Removed extraneous modules and updated removegenes module

This commit is contained in:
Sruthi Suresh 2020-11-11 12:53:26 -06:00 committed by sruthipsuresh
parent 1426d89440
commit 637b545168
14 changed files with 8 additions and 463 deletions

View file

@ -1,59 +0,0 @@
/*
* -----------------------------------------------------
* 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

@ -1,41 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
def VERSION = '2.29'
process BEDTOOLS_FIXBEDCOORDINATES {
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::bedtools =2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
} else {
container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
}
input:
tuple val(meta), path("*.sloprefseq.bed")
output:
tuple val(meta), path("*.sloprefseqsorted.bed"), emit: bed
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
// sorted via chromosome, then by start position
"""
awk -F '\\t' 'length($1) <= 5 {{ print }}' ${prefix}.sloprefseq.bed |
awk '{{ if ($2 > $3) {{ t = $2; $2 = $3; $3 = t; }} \
else if ($2 == $3) {{ $3 += 1; }} print $0; }}' OFS='\\t' - \
| sort-bed > ${prefix}.sloprefseqsorted.bed
echo $VERSION > ${software}.version.txt
"""
}

View file

@ -1,55 +0,0 @@
name: bedtools_fixbedcoordinates
description: Removes chrXYZ_random entries in hg18, fixes alignments if start is after the end and
sorts the entries
keywords:
- bed
- length
- sort
tools:
- bedtools:
description: |
A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
documentation: https://bedtools.readthedocs.io/en/latest/
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
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: List of bed files
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"

View file

@ -4,9 +4,7 @@ include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
def VERSION = '4.11'
process BEDTOOLS_SLOPEREFSEQ {
process BEDTOOLS_REMOVEGENES {
tag "$meta.id"
label 'process_medium'
publishDir "${params.outdir}",
@ -21,11 +19,11 @@ process BEDTOOLS_SLOPEREFSEQ {
}
input:
path metatranscripts
tuple val(meta), path("*.sloprefseqsorted.bed")
tuple val(meta), path(slopbed)
path metatranscript
output:
tuple val(meta), path("*.nogenes.bed"), emit: bed
tuple val(meta), path("*.nogenes.bed"), emit: nogenesbed
path "*.version.txt", emit: version
script:
@ -33,8 +31,8 @@ process BEDTOOLS_SLOPEREFSEQ {
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
// sorted via chromosome, then by start position
"""
bedtools intersect -a $metatranscripts -b ${prefix}.sloprefseqsorted.bed -v \\
sort -k1,1 -k2,2n > {prefix}.nogenes.bed
echo $VERSION > ${software}.version.txt
bedtools intersect -a $metatranscript -b $slopbed -v \\
| sortBed > ${prefix}.nogenes.bed
bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
"""
}

View file

@ -1,5 +1,5 @@
name: bedtools_removegenes
description: Adds 1 KB to the front of the genes and 10 KB to the end of the sequence.
description: Removes the intergenic regions from GRO-Seq Transcripts
keywords:

View file

@ -1,39 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
def VERSION = '4.11'
process BEDTOOLS_SLOPEREFSEQ {
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::bedtools =2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
} else {
container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
}
input:
path sizes
tuple val(meta), path(beds)
output:
tuple val(meta), path("*.sloprefseq.bed"), emit: bed
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
def beds_files = beds.sort()
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
slopBed -i $beds -g $sizes -l ${params.upstream} -r {params.downstream} > ${prefix}.sloprefseq.bed
echo $VERSION > ${software}.version.txt
"""
}

View file

@ -1,55 +0,0 @@
name: bedtools_sloperefseq
description: Adds 1 KB to the front of the genes and 10 KB to the end of the sequence.
keywords:
- bed
- slopBed
- downstream
- upstream
tools:
- bedtools:
description: |
A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
documentation: https://bedtools.readthedocs.io/en/latest/
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
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: List of bed files
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"

View file

@ -1,59 +0,0 @@
/*
* -----------------------------------------------------
* 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

@ -1,39 +0,0 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [upstream: 1,
downstream: 10 ]
def options = initOptions(params.options)
process BEDTOOLS_SLOPREFSEQ {
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::bedtools =2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/bedtools:2.29.2--hc088bd4_0 "
} else {
container "quay.io/biocontainers/bedtools:2.29.2--hc088bd4_0"
}
input:
tuple val(meta), path(beds)
path sizes
output:
tuple val(meta), path("*.sloprefseq.bed"), emit: bed
path "*.version.txt", emit: version
script:
def software = getSoftwareName(task.process)
def beds_files = beds.sort()
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
slopBed -i ln -s ${beds[0]} -g ln -s $sizes -l ${params.upstream} -r ${params.downstream} > ${prefix}.sloprefseq.bed
bedtools --version | sed -e "s/Bedtools v//g" > ${software}.version.txt
"""
}

View file

@ -1,55 +0,0 @@
name: bedtools_sloperefseq
description: Adds 1 KB to the front of the genes and 10 KB to the end of the sequence.
keywords:
- bed
- slopBed
- downstream
- upstream
tools:
- bedtools:
description: |
A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
documentation: https://bedtools.readthedocs.io/en/latest/
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
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: List of bed files
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Edited bed file
pattern: "*.{bed}"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"

View file

@ -1,5 +0,0 @@
chr1 951 1061
chr1 1300 1420
chr1 1400 1500

View file

@ -1 +0,0 @@
chr1 1780869

View file

@ -1,25 +0,0 @@
#!/usr/bin/env nextflow
nextflow.preview.dsl = 2
include { BEDTOOLS_SLOPREFSEQ } from '../../sloprefseq/main.nf' addParams( options: [publish_dir:'test_bed_file'])
// Define input channels
// Run the workflow
workflow test_bed_file{
def input = []
input = [ [ id:'test', single_end:true ],
[ file("${baseDir}/input/A.bed", checkIfExists: true),] ]
BEDTOOLS_SLOPREFSEQ (
input,
file("${baseDir}/input/genome.sizes", checkIfExists: true)
)
}
workflow {
test_bed_file()
}

View file

@ -1,20 +0,0 @@
params {
outdir = "output/"
publish_dir_mode = "copy"
enable_conda = false
}
profiles {
conda {
params.enable_conda = true
}
docker {
docker.enabled = true
docker.runOptions = '-u \$(id -u):\$(id -g)'
}
singularity {
singularity.enabled = true
singularity.autoMounts = true
}
}