Merge pull request #110 from luslab/master

Add SEACR module containing a single CALLPEAK process
This commit is contained in:
Harshil Patel 2021-02-01 09:48:15 +00:00 committed by GitHub
commit 2c962f34df
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
10 changed files with 22924 additions and 3 deletions

40
.github/workflows/seacr_callpeak.yml vendored Normal file
View file

@ -0,0 +1,40 @@
name: seacr_callpeak
on:
push:
paths:
- software/seacr/callpeak/**
- .github/workflows/seacr_callpeak.yml
- tests/software/seacr/**
pull_request:
paths:
- software/seacr/callpeak/**
- .github/workflows/seacr_callpeak.yml
- tests/software/seacr/**
jobs:
ci_test:
runs-on: ubuntu-latest
strategy:
matrix:
nxf_version: [20.11.0-edge]
env:
NXF_ANSI_LOG: false
steps:
- uses: actions/checkout@v2
- name: Install Nextflow
env:
NXF_VER: ${{ matrix.nxf_version }}
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: "3.x"
- name: Install dependencies
run: python -m pip install --upgrade pip pytest-workflow
# Test the module
- run: pytest --tag seacr_callpeak --symlink --wt 2

1
.gitignore vendored
View file

@ -2,5 +2,6 @@
work/ work/
results/ results/
test_output/ test_output/
output/
.DS_Store .DS_Store
*.code-workspace *.code-workspace

3
.gitmodules vendored
View file

@ -1,3 +0,0 @@
[submodule "test-datasets"]
path = test-datasets
url = https://github.com/nf-core/test-datasets.git

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 +1,42 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
def options = initOptions(params.options)
def VERSION = '1.3'
process SEACR_CALLPEAK {
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::seacr=1.3 conda-forge::r-base=4.0.2 bioconda::bedtools=2.29.2" : null)
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/mulled-v2-03bfeb32fe80910c231f630d4262b83677c8c0f4:5bb5ed4307a8187a7f34730b00431de93688fa59-0"
} else {
container 'quay.io/biocontainers/mulled-v2-03bfeb32fe80910c231f630d4262b83677c8c0f4:5bb5ed4307a8187a7f34730b00431de93688fa59-0'
}
input:
tuple val(meta), path(bedgraph), path(ctrlbedgraph)
output:
tuple val(meta), path("*.bed"), emit: bed
path "*.version.txt" , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
"""
SEACR_1.3.sh \\
$bedgraph \\
$ctrlbedgraph \\
$options.args \\
$prefix
echo $VERSION > ${software}.version.txt
"""
}

View file

@ -0,0 +1,69 @@
name: seacr_callpeak
description: Call peaks using SEACR on sequenced reads in bedgraph format
keywords:
- peak-caller
- peaks
- bedgraph
- cut&tag
- cut&run
- chromatin
- seacr
tools:
- seacr:
description: |
SEACR is intended to call peaks and enriched regions from sparse CUT&RUN
or chromatin profiling data in which background is dominated by "zeroes"
(i.e. regions with no read coverage).
homepage: https://github.com/FredHutch/SEACR
documentation: https://github.com/FredHutch/SEACR
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', single_end:false ]
- bedgraph:
type: file
description: |
The target bedgraph file from which the peaks will be calculated.
- ctrlbedgraph:
type: file
description: |
Control (IgG) data bedgraph file to generate an empirical threshold for peak calling.
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: Bed file containing the calculated peaks.
pattern: "*.bed"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
authors:
- "@chris-cheshire"

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,20 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { SEACR_CALLPEAK } from '../../../software/seacr/callpeak/main.nf' addParams( options: [ args:'norm stringent' ] )
workflow test_seacr_callpeak {
def input = []
input = [[ id:'test_1'],
file("${launchDir}/tests/data/bedgraph/K27me3_1_to_chr20.bedgraph", checkIfExists: true),
file("${launchDir}/tests/data/bedgraph/IgG_1_to_chr20.bedgraph", checkIfExists: true) ]
SEACR_CALLPEAK ( input )
}
// For local testing
workflow {
test_seacr_callpeak()
}

View file

@ -0,0 +1,8 @@
- name: Run seacr call peak test workflow
command: nextflow run ./tests/software/seacr/ -profile docker -entry test_seacr_callpeak -c tests/config/nextflow.config
tags:
- seacr
- seacr_callpeak
files:
- path: output/seacr/test_1.stringent.bed
md5sum: 3ac70475669eb6a7b8ca89e19a08a28e