam:
description: PacBio BAM C++ library
homepage: https://github.com/PacificBiosciences/pbbioconda
documentation: https://pbbam.readthedocs.io/en/latest/tools/pbmerge.html
tool_dev_url: https://github.com/pacificbiosciences/pbbam/
doi: ""
licence: ['BSD-3-clause-Clear']
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: BAM files to merge
pattern: "*.bam"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- bam:
type: file
description: The merged bam file
pattern: "*.bam"
- pbi:
type: file
description: BAM Pacbio index file
pattern: "*.bam.pbi"
authors:
- "@sguizard"

View file

@ -731,6 +731,10 @@ pangolin:
- modules/pangolin/** - modules/pangolin/**
- tests/modules/pangolin/** - tests/modules/pangolin/**
pbbam/pbmerge:
- modules/pbbam/pbmerge/**
- tests/modules/pbbam/pbmerge/**
pbccs: pbccs:
- modules/pbccs/** - modules/pbccs/**
- tests/modules/pbccs/** - tests/modules/pbccs/**

View file

@ -0,0 +1,18 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { PBBAM_PBMERGE } from '../../../../modules/pbbam/pbmerge/main.nf' addParams( options: [suffix: '.merged'] )
workflow test_pbbam_pbmerge {
input = [
[ id:'test' ], // meta map
[
file(params.test_data['homo_sapiens']['pacbio']['cluster'] , checkIfExists: true),
file(params.test_data['homo_sapiens']['pacbio']['singletons'], checkIfExists: true)
]
]
PBBAM_PBMERGE ( input )
}

View file

@ -0,0 +1,10 @@
- name: pbbam pbmerge test_pbbam_pbmerge
command: nextflow run tests/modules/pbbam/pbmerge -entry test_pbbam_pbmerge -c tests/config/nextflow.config
tags:
- pbbam/pbmerge
- pbbam
files:
- path: output/pbbam/test.merged.bam
md5sum: 727c7ba1289192085c06890dda70f973
- path: output/pbbam/test.merged.bam.pbi
md5sum: edfadd3a81c598d1ee051899792db75d