Added the rtgtools/vcfeval module

This commit is contained in:
Nicolas Vannieuwkerke 2022-05-06 14:23:40 +02:00
parent 3c07602443
commit 84b354ab6a
5 changed files with 113 additions and 76 deletions

View file

@ -1,46 +1,18 @@
// TODO nf-core: If in doubt look at other nf-core/modules to see how we are doing things! :)
// https://github.com/nf-core/modules/tree/master/modules
// You can also ask for help via your pull request or on the #modules channel on the nf-core Slack workspace:
// https://nf-co.re/join
// TODO nf-core: A module file SHOULD only define input and output files as command-line parameters.
// All other parameters MUST be provided using the "task.ext" directive, see here:
// https://www.nextflow.io/docs/latest/process.html#ext
// where "task.ext" is a string.
// Any parameters that need to be evaluated in the context of a particular sample
// e.g. single-end/paired-end data MUST also be defined and evaluated appropriately.
// TODO nf-core: Software that can be piped together SHOULD be added to separate module files
// unless there is a run-time, storage advantage in implementing in this way
// e.g. it's ok to have a single module for bwa to output BAM instead of SAM:
// bwa mem | samtools view -B -T ref.fasta
// TODO nf-core: Optional inputs are not currently supported by Nextflow. However, using an empty
// list (`[]`) instead of a file can be used to work around this issue.
process RTGTOOLS_VCFEVAL { process RTGTOOLS_VCFEVAL {
tag "$meta.id" tag "$meta.id"
label 'process_medium' label 'process_medium'
// TODO nf-core: List required Conda package(s).
// Software MUST be pinned to channel (i.e. "bioconda"), version (i.e. "1.10").
// For Conda, the build (i.e. "h9402c20_2") must be EXCLUDED to support installation on different operating systems.
// TODO nf-core: See section in main README for further information regarding finding and adding container addresses to the section below.
conda (params.enable_conda ? "bioconda::rtg-tools=3.12.1" : null) conda (params.enable_conda ? "bioconda::rtg-tools=3.12.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/rtg-tools:3.12.1--hdfd78af_0': 'https://depot.galaxyproject.org/singularity/rtg-tools:3.12.1--hdfd78af_0':
'quay.io/biocontainers/rtg-tools:3.12.1--hdfd78af_0' }" 'quay.io/biocontainers/rtg-tools:3.12.1--hdfd78af_0' }"
input: input:
// TODO nf-core: Where applicable all sample-specific information e.g. "id", "single_end", "read_group" tuple val(meta), path(truth_vcf), path(truth_vcf_tbi), path(query_vcf), path(query_vcf_tbi), path(bed)
// MUST be provided as an input via a Groovy Map called "meta". path(sdf)
// This information may not be required in some instances e.g. indexing reference genome files:
// https://github.com/nf-core/modules/blob/master/modules/bwa/index/main.nf
// TODO nf-core: Where applicable please provide/convert compressed files as input/output
// e.g. "*.fastq.gz" and NOT "*.fastq", "*.bam" and NOT "*.sam" etc.
tuple val(meta), path(bam)
output: output:
// TODO nf-core: Named file extensions MUST be emitted for ALL output channels tuple val(meta), path("*.txt"), emit: results
tuple val(meta), path("*.bam"), emit: bam
// TODO nf-core: List additional required output channels/values here
path "versions.yml" , emit: versions path "versions.yml" , emit: versions
when: when:
@ -49,19 +21,35 @@ process RTGTOOLS_VCFEVAL {
script: script:
def args = task.ext.args ?: '' def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}" def prefix = task.ext.prefix ?: "${meta.id}"
// TODO nf-core: Where possible, a command MUST be provided to obtain the version number of the software e.g. 1.10 def regions = bed ? "--bed-regions=$bed" : ""
// If the software is unable to output a version number on the command-line then it can be manually specified def truth_index = truth_vcf_tbi ? "" : "rtg index $truth_vcf"
// e.g. https://github.com/nf-core/modules/blob/master/modules/homer/annotatepeaks/main.nf def query_index = query_vcf_tbi ? "" : "rtg index $query_vcf"
// Each software used MUST provide the software name and version number in the YAML version file (versions.yml)
// TODO nf-core: It MUST be possible to pass additional parameters to the tool as a command-line string via the "task.ext.args" directive sdf_basename = sdf.getBaseName().replace(".tar","")
// TODO nf-core: If the tool supports multi-threading then you MUST provide the appropriate parameter tar_decomp = ""
// using the Nextflow "task" variable e.g. "--threads $task.cpus" if((sdf =~ /.tar.gz\b/).find() == true) {
// TODO nf-core: Please replace the example samtools command below with your module's command tar_decomp = "tar -xzf $sdf"
// TODO nf-core: Please indent the command appropriately (4 spaces!!) to help with readability ;) }
""" """
$tar_decomp
$truth_index
$query_index
rtg vcfeval \\
$args \\
--baseline=$truth_vcf \\
$regions \\
--calls=$query_vcf \\
--output=$prefix \\
--template=$sdf_basename \\
--threads=$task.cpus \\
> ${prefix}_results.txt
cat <<-END_VERSIONS > versions.yml cat <<-END_VERSIONS > versions.yml
"${task.process}": "${task.process}":
rtgtools: \$(echo \$(rtg version | head -n 1 | awk '{print \$4}')) rtg-tools: \$(echo \$(rtg version | head -n 1 | awk '{print \$4}'))
END_VERSIONS END_VERSIONS
""" """
} }

View file

@ -1,51 +1,63 @@
name: "rtgtools_vcfeval" name: "rtgtools_vcfeval"
## TODO nf-core: Add a description of the module and list keywords description: The VCFeval tool of RTG tools. It is used to evaluate called variants for agreement with a baseline variant set
description: write your description here
keywords: keywords:
- sort - benchmarking
- vcf
- rtg-tools
tools: tools:
- "rtgtools": - "rtgtools":
## TODO nf-core: Add a description and other details for the software below
description: "RealTimeGenomics Tools -- Utilities for accurate VCF comparison and manipulation" description: "RealTimeGenomics Tools -- Utilities for accurate VCF comparison and manipulation"
homepage: "None" homepage: "https://www.realtimegenomics.com/products/rtg-tools"
documentation: "None" documentation: "https://github.com/RealTimeGenomics/rtg-tools"
tool_dev_url: "None" tool_dev_url: "https://github.com/RealTimeGenomics/rtg-tools"
doi: "" doi: ""
licence: "['BSD']" licence: "['BSD']"
## TODO nf-core: Add a description of all of the variables used as input
input: input:
# Only when we have meta
- meta: - meta:
type: map type: map
description: | description: |
Groovy Map containing sample information Groovy Map containing sample information
e.g. [ id:'test', single_end:false ] e.g. [ id:'test', single_end:false ]
# - truth_vcf:
## TODO nf-core: Delete / customise this example input
- bam:
type: file type: file
description: BAM/CRAM/SAM file description: A standard VCF to compare against
pattern: "*.{bam,cram,sam}" pattern: "*.{vcf,vcf.gz}"
- truth_vcf_index:
type: file
description: The index of the standard VCF (optional)
pattern: "*.tbi"
- query_vcf:
type: file
description: A VCF with called variants to benchmark against the standard
pattern: "*.{vcf,vcf.gz}"
- query_vcf_index:
type: file
description: The index of the called VCF (optional)
pattern: "*.tbi"
- bed:
type: file
description: The BED file of the called VCF
pattern: "*.bed"
- sdf:
type: folder/file
description: The SDF (RTG Sequence Data File) of the reference genome. Can be a folder or a tar-zipped folder.
pattern: "*.{,tar.gz}"
## TODO nf-core: Add a description of all of the variables used as output
output: output:
#Only when we have meta
- meta: - meta:
type: map type: map
description: | description: |
Groovy Map containing sample information Groovy Map containing sample information
e.g. [ id:'test', single_end:false ] e.g. [ id:'test', single_end:false ]
#
- versions: - versions:
type: file type: file
description: File containing software versions description: File containing software versions
pattern: "versions.yml" pattern: "versions.yml"
## TODO nf-core: Delete / customise this example output - results:
- bam:
type: file type: file
description: Sorted BAM/CRAM/SAM file description: A text file containing the results of the benchmark
pattern: "*.{bam,cram,sam}" pattern: "*.txt"
authors: authors:
- "@nvnieuwk" - "@nvnieuwk"

View file

@ -132,6 +132,7 @@ params {
transcriptome_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta" transcriptome_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta"
genome2_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome2.fasta" genome2_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome2.fasta"
genome_chain_gz = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz" genome_chain_gz = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz"
genome_21_sdf = "${test_data_dir}/genomics/homo_sapiens/genome/genome_sdf.tar.gz"
genome_21_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta" genome_21_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta"
genome_21_fasta_fai = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai" genome_21_fasta_fai = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai"
genome_21_dict = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict" genome_21_dict = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.dict"
@ -263,6 +264,9 @@ params {
test2_haplotc_ann_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz" test2_haplotc_ann_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz"
test2_haplotc_ann_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz.tbi" test2_haplotc_ann_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.ann.vcf.gz.tbi"
test2_haplotc_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz"
test2_haplotc_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/haplotypecaller_calls/test2_haplotc.vcf.gz.tbi"
test2_recal = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal" test2_recal = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal"
test2_recal_idx = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal.idx" test2_recal_idx = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.recal.idx"
test2_tranches = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.tranches" test2_tranches = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/variantrecalibrator/test2.tranches"

View file

@ -7,9 +7,35 @@ include { RTGTOOLS_VCFEVAL } from '../../../../modules/rtgtools/vcfeval/main.nf'
workflow test_rtgtools_vcfeval { workflow test_rtgtools_vcfeval {
input = [ input = [
[ id:'test', single_end:false ], // meta map [ id:'test' ], // meta map
file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz_tbi'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz_tbi'], checkIfExists: true),
file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
] ]
RTGTOOLS_VCFEVAL ( input ) sdf = Channel.value(
file(params.test_data['homo_sapiens']['genome']['genome_21_sdf'])
)
RTGTOOLS_VCFEVAL ( input, sdf )
}
workflow test_rtgtools_vcfeval_no_index {
input = [
[ id:'test' ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_ann_vcf_gz'], checkIfExists: true),
[],
file(params.test_data['homo_sapiens']['illumina']['test2_haplotc_vcf_gz'], checkIfExists: true),
[],
file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
]
sdf = Channel.value(
file(params.test_data['homo_sapiens']['genome']['genome_21_sdf'])
)
RTGTOOLS_VCFEVAL ( input, sdf )
} }

View file

@ -1,14 +1,21 @@
## TODO nf-core: Please run the following command to build this file: - name: rtgtools vcfeval test_rtgtools_vcfeval
# nf-core modules create-test-yml rtgtools/vcfeval command: nextflow run tests/modules/rtgtools/vcfeval -entry test_rtgtools_vcfeval -c tests/config/nextflow.config
- name: "rtgtools vcfeval"
command: nextflow run ./tests/modules/rtgtools/vcfeval -entry test_rtgtools_vcfeval -c ./tests/config/nextflow.config -c ./tests/modules/rtgtools/vcfeval/nextflow.config
tags: tags:
- "rtgtools" - rtgtools
# - rtgtools/vcfeval
- "rtgtools/vcfeval"
#
files: files:
- path: "output/rtgtools/test.bam" - path: output/rtgtools/test_results.txt
md5sum: e667c7caad0bc4b7ac383fd023c654fc md5sum: 2e011aa6e54d258fcc3b45b2dda02ae4
- path: output/rtgtools/versions.yml - path: output/rtgtools/versions.yml
md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b md5sum: 270ed7a5a8e347b251eb4aa2198f98e8
- name: rtgtools vcfeval test_rtgtools_vcfeval_no_index
command: nextflow run tests/modules/rtgtools/vcfeval -entry test_rtgtools_vcfeval_no_index -c tests/config/nextflow.config
tags:
- rtgtools
- rtgtools/vcfeval
files:
- path: output/rtgtools/test_results.txt
md5sum: 2e011aa6e54d258fcc3b45b2dda02ae4
- path: output/rtgtools/versions.yml
md5sum: 8d0407000988c78fa43fe5cfe3d4449d