Merge branch 'master' into gatk4-mergevcfs

This commit is contained in:
Kevin Menden 2021-02-19 14:11:30 +01:00 committed by GitHub
commit 0202162b17
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
13 changed files with 397 additions and 0 deletions

8
.github/filters.yml vendored
View file

@ -132,6 +132,14 @@ gatk4_mergevcfs:
- software/gatk4/mergevcfs/** - software/gatk4/mergevcfs/**
- tests/software/gatk4/mergevcfs/** - tests/software/gatk4/mergevcfs/**
gatk4_bedtointervallist:
- software/gatk4/bedtointervallist/**
- tests/software/gatk4/bedtointervallist/**
gatk4_samtofastq:
- software/gatk4/samtofastq/**
- tests/software/gatk4/samtofastq/**
gffread: gffread:
- software/gffread/** - software/gffread/**
- tests/software/gffread/** - tests/software/gffread/**

View file

@ -0,0 +1,59 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

View file

@ -0,0 +1,41 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process GATK4_BEDTOINTERVALLIST {
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), publish_id:meta.id) }
conda (params.enable_conda ? 'bioconda::gatk4:4.1.9.0' : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container 'https://depot.galaxyproject.org/singularity/gatk4:4.1.9.0--py39_0'
} else {
container 'quay.io/biocontainers/gatk4:4.1.9.0--py39_0'
}
input:
tuple val(meta), path(bed)
path sequence_dict
output:
tuple val(meta), path('*.interval_list'), emit: interval_list
path '*.version.txt' , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}"
"""
gatk BedToIntervalList \\
-I $bed \\
-SD $sequence_dict \\
-O ${prefix}.interval_list \\
$options.args
gatk --version | grep Picard | sed "s/Picard Version: //g" > ${software}.version.txt
"""
}

View file

@ -0,0 +1,60 @@
name: gatk4_bedtointervallist
description: Creates an interval list from a bed file and a reference dict
keywords:
- bed
- interval list
tools:
- gatk4:
description: |
Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
with a primary focus on variant discovery and genotyping. Its powerful processing engine
and high-performance computing features make it capable of taking on projects of any size.
homepage: https://gatk.broadinstitute.org/hc/en-us
documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
doi: 10.1158/1538-7445.AM2017-3590
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
- singularity_pull_docker_container:
type: boolean
description: |
Instead of directly downloading Singularity images for use with Singularity,
force the workflow to pull and convert Docker containers instead.
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test']
- bed:
type: file
description: Input bed file
pattern: "*.bed"
- dict:
type: file
description: Sequence dictionary
pattern: "*.dict"
output:
- interval_list:
type: file
description: gatk interval list file
pattern: "*.interval_list"
- version:
type: file
description: File containing software version
pattern: "*.version.txt"
authors:
- "@kevinmenden"

View file

@ -0,0 +1,59 @@
/*
* -----------------------------------------------------
* Utility functions used in nf-core DSL2 module files
* -----------------------------------------------------
*/
/*
* Extract name of software tool from process name using $task.process
*/
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
/*
* Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
*/
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.publish_by_id = args.publish_by_id ?: false
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
/*
* Tidy up and join elements of a list to return a path string
*/
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
/*
* Function to save/publish module results
*/
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_id) {
path_list.add(args.publish_id)
}
if (ioptions.publish_files instanceof Map) {
for (ext in ioptions.publish_files) {
if (args.filename.endsWith(ext.key)) {
def ext_list = path_list.collect()
ext_list.add(ext.value)
return "${getPathFromList(ext_list)}/$args.filename"
}
}
} else if (ioptions.publish_files == null) {
return "${getPathFromList(path_list)}/$args.filename"
}
}
}

View file

@ -0,0 +1,40 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
process GATK4_SAMTOFASTQ {
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), publish_id:meta.id) }
conda (params.enable_conda ? 'bioconda::gatk4:4.1.9.0' : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container 'https://depot.galaxyproject.org/singularity/gatk4:4.1.9.0--py39_0'
} else {
container 'quay.io/biocontainers/gatk4:4.1.9.0--py39_0'
}
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path('*.fastq.gz') , emit: fastq
path '*.version.txt' , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}.${options.suffix}" : "${meta.id}"
def output = meta.single_end ? "FASTQ=${prefix}.fastq.gz" : "FASTQ=${prefix}_1.fastq.gz SECOND_END_FASTQ=${prefix}_2.fastq.gz"
"""
gatk SamToFastq \\
I=$bam \\
$output \\
$options.args
gatk --version | grep Picard | sed "s/Picard Version: //g" > ${software}.version.txt
"""
}

View file

@ -0,0 +1,56 @@
name: gatk4_samtofastq
description: Converts BAM/SAM file to FastQ format
keywords:
- bed
- interval list
tools:
- gatk4:
description: |
Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
with a primary focus on variant discovery and genotyping. Its powerful processing engine
and high-performance computing features make it capable of taking on projects of any size.
homepage: https://gatk.broadinstitute.org/hc/en-us
documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
doi: 10.1158/1538-7445.AM2017-3590
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
- singularity_pull_docker_container:
type: boolean
description: |
Instead of directly downloading Singularity images for use with Singularity,
force the workflow to pull and convert Docker containers instead.
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test']
- bam:
type: file
description: Input SAM/BAM file
pattern: "*.{bam,sam}"
output:
- fastq:
type: file
description: converted fastq file
pattern: "*.fastq"
- version:
type: file
description: File containing software version
pattern: "*.version.txt"
authors:
- "@kevinmenden"

View file

@ -0,0 +1,4 @@
MT192765.1 1242 1264 nCoV-2019_5_LEFT 1 +
MT192765.1 1623 1651 nCoV-2019_5_RIGHT 1 -
MT192765.1 1573 1595 nCoV-2019_6_LEFT 2 +
MT192765.1 1942 1964 nCoV-2019_6_RIGHT 2 -

View file

@ -0,0 +1,2 @@
@HD VN:1.6
@SQ SN:MT192765.1 LN:29829 M5:c95f3e5592d0ad9974e41e7f0ea14eb0 UR:file:/Users/kevin/Documents/nfcore/modules/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.fna

View file

@ -0,0 +1,16 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { GATK4_BEDTOINTERVALLIST } from '../../../../software/gatk4/bedtointervallist/main.nf' addParams( options: [:] )
workflow test_gatk4_bedtointervallist {
def input = []
input = [ [ id:'test' ], // meta map
[ file("${launchDir}/tests/data/bed/sarscov2.bed", checkIfExists: true)] ]
sd = file("${launchDir}/tests/data/fasta/sarscov2/GCA_011545545.1_ASM1154554v1_genomic.dict", checkIfExists: true)
GATK4_BEDTOINTERVALLIST ( input, sd )
}

View file

@ -0,0 +1,8 @@
- name: gatk4 bedtointervallist
command: nextflow run ./tests/software/gatk4/bedtointervallist -entry test_gatk4_bedtointervallist -c tests/config/nextflow.config
tags:
- gatk4
- gatk4_bedtointervallist
files:
- path: output/gatk4/test.interval_list
md5sum: e51101c9357fb2d59fd30e370eefa39c

View file

@ -0,0 +1,23 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { GATK4_SAMTOFASTQ } from '../../../../software/gatk4/samtofastq/main.nf' addParams( options: [:] )
workflow test_gatk4_samtofastq_single_end {
def input = []
input = [ [ id:'test', single_end: true ], // meta map
[ file("${launchDir}/tests/data/bam/test.single_end.sorted.bam", checkIfExists: true)] ]
GATK4_SAMTOFASTQ ( input )
}
workflow test_gatk4_samtofastq_paired_end {
def input = []
input = [ [ id:'test', single_end: false ], // meta map
[ file("${launchDir}/tests/data/bam/test.single_end.sorted.bam", checkIfExists: true)] ]
GATK4_SAMTOFASTQ ( input )
}

View file

@ -0,0 +1,21 @@
- name: gatk4 samtofastq single-end
command: nextflow run ./tests/software/gatk4/samtofastq -entry test_gatk4_samtofastq_single_end -c tests/config/nextflow.config
tags:
- gatk4
- gatk4_samtofastq
- gatk4_samtofastq_single_end
files:
- path: output/gatk4/test.fastq.gz
md5sum: 61c6d3556ac6e0d09d800415b9a48508
- name: gatk4 samtofastq paired-end
command: nextflow run ./tests/software/gatk4/samtofastq -entry test_gatk4_samtofastq_paired_end -c tests/config/nextflow.config
tags:
- gatk4
- gatk4_samtofastq
- gatk4_samtofastq_paired_end
files:
- path: output/gatk4/test_1.fastq.gz
md5sum: 61c6d3556ac6e0d09d800415b9a48508
- path: output/gatk4/test_2.fastq.gz
md5sum: d0e74ab8dccca91c0ccd7125e588d5cd