feat: add VEP module (#547)

* feat: add VEP module

* fix: name

* fix: EC lint]

* feat: add info about params

* fix: params as params, not input

* fix: improve script

* Update software/ensemblvep/environment.yml

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

* Apply suggestions from code review

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

* Apply suggestions from code review

* Apply suggestions from code review

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

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
This commit is contained in:
Maxime U. Garcia 2021-07-06 14:11:11 +02:00 committed by GitHub
parent 3f4eccbf0f
commit 7b4a28b6e8
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 284 additions and 0 deletions

View file

@ -0,0 +1,30 @@
FROM nfcore/base:1.14
LABEL \
author="Maxime Garcia" \
description="VEP image for nf-core pipelines" \
maintainer="maxime.garcia@scilifelab.se"
# Install the conda environment
COPY environment.yml /
RUN conda env create -f /environment.yml && conda clean -a
# Add conda installation dir to PATH (instead of doing 'conda activate')
ENV PATH /opt/conda/envs/nf-core-vep-104.3/bin:$PATH
# Setup default ARG variables
ARG GENOME=GRCh38
ARG SPECIES=homo_sapiens
ARG VEP_VERSION=99
# Download Genome
RUN vep_install \
-a c \
-c .vep \
-s ${SPECIES} \
-y ${GENOME} \
--CACHE_VERSION ${VEP_VERSION} \
--CONVERT \
--NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE
# Dump the details of the installed packages to a file for posterity
RUN conda env export --name nf-core-vep-104.3 > nf-core-vep-104.3.yml

27
software/ensemblvep/build.sh Executable file
View file

@ -0,0 +1,27 @@
#!/usr/bin/env bash
set -euo pipefail
# Build and push all containers
build_push() {
GENOME=$1
SPECIES=$2
VEP_VERSION=$3
VEP_TAG=$4
docker build \
-t nfcore/vep:${VEP_TAG}.${GENOME} \
software/vep/. \
--build-arg GENOME=${GENOME} \
--build-arg SPECIES=${SPECIES} \
--build-arg VEP_VERSION=${VEP_VERSION}
docker push nfcore/vep:${VEP_TAG}.${GENOME}
}
build_push "GRCh37" "homo_sapiens" "104" "104.3"
build_push "GRCh38" "homo_sapiens" "104" "104.3"
build_push "GRCm38" "mus_musculus" "102" "104.3"
build_push "GRCm39" "mus_musculus" "104" "104.3"
build_push "CanFam3.1" "canis_lupus_familiaris" "104" "104.3"
build_push "WBcel235" "caenorhabditis_elegans" "104" "104.3"

View file

@ -0,0 +1,10 @@
# You can use this file to create a conda environment for this module:
# conda env create -f environment.yml
name: nf-core-vep-104.3
channels:
- conda-forge
- bioconda
- defaults
dependencies:
- bioconda::ensembl-vep=104.3

View file

@ -0,0 +1,68 @@
//
// Utility functions used in nf-core DSL2 module files
//
//
// Extract name of software tool from process name using $task.process
//
def getSoftwareName(task_process) {
return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
}
//
// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
//
def initOptions(Map args) {
def Map options = [:]
options.args = args.args ?: ''
options.args2 = args.args2 ?: ''
options.args3 = args.args3 ?: ''
options.publish_by_meta = args.publish_by_meta ?: []
options.publish_dir = args.publish_dir ?: ''
options.publish_files = args.publish_files
options.suffix = args.suffix ?: ''
return options
}
//
// Tidy up and join elements of a list to return a path string
//
def getPathFromList(path_list) {
def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries
paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
return paths.join('/')
}
//
// Function to save/publish module results
//
def saveFiles(Map args) {
if (!args.filename.endsWith('.version.txt')) {
def ioptions = initOptions(args.options)
def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
if (ioptions.publish_by_meta) {
def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
for (key in key_list) {
if (args.meta && key instanceof String) {
def path = key
if (args.meta.containsKey(key)) {
path = args.meta[key] instanceof Boolean ? "${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 +1,62 @@
// Import generic module functions
include { initOptions; saveFiles; getSoftwareName } from './functions'
params.options = [:]
options = initOptions(params.options)
params.use_cache = false
params.vep_tag = ""
process ENSEMBLVEP {
label 'process_medium'
publishDir "${params.outdir}",
mode: params.publish_dir_mode,
saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
conda (params.enable_conda ? "bioconda::ensembl-vep=104.3" : null)
if (params.use_cache) {
if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
container "https://depot.galaxyproject.org/singularity/ensembl-vep:104.3--pl5262h4a94de4_0"
} else {
container "quay.io/biocontainers/ensembl-vep:104.3--pl5262h4a94de4_0"
}
} else {
container "nfcore/vep:${params.vep_tag}"
}
input:
tuple val(meta), path(vcf)
val genome
val species
val cache_version
path cache
output:
tuple val(meta), path("*.ann.vcf"), emit: vcf
path "*.summary.html" , emit: report
path "*.version.txt" , emit: version
script:
def software = getSoftwareName(task.process)
def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
dir_cache = params.use_cache ? "\${PWD}/${cache}" : "/.vep"
"""
mkdir $prefix
vep \\
-i $vcf \\
-o ${prefix}.ann.vcf \\
$options.args \\
--assembly $genome \\
--species $species \\
--cache \\
--cache_version $cache_version \\
--dir_cache $dir_cache \\
--fork $task.cpus \\
--format vcf \\
--stats_file ${prefix}.summary.html
rm -rf $prefix
echo \$(vep --help 2>&1) > ${software}.version.txt
"""
}

View file

@ -0,0 +1,64 @@
name: ENSEMBLVEP
description: Ensembl Variant Effect Predictor (VEP)
keywords:
- annotation
tools:
- ensemblvep:
description: |
VEP determines the effect of your variants (SNPs, insertions, deletions, CNVs
or structural variants) on genes, transcripts, and protein sequence, as well as regulatory regions.
homepage: https://www.ensembl.org/info/docs/tools/vep/index.html
documentation: https://www.ensembl.org/info/docs/tools/vep/script/index.html
params:
- use_cache:
type: boolean
description: |
Enable the usage of containers with cache
Does not work with conda
- vep_tag:
type: value
description: |
Specify the tag for the container
https://hub.docker.com/r/nfcore/vep/tags
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- vcf:
type: file
description: |
vcf to annotate
- genome:
type: value
description: |
which genome to annotate with
- species:
type: value
description: |
which species to annotate with
- cache_version:
type: value
description: |
which version of the cache to annotate with
- cache:
type: file
description: |
path to VEP cache (optional)
output:
- vcf:
type: file
description: |
annotated vcf
pattern: "*.ann.vcf"
- report:
type: file
description: VEP report file
pattern: "*.html"
- version:
type: file
description: File containing software version
pattern: "*.{version.txt}"
authors:
- "@maxulysse"

View file

@ -230,6 +230,10 @@ dshbio/splitgff3:
- software/dshbio/splitgff3/**
- tests/software/dshbio/splitgff3/**
ensemblvep:
- software/ensemblvep/**
- tests/software/ensemblvep/**
fastp:
- software/fastp/**
- tests/software/fastp/**

View file

@ -0,0 +1,12 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { ENSEMBLVEP } from '../../../software/ensemblvep/main.nf' addParams( vep_tag: '104.3.WBcel235', use_cache: false )
workflow test_ensemblvep {
input = [ [ id:'test' ], // meta map
[ file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true) ]
]
ENSEMBLVEP ( input, "WBcel235", "caenorhabditis_elegans", "104", [] )
}

View file

@ -0,0 +1,7 @@
- name: ensemblvep test_ensemblvep
command: nextflow run tests/software/ensemblvep -entry test_ensemblvep -c tests/config/nextflow.config
tags:
- ensemblvep
files:
- path: output/ensemblvep/test.ann.vcf
- path: output/ensemblvep/test.summary.html