Merge branch 'master' into sexdeterrmine

This commit is contained in:
Thiseas C. Lamnidis 2022-05-24 13:17:37 +02:00 committed by GitHub
commit 6d04395c3c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
29 changed files with 509 additions and 149 deletions

View file

@ -0,0 +1,36 @@
process CNVKIT_ANTITARGET {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
input:
tuple val(meta), path(targets)
output:
tuple val(meta), path("*.bed"), emit: bed
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
"""
cnvkit.py \\
antitarget \\
$targets \\
--output ${prefix}.antitarget.bed \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}

View file

@ -0,0 +1,44 @@
name: cnvkit_antitarget
description:
keywords:
- cvnkit
- antitarget
tools:
- cnvkit:
description: |
CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
homepage: https://cnvkit.readthedocs.io/en/stable/index.html
documentation: https://cnvkit.readthedocs.io/en/stable/index.html
tool_dev_url: "https://github.com/etal/cnvkit"
doi: 10.1371/journal.pcbi.1004873
licence: ["Apache-2.0"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- targets:
type: file
description: File containing genomic regions
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: File containing off-target regions
pattern: "*.{bed}"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@SusiJo"

View file

@ -2,10 +2,10 @@ process CNVKIT_BATCH {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9' : null)
conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9 bioconda::samtools=1.15.1' : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0' :
'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' :
'quay.io/biocontainers/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' }"
input:
tuple val(meta), path(tumor), path(normal)
@ -18,6 +18,8 @@ process CNVKIT_BATCH {
tuple val(meta), path("*.cnn"), emit: cnn, optional: true
tuple val(meta), path("*.cnr"), emit: cnr, optional: true
tuple val(meta), path("*.cns"), emit: cns, optional: true
tuple val(meta), path("*.pdf"), emit: pdf, optional: true
tuple val(meta), path("*.png"), emit: png, optional: true
path "versions.yml" , emit: versions
when:
@ -25,21 +27,39 @@ process CNVKIT_BATCH {
script:
def args = task.ext.args ?: ''
def normal_args = normal ? "--normal $normal" : ""
def fasta_args = fasta ? "--fasta $fasta" : ""
// execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
// input pair is assumed to have same extension if both exist
def is_cram = tumor.Extension == "cram" ? true : false
def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
// do not run samtools on normal samples in tumor_only mode
def normal_exists = normal ? true: false
// tumor_only mode does not need fasta & target
// instead it requires a pre-computed reference.cnn which is built from fasta & target
def (normal_out, normal_args, fasta_args) = ["", "", ""]
if (normal_exists){
def normal_prefix = normal.BaseName
normal_out = is_cram ? "${normal_prefix}" + ".bam" : "${normal}"
normal_args = normal_prefix ? "--normal $normal_out" : ""
fasta_args = fasta ? "--fasta $fasta" : ""
}
def target_args = targets ? "--targets $targets" : ""
def reference_args = reference ? "--reference $reference" : ""
def target_args = ""
if (args.contains("--method wgs") || args.contains("-m wgs")) {
target_args = targets ? "--targets $targets" : ""
}
else {
target_args = "--targets $targets"
}
"""
if $is_cram; then
samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out
if $normal_exists; then
samtools view -T $fasta $normal -@ $task.cpus -o $normal_out
fi
fi
cnvkit.py \\
batch \\
$tumor \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\

View file

@ -11,27 +11,6 @@ tools:
homepage: https://cnvkit.readthedocs.io/en/stable/index.html
documentation: https://cnvkit.readthedocs.io/en/stable/index.html
licence: ["Apache-2.0"]
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
@ -49,7 +28,7 @@ input:
- fasta:
type: file
description: |
Input reference genome fasta file
Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided)
- targetfile:
type: file
description: |
@ -80,6 +59,14 @@ output:
type: file
description: File containing copy number segment information
pattern: "*.{cns}"
- pdf:
type: file
description: File with plot of copy numbers or segments on chromosomes
pattern: "*.{pdf}"
- png:
type: file
description: File with plot of bin-level log2 coverages and segmentation calls
pattern: "*.{png}"
- versions:
type: file
description: File containing software versions
@ -91,3 +78,4 @@ authors:
- "@drpatelh"
- "@fbdtemme"
- "@lassefolkersen"
- "@SusiJo"

View file

@ -0,0 +1,39 @@
process CNVKIT_REFERENCE {
tag "$reference"
label 'process_low'
conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
input:
path fasta
path targets
path antitargets
output:
path("*.cnn") , emit: cnn
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
"""
cnvkit.py \\
reference \\
--fasta $fasta \\
--targets $targets \\
--antitargets $antitargets \\
--output reference.cnn \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}

View file

@ -0,0 +1,47 @@
name: cnvkit_reference
description:
keywords:
- cnvkit
- reference
tools:
- cnvkit:
description: |
CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
homepage: https://cnvkit.readthedocs.io/en/stable/index.html
documentation: https://cnvkit.readthedocs.io/en/stable/index.html
tool_dev_url: https://github.com/etal/cnvkit
doi: 10.1371/journal.pcbi.1004873
licence: ["Apache-2.0"]
input:
- fasta:
type: file
description: File containing reference genome
pattern: "*.{fasta}"
- targets:
type: file
description: File containing genomic regions
pattern: "*.{bed}"
- antitargets:
type: file
description: File containing off-target genomic regions
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- reference:
type: file
description: File containing a copy-number reference (required for CNV calling in tumor_only mode)
pattern: "*.{cnn}"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@SusiJo"

View file

@ -24,7 +24,7 @@ process PICARD_COLLECTHSMETRICS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def reference = fasta ? "-R $fasta" : ""
def reference = fasta ? "--REFERENCE_SEQUENCE ${fasta}" : ""
def avail_mem = 3
if (!task.memory) {

View file

@ -22,6 +22,7 @@ process PICARD_COLLECTMULTIPLEMETRICS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def reference = fasta ? "--REFERENCE_SEQUENCE ${fasta}" : ""
def avail_mem = 3
if (!task.memory) {
log.info '[Picard CollectMultipleMetrics] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -35,7 +36,7 @@ process PICARD_COLLECTMULTIPLEMETRICS {
$args \\
--INPUT $bam \\
--OUTPUT ${prefix}.CollectMultipleMetrics \\
--REFERENCE_SEQUENCE $fasta
$reference
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -34,7 +34,7 @@ process PICARD_COLLECTWGSMETRICS {
$args \\
--INPUT $bam \\
--OUTPUT ${prefix}.CollectWgsMetrics.coverage_metrics \\
--REFERENCE_SEQUENCE $fasta
--REFERENCE_SEQUENCE ${fasta}
cat <<-END_VERSIONS > versions.yml

View file

@ -9,12 +9,13 @@ process UMITOOLS_DEDUP {
input:
tuple val(meta), path(bam), path(bai)
val get_output_stats
output:
tuple val(meta), path("*.bam") , emit: bam
tuple val(meta), path("*edit_distance.tsv"), emit: tsv_edit_distance
tuple val(meta), path("*per_umi.tsv") , emit: tsv_per_umi
tuple val(meta), path("*per_position.tsv") , emit: tsv_umi_per_position
tuple val(meta), path("*edit_distance.tsv"), optional:true, emit: tsv_edit_distance
tuple val(meta), path("*per_umi.tsv") , optional:true, emit: tsv_per_umi
tuple val(meta), path("*per_position.tsv") , optional:true, emit: tsv_umi_per_position
path "versions.yml" , emit: versions
when:
@ -24,12 +25,13 @@ process UMITOOLS_DEDUP {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def paired = meta.single_end ? "" : "--paired"
def stats = get_output_stats ? "--output-stats $prefix" : ""
"""
umi_tools \\
dedup \\
-I $bam \\
-S ${prefix}.bam \\
--output-stats $prefix \\
$stats \\
$paired \\
$args

View file

@ -26,6 +26,10 @@ input:
description: |
BAM index files corresponding to the input BAM file.
pattern: "*.{bai}"
- get_output_stats:
type: boolean
description: |
Whether or not to generate output stats.
output:
- meta:
type: map

View file

@ -447,10 +447,18 @@ cmseq/polymut:
- modules/cmseq/polymut/**
- tests/modules/cmseq/polymut/**
cnvkit/antitarget:
- modules/cnvkit/antitarget/**
- tests/modules/cnvkit/antitarget/**
cnvkit/batch:
- modules/cnvkit/batch/**
- tests/modules/cnvkit/batch/**
cnvkit/reference:
- modules/cnvkit/reference/**
- tests/modules/cnvkit/reference/**
controlfreec/assesssignificance:
- modules/controlfreec/assesssignificance/**
- tests/modules/controlfreec/assesssignificance/**

View file

@ -142,6 +142,7 @@ params {
genome_21_sizes = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.sizes"
genome_21_interval_list = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/genome.interval_list"
genome_21_multi_interval_bed = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed"
genome_21_multi_interval_antitarget_bed = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.antitarget.bed"
genome_21_multi_interval_bed_gz = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz"
genome_21_multi_interval_bed_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz.tbi"
genome_21_chromosomes_dir = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz"

View file

@ -0,0 +1,16 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { CNVKIT_ANTITARGET } from '../../../../modules/cnvkit/antitarget/main.nf'
workflow test_cnvkit_antitarget {
input = [
[ id:'test' ], // meta map
file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
]
CNVKIT_ANTITARGET ( input )
}

View file

@ -0,0 +1,5 @@
process {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
}

View file

@ -0,0 +1,8 @@
- name: cnvkit antitarget test_cnvkit_antitarget
command: nextflow run ./tests/modules/cnvkit/antitarget -entry test_cnvkit_antitarget -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/antitarget/nextflow.config
tags:
- cnvkit
- cnvkit/antitarget
files:
- path: output/cnvkit/test.antitarget.bed
md5sum: 3d4d20f9f23b39970865d29ef239d20b

View file

@ -35,8 +35,8 @@ workflow test_cnvkit_cram {
input = [
[ id:'test'], // meta map
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true)
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
@ -50,8 +50,20 @@ workflow test_cnvkit_tumoronly {
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true),
[]
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
CNVKIT_TUMORONLY ( input, [], [], reference )
}
workflow test_cnvkit_tumoronly_cram {
input = [
[ id:'test'], // meta map
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
[]
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
CNVKIT_TUMORONLY ( input, fasta, [], reference )
}

View file

@ -1,15 +1,14 @@
- name: cnvkit batch test_cnvkit_hybrid
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_hybrid -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit/batch
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/baits.antitarget.bed
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/cnvkit/baits.target.bed
md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
- path: output/cnvkit/reference.cnn
md5sum: ac99c1ad8b917b96ae15119146c91ab9
md5sum: 035d031f54c5f1b43b903da96559b475
- path: output/cnvkit/test.paired_end.sorted.antitargetcoverage.cnn
md5sum: 203caf8cef6935bb50b4138097955cb8
- path: output/cnvkit/test.paired_end.sorted.bintest.cns
@ -30,17 +29,16 @@
- name: cnvkit batch test_cnvkit_wgs
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_wgs -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit/batch
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/genome.antitarget.bed
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/cnvkit/genome.bed
md5sum: 87a15eb9c2ff20ccd5cd8735a28708f7
- path: output/cnvkit/genome.target.bed
md5sum: a13353ae9c8405e701390c069255bbd2
- path: output/cnvkit/reference.cnn
md5sum: 05c6211e0179885b8a83e44fd21d5f86
md5sum: 1606a85410bfaa79464be6e98699aa83
- path: output/cnvkit/test.paired_end.sorted.antitargetcoverage.cnn
md5sum: 203caf8cef6935bb50b4138097955cb8
- path: output/cnvkit/test.paired_end.sorted.targetcoverage.cnn
@ -61,17 +59,16 @@
- name: cnvkit batch test_cnvkit_cram
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_cram -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit/batch
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/genome.antitarget.bed
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/cnvkit/genome.bed
md5sum: 87a15eb9c2ff20ccd5cd8735a28708f7
- path: output/cnvkit/genome.target.bed
md5sum: a13353ae9c8405e701390c069255bbd2
- path: output/cnvkit/reference.cnn
md5sum: 05c6211e0179885b8a83e44fd21d5f86
md5sum: 1606a85410bfaa79464be6e98699aa83
- path: output/cnvkit/test.paired_end.sorted.antitargetcoverage.cnn
md5sum: 203caf8cef6935bb50b4138097955cb8
- path: output/cnvkit/test.paired_end.sorted.targetcoverage.cnn
@ -92,10 +89,19 @@
- name: cnvkit batch test_cnvkit_tumoronly
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit/batch
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/reference.antitarget-tmp.bed
- path: output/cnvkit/reference.target-tmp.bed
md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
- name: cnvkit batch test_cnvkit_tumoronly_cram
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly_cram -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/reference.antitarget-tmp.bed
md5sum: d41d8cd98f00b204e9800998ecf8427e
- path: output/cnvkit/reference.target-tmp.bed
md5sum: 26d25ff2d6c45b6d92169b3559c6acdb

View file

@ -0,0 +1,14 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { CNVKIT_REFERENCE } from '../../../../modules/cnvkit/reference/main.nf'
workflow test_cnvkit_reference {
fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
targets = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
antitargets = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_antitarget_bed'], checkIfExists: true)
CNVKIT_REFERENCE ( fasta, targets, antitargets )
}

View file

@ -0,0 +1,5 @@
process {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
}

View file

@ -0,0 +1,8 @@
- name: cnvkit reference test_cnvkit_reference
command: nextflow run ./tests/modules/cnvkit/reference -entry test_cnvkit_reference -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/reference/nextflow.config
tags:
- cnvkit/reference
- cnvkit
files:
- path: output/cnvkit/reference.cnn
md5sum: 7c4a7902f5ab101b1f9d6038d331b3d9

View file

@ -16,3 +16,14 @@ workflow test_picard_collecthsmetrics {
PICARD_COLLECTHSMETRICS ( input, fasta, fai, bait_intervals, target_intervals )
}
workflow test_picard_collecthsmetrics_nofasta {
input = [ [ id:'test', single_end:false ], // meta map
file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ]
bait_intervals = file(params.test_data['sarscov2']['genome']['baits_interval_list'], checkIfExists: true)
target_intervals = file(params.test_data['sarscov2']['genome']['targets_interval_list'], checkIfExists: true)
PICARD_COLLECTHSMETRICS ( input, [], [], bait_intervals, target_intervals )
}

View file

@ -1,8 +1,15 @@
- name: picard collecthsmetrics test_picard_collecthsmetrics
command: nextflow run ./tests/modules/picard/collecthsmetrics -entry test_picard_collecthsmetrics -c ./tests/config/nextflow.config -c ./tests/modules/picard/collecthsmetrics/nextflow.config
tags:
- picard
- picard/collecthsmetrics
- picard
files:
- path: output/picard/test.CollectHsMetrics.coverage_metrics
- name: picard collecthsmetrics test_picard_collecthsmetrics_nofasta
command: nextflow run ./tests/modules/picard/collecthsmetrics -entry test_picard_collecthsmetrics_nofasta -c ./tests/config/nextflow.config -c ./tests/modules/picard/collecthsmetrics/nextflow.config
tags:
- picard/collecthsmetrics
- picard
files:
# The file can't be md5'd consistently
- path: output/picard/test.CollectHsMetrics.coverage_metrics

View file

@ -5,10 +5,20 @@ nextflow.enable.dsl = 2
include { PICARD_COLLECTMULTIPLEMETRICS } from '../../../../modules/picard/collectmultiplemetrics/main.nf'
workflow test_picard_collectmultiplemetrics {
input = [ [ id:'test', single_end:false ], // meta map
input = [
[ id:'test', single_end:false ], // meta map
file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
]
fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
PICARD_COLLECTMULTIPLEMETRICS ( input, fasta )
}
workflow test_picard_collectmultiplemetrics_nofasta {
input = [
[ id:'test', single_end:false ], // meta map
file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
]
PICARD_COLLECTMULTIPLEMETRICS ( input, [] )
}

View file

@ -1,17 +1,33 @@
- name: picard collectmultiplemetrics
- name: picard collectmultiplemetrics test_picard_collectmultiplemetrics
command: nextflow run ./tests/modules/picard/collectmultiplemetrics -entry test_picard_collectmultiplemetrics -c ./tests/config/nextflow.config -c ./tests/modules/picard/collectmultiplemetrics/nextflow.config
tags:
- picard
- picard/collectmultiplemetrics
files:
# These can't be md5'd consistently
- path: ./output/picard/test.CollectMultipleMetrics.alignment_summary_metrics
- path: ./output/picard/test.CollectMultipleMetrics.insert_size_metrics
- path: ./output/picard/test.CollectMultipleMetrics.quality_distribution_metrics
- path: ./output/picard/test.CollectMultipleMetrics.quality_by_cycle_metrics
- path: ./output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle_metrics
- path: ./output/picard/test.CollectMultipleMetrics.quality_by_cycle.pdf
- path: ./output/picard/test.CollectMultipleMetrics.quality_distribution.pdf
- path: ./output/picard/test.CollectMultipleMetrics.read_length_histogram.pdf
- path: ./output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle.pdf
- path: ./output/picard/test.CollectMultipleMetrics.insert_size_histogram.pdf
- path: output/picard/test.CollectMultipleMetrics.alignment_summary_metrics
- path: output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle.pdf
- path: output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle_metrics
- path: output/picard/test.CollectMultipleMetrics.insert_size_histogram.pdf
- path: output/picard/test.CollectMultipleMetrics.insert_size_metrics
- path: output/picard/test.CollectMultipleMetrics.quality_by_cycle.pdf
- path: output/picard/test.CollectMultipleMetrics.quality_by_cycle_metrics
- path: output/picard/test.CollectMultipleMetrics.quality_distribution.pdf
- path: output/picard/test.CollectMultipleMetrics.quality_distribution_metrics
- path: output/picard/test.CollectMultipleMetrics.read_length_histogram.pdf
- name: picard collectmultiplemetrics test_picard_collectmultiplemetrics_nofasta
command: nextflow run ./tests/modules/picard/collectmultiplemetrics -entry test_picard_collectmultiplemetrics_nofasta -c ./tests/config/nextflow.config -c ./tests/modules/picard/collectmultiplemetrics/nextflow.config
tags:
- picard
- picard/collectmultiplemetrics
files:
- path: output/picard/test.CollectMultipleMetrics.alignment_summary_metrics
- path: output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle.pdf
- path: output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle_metrics
- path: output/picard/test.CollectMultipleMetrics.insert_size_histogram.pdf
- path: output/picard/test.CollectMultipleMetrics.insert_size_metrics
- path: output/picard/test.CollectMultipleMetrics.quality_by_cycle.pdf
- path: output/picard/test.CollectMultipleMetrics.quality_by_cycle_metrics
- path: output/picard/test.CollectMultipleMetrics.quality_distribution.pdf
- path: output/picard/test.CollectMultipleMetrics.quality_distribution_metrics
- path: output/picard/test.CollectMultipleMetrics.read_length_histogram.pdf

View file

@ -5,7 +5,3 @@
- picard
files:
- path: output/picard/test.CollectWgsMetrics.coverage_metrics
contains:
- "GENOME_TERRITORY"
- "29829"
- "17554"

View file

@ -12,45 +12,72 @@ include { UMITOOLS_DEDUP } from '../../../../modules/umitools/dedup/main.nf'
// Test with no UMI
//
workflow test_umitools_dedup_no_umi {
input = [ [ id:'test'], // meta map
[ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ],
[ file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true) ]
input = [
[ id:'test'], // meta map
file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
]
get_output_stats = false
UMITOOLS_DEDUP ( input )
UMITOOLS_DEDUP ( input, get_output_stats )
}
//
// Test with single-end data
// Test with single-end data without --output-stats
//
workflow test_umitools_dedup_single_end {
input = [ [ id:'test', single_end:true ], // meta map
[ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
workflow test_umitools_dedup_single_end_no_stats {
input = [
[ id:'test', single_end:true ], // meta map
file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
]
fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
get_output_stats = false
UMITOOLS_EXTRACT ( input )
BWA_INDEX ( fasta )
BWA_MEM ( UMITOOLS_EXTRACT.out.reads, BWA_INDEX.out.index, true )
SAMTOOLS_INDEX (BWA_MEM.out.bam)
UMITOOLS_DEDUP(BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]))
SAMTOOLS_INDEX ( BWA_MEM.out.bam )
UMITOOLS_DEDUP ( BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]), get_output_stats )
}
//
// Test with paired-end data
// Test with paired-end data without --output-stats
//
workflow test_umitools_dedup_paired_end {
input = [ [ id:'test', single_end:false ], // meta map
[ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
workflow test_umitools_dedup_paired_end_no_stats {
input = [
[ id:'test', single_end:false ], // meta map
[
file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
]
]
fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
get_output_stats = false
UMITOOLS_EXTRACT ( input )
BWA_INDEX ( fasta )
BWA_MEM ( UMITOOLS_EXTRACT.out.reads, BWA_INDEX.out.index, true )
SAMTOOLS_INDEX (BWA_MEM.out.bam)
UMITOOLS_DEDUP(BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]))
SAMTOOLS_INDEX ( BWA_MEM.out.bam )
UMITOOLS_DEDUP ( BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]), get_output_stats )
}
//
// Test with paired-end data with --output-stats
//
workflow test_umitools_dedup_paired_end_stats {
input = [
[ id:'test', single_end:false ], // meta map
[
file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true)
]
]
fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
get_output_stats = true
UMITOOLS_EXTRACT ( input )
BWA_INDEX ( fasta )
BWA_MEM ( UMITOOLS_EXTRACT.out.reads, BWA_INDEX.out.index, true )
SAMTOOLS_INDEX ( BWA_MEM.out.bam )
UMITOOLS_DEDUP ( BWA_MEM.out.bam.join(SAMTOOLS_INDEX.out.bai, by: [0]), get_output_stats )
}

View file

@ -7,11 +7,7 @@ process {
}
withName: UMITOOLS_DEDUP {
ext.args = ''
ext.prefix = 'dedup'
ext.prefix = { "${meta.id}.dedup" }
}
withName: BWA_MEM {
ext.args2 = ''
}
}

View file

@ -1,54 +1,87 @@
- name: umitools dedup test_umitools_dedup_no_umi
command: nextflow run tests/modules/umitools/dedup -entry test_umitools_dedup_no_umi -c tests/config/nextflow.config
command: nextflow run ./tests/modules/umitools/dedup -entry test_umitools_dedup_no_umi -c ./tests/config/nextflow.config -c ./tests/modules/umitools/dedup/nextflow.config
tags:
- umitools/dedup
- umitools
files:
- path: output/umitools/dedup.bam
md5sum: 53b4edc399db81b87d2343e78af73cf0
- path: output/umitools/dedup_edit_distance.tsv
md5sum: 65186b0964e2f8d970cc04d736d8b119
- path: output/umitools/dedup_per_umi.tsv
md5sum: 8e6783a4a79437b095f095f2aefe7c01
- path: output/umitools/dedup_per_umi_per_position.tsv
md5sum: 9386db4a104b8e4e32f3ca4a84efa4ac
- path: output/umitools/versions.yml
md5sum: 4aaaa33565bcd9a984255139933d6446
- path: output/umitools/test.dedup.bam
- name: umitools dedup test_umitools_dedup_single_end
command: nextflow run tests/modules/umitools/dedup -entry test_umitools_dedup_single_end -c tests/config/nextflow.config
- name: umitools dedup test_umitools_dedup_single_end_no_stats
command: nextflow run ./tests/modules/umitools/dedup -entry test_umitools_dedup_single_end_no_stats -c ./tests/config/nextflow.config -c ./tests/modules/umitools/dedup/nextflow.config
tags:
- umitools
- umitools/dedup
- umitools
files:
- path: output/bwa/bwa/genome.amb
md5sum: 3a68b8b2287e07dd3f5f95f4344ba76e
- path: output/bwa/bwa/genome.ann
md5sum: c32e11f6c859f166c7525a9c1d583567
- path: output/bwa/bwa/genome.bwt
md5sum: 0469c30a1e239dd08f68afe66fde99da
- path: output/bwa/bwa/genome.pac
md5sum: 983e3d2cd6f36e2546e6d25a0da78d66
- path: output/bwa/bwa/genome.sa
md5sum: ab3952cabf026b48cd3eb5bccbb636d1
- path: output/bwa/test.bam
md5sum: ea41a3cdca1856b22845e1067fd31f37
- path: output/bwa/versions.yml
md5sum: ce4d987f2c53f4c01b31d210c357b24a
md5sum: 3ecbe569cadb9b6c881917ce60779f75
- path: output/samtools/test.bam.bai
md5sum: 095af0ad3921212597ffd7c342ecd5a0
- path: output/samtools/versions.yml
md5sum: 69b7cde627c9b4e8403dfc125db71cc7
- path: output/umitools/dedup.bam
md5sum: d95df177063432748ff33f473910cb1e
- path: output/umitools/versions.yml
md5sum: 730e768dd199d2f5bfb6fd0850446344
- path: output/umitools/test.dedup.bam
- path: output/umitools/test.umi_extract.fastq.gz
- path: output/umitools/test.umi_extract.log
- name: umitools dedup test_umitools_dedup_paired_end
command: nextflow run tests/modules/umitools/dedup -entry test_umitools_dedup_paired_end -c tests/config/nextflow.config
- name: umitools dedup test_umitools_dedup_paired_end_no_stats
command: nextflow run ./tests/modules/umitools/dedup -entry test_umitools_dedup_paired_end_no_stats -c ./tests/config/nextflow.config -c ./tests/modules/umitools/dedup/nextflow.config
tags:
- umitools
- umitools/dedup
- umitools
files:
- path: output/bwa/bwa/genome.amb
md5sum: 3a68b8b2287e07dd3f5f95f4344ba76e
- path: output/bwa/bwa/genome.ann
md5sum: c32e11f6c859f166c7525a9c1d583567
- path: output/bwa/bwa/genome.bwt
md5sum: 0469c30a1e239dd08f68afe66fde99da
- path: output/bwa/bwa/genome.pac
md5sum: 983e3d2cd6f36e2546e6d25a0da78d66
- path: output/bwa/bwa/genome.sa
md5sum: ab3952cabf026b48cd3eb5bccbb636d1
- path: output/bwa/test.bam
md5sum: 1ad786cae0ff2254c655e3a206929617
- path: output/bwa/versions.yml
md5sum: b524c5ddf61c20f4a0a93ae8fc78b851
md5sum: e7dcbac1825bf210409b762dbb4fec8f
- path: output/samtools/test.bam.bai
md5sum: 7496f4056a8e86327ca93e350f282fc2
- path: output/samtools/versions.yml
md5sum: 72fc2ab934fd4bca0f7f14a705530d34
- path: output/umitools/dedup.bam
md5sum: e8d1eae2aacef76254948c5568e94555
- path: output/umitools/versions.yml
md5sum: fd39e05042d354b3d8de49b617d3183d
md5sum: f75780d1de7860329b7fb4afeadc4bed
- path: output/umitools/test.dedup.bam
- path: output/umitools/test.umi_extract.log
- path: output/umitools/test.umi_extract_1.fastq.gz
- path: output/umitools/test.umi_extract_2.fastq.gz
- name: umitools dedup test_umitools_dedup_paired_end_stats
command: nextflow run ./tests/modules/umitools/dedup -entry test_umitools_dedup_paired_end_stats -c ./tests/config/nextflow.config -c ./tests/modules/umitools/dedup/nextflow.config
tags:
- umitools/dedup
- umitools
files:
- path: output/bwa/bwa/genome.amb
md5sum: 3a68b8b2287e07dd3f5f95f4344ba76e
- path: output/bwa/bwa/genome.ann
md5sum: c32e11f6c859f166c7525a9c1d583567
- path: output/bwa/bwa/genome.bwt
md5sum: 0469c30a1e239dd08f68afe66fde99da
- path: output/bwa/bwa/genome.pac
md5sum: 983e3d2cd6f36e2546e6d25a0da78d66
- path: output/bwa/bwa/genome.sa
md5sum: ab3952cabf026b48cd3eb5bccbb636d1
- path: output/bwa/test.bam
md5sum: e7dcbac1825bf210409b762dbb4fec8f
- path: output/samtools/test.bam.bai
md5sum: f75780d1de7860329b7fb4afeadc4bed
- path: output/umitools/test.dedup.bam
- path: output/umitools/test.dedup_edit_distance.tsv
md5sum: c247a49b58768e6e2e86a6c08483e612
- path: output/umitools/test.dedup_per_umi.tsv
md5sum: 10e35ca37f2bfb521ac6dd7314951a68
- path: output/umitools/test.dedup_per_umi_per_position.tsv
md5sum: 2e1a12e6f720510880068deddeefe063
- path: output/umitools/test.umi_extract.log
- path: output/umitools/test.umi_extract_1.fastq.gz
- path: output/umitools/test.umi_extract_2.fastq.gz