Merge branch 'master' into gatk_spark

This commit is contained in:
SusiJo 2022-06-02 16:24:39 +02:00 committed by GitHub
commit 1b93cde9ff
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
36 changed files with 785 additions and 110 deletions

View file

@ -10,6 +10,7 @@ process CNVKIT_BATCH {
input:
tuple val(meta), path(tumor), path(normal)
path fasta
path fasta_fai
path targets
path reference
@ -28,48 +29,167 @@ process CNVKIT_BATCH {
script:
def args = task.ext.args ?: ''
// 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" : "${tumor}"
def tumor_exists = tumor ? true : false
def normal_exists = normal ? true : false
// execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
def tumor_cram = tumor_exists && tumor.Extension == "cram" ? true : false
def normal_cram = normal_exists && normal.Extension == "cram" ? true : false
def tumor_bam = tumor_exists && tumor.Extension == "bam" ? true : false
def normal_bam = normal_exists && normal.Extension == "bam" ? true : false
def tumor_out = tumor_cram ? tumor.BaseName + ".bam" : "${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) = ["", "", ""]
def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : ""
if (normal_exists){
def normal_prefix = normal.BaseName
normal_out = is_cram ? "${normal_prefix}" + ".bam" : "${normal}"
normal_args = normal_prefix ? "--normal $normal_out" : ""
normal_out = normal_cram ? "${normal_prefix}" + ".bam" : "${normal}"
fasta_args = fasta ? "--fasta $fasta" : ""
// germline mode
// normal samples must be input without a flag
// requires flag --normal to be empty []
if(!tumor_exists){
tumor_out = "${normal_prefix}" + ".bam"
normal_args = "--normal "
}
// somatic mode
else {
normal_args = normal_prefix ? "--normal $normal_out" : ""
}
}
def target_args = targets ? "--targets $targets" : ""
def reference_args = reference ? "--reference $reference" : ""
"""
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
// somatic_mode cram_input
if (tumor_cram && normal_cram){
"""
samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out
samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $normal_out
cnvkit.py \\
batch \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\
$target_args \\
--processes $task.cpus \\
$args
cnvkit.py \\
batch \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\
$target_args \\
--processes $task.cpus \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}
// somatic_mode bam_input
else if (tumor_bam && normal_bam){
"""
cnvkit.py \\
batch \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\
$target_args \\
--processes $task.cpus \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}
// tumor_only_mode cram_input
else if(tumor_cram && !normal_exists){
"""
samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out
cnvkit.py \\
batch \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\
$target_args \\
--processes $task.cpus \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}
// tumor_only bam_input
else if(tumor_bam && !normal_exists){
"""
cnvkit.py \\
batch \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\
$target_args \\
--processes $task.cpus \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}
// germline mode cram_input
// normal_args must be --normal []
else if (normal_cram && !tumor_exists){
"""
samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $tumor_out
cnvkit.py \\
batch \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\
$target_args \\
--processes $task.cpus \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}
// germline mode bam_input
else if (normal_bam && !tumor_exists){
"""
cnvkit.py \\
batch \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\
$target_args \\
--processes $task.cpus \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}

View file

@ -29,6 +29,10 @@ input:
type: file
description: |
Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided)
- fasta_fai:
type: file
description: |
Input reference genome fasta index (optional, but recommended for cram_input)
- targetfile:
type: file
description: |

View file

@ -2,13 +2,15 @@ process DEEPTOOLS_BAMCOVERAGE {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::deeptools=3.5.1" : null)
conda (params.enable_conda ? "bioconda::deeptools=3.5.1 bioconda::samtools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/deeptools:3.5.1--py_0':
'quay.io/biocontainers/deeptools:3.5.1--py_0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-eb9e7907c7a753917c1e4d7a64384c047429618a:2c687053c0252667cca265c9f4118f2c205a604c-0':
'quay.io/biocontainers/mulled-v2-eb9e7907c7a753917c1e4d7a64384c047429618a:2c687053c0252667cca265c9f4118f2c205a604c-0' }"
input:
tuple val(meta), path(input), path(input_index)
path(fasta)
path(fasta_fai)
output:
tuple val(meta), path("*.bigWig") , emit: bigwig, optional: true
@ -22,16 +24,44 @@ process DEEPTOOLS_BAMCOVERAGE {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}.bigWig"
"""
bamCoverage \\
--bam $input \\
$args \\
--numberOfProcessors ${task.cpus} \\
--outFileName ${prefix}
// cram_input is currently not working with deeptools
// therefore it's required to convert cram to bam first
def is_cram = input.Extension == "cram" ? true : false
def input_out = is_cram ? input.BaseName + ".bam" : "${input}"
def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : ""
if (is_cram){
"""
samtools view -T $fasta $input $fai_reference -@ $task.cpus -o $input_out
samtools index -b $input_out -@ $task.cpus
bamCoverage \\
--bam $input_out \\
$args \\
--numberOfProcessors ${task.cpus} \\
--outFileName ${prefix}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
END_VERSIONS
"""
}
else {
"""
bamCoverage \\
--bam $input_out \\
$args \\
--numberOfProcessors ${task.cpus} \\
--outFileName ${prefix}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
END_VERSIONS
"""
}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
END_VERSIONS
"""
}

View file

@ -25,6 +25,14 @@ input:
type: file
description: BAM/CRAM index file
pattern: "*.{bai,crai}"
- fasta:
type: file
description: Reference file the CRAM file was created with (required with CRAM input)
pattern: "*.{fasta,fa}"
- fasta_fai:
type: file
description: Index of the reference file (optional, but recommended)
pattern: "*.{fai}"
output:
- meta:
@ -47,3 +55,4 @@ output:
authors:
- "@FriederikeHanssen"
- "@SusiJo"

View file

@ -11,8 +11,8 @@ RUN conda env create -f /environment.yml && conda clean -a
# Setup default ARG variables
ARG GENOME=GRCh38
ARG SPECIES=homo_sapiens
ARG VEP_VERSION=104
ARG VEP_TAG=104.3
ARG VEP_VERSION=105
ARG VEP_TAG=105.0
# Add conda installation dir to PATH (instead of doing 'conda activate')
ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH

View file

@ -20,9 +20,9 @@ build_push() {
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"
build_push "GRCh37" "homo_sapiens" "105" "105.0"
build_push "GRCh38" "homo_sapiens" "105" "105.0"
build_push "GRCm38" "mus_musculus" "102" "105.0"
build_push "GRCm39" "mus_musculus" "105" "105.0"
build_push "CanFam3.1" "canis_lupus_familiaris" "104" "105.0"
build_push "WBcel235" "caenorhabditis_elegans" "105" "105.0"

View file

@ -1,10 +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
name: nf-core-vep-105.0
channels:
- conda-forge
- bioconda
- defaults
dependencies:
- bioconda::ensembl-vep=104.3
- bioconda::ensembl-vep=105.0

View file

@ -11,7 +11,7 @@ process FILTLONG {
tuple val(meta), path(shortreads), path(longreads)
output:
tuple val(meta), path("${meta.id}_lr_filtlong.fastq.gz"), emit: reads
tuple val(meta), path("*.fastq.gz"), emit: reads
path "versions.yml" , emit: versions
when:
@ -21,12 +21,13 @@ process FILTLONG {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def short_reads = !shortreads ? "" : meta.single_end ? "-1 $shortreads" : "-1 ${shortreads[0]} -2 ${shortreads[1]}"
if ("$longreads" == "${prefix}.fastq.gz") error "Longread FASTQ input and output names are the same, set prefix in module configuration to disambiguate!"
"""
filtlong \\
$short_reads \\
$args \\
$longreads \\
| gzip -n > ${prefix}_lr_filtlong.fastq.gz
| gzip -n > ${prefix}.fastq.gz
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -0,0 +1,48 @@
process GATK4_CALIBRATEDRAGSTRMODEL {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
input:
tuple val(meta), path(bam), path(bam_index)
path fasta
path fasta_fai
path dict
path strtablefile
output:
tuple val(meta), path("*.txt") , emit: dragstr_model
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK CalibrateDragstrModel] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" CalibrateDragstrModel \\
--input $bam \\
--output ${prefix}.txt \\
--reference $fasta \\
--str-table-path $strtablefile \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
}

View file

@ -0,0 +1,70 @@
name: gatk4_calibratedragstrmodel
description: estimates the parameters for the DRAGstr model
keywords:
- gatk4
- bam
- cram
- sam
- calibratedragstrmodel
tools:
- gatk4:
description:
Genome Analysis Toolkit (GATK4). Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
with a primary focus on variant discovery and genotyping. Its powerful processing engine
and high-performance computing features make it capable of taking on projects of any size.
homepage: https://gatk.broadinstitute.org/hc/en-us
documentation: https://gatk.broadinstitute.org/hc/en-us/articles/360057441571-CalibrateDragstrModel-BETA-
tool_dev_url: https://github.com/broadinstitute/gatk
doi: 10.1158/1538-7445.AM2017-3590
licence: ["Apache-2.0"]
input:
# Only when we have meta
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: BAM/CRAM/SAM file
pattern: "*.{bam,cram,sam}"
- bam_index:
type: file
description: index of the BAM/CRAM/SAM file
pattern: "*.{bai,crai,sai}"
- fasta:
type: file
description: The reference FASTA file
pattern: "*.{fasta,fa}"
- fasta_fai:
type: file
description: The index of the reference FASTA file
pattern: "*.fai"
- dict:
type: file
description: The sequence dictionary of the reference FASTA file
pattern: "*.dict"
- strtablefile:
type: file
description: The StrTableFile zip folder of the reference FASTA file
pattern: "*.zip"
output:
#Only when we have meta
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- dragstr_model:
type: file
description: The DragSTR model
pattern: "*.txt"
authors:
- "@nvnieuwk"

View file

@ -0,0 +1,53 @@
process GATK4_COMPOSESTRTABLEFILE {
tag "$fasta"
label 'process_low'
conda (params.enable_conda ? "bioconda::gatk4=4.2.6.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gatk4:4.2.6.1--hdfd78af_0':
'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
input:
path(fasta)
path(fasta_fai)
path(dict)
output:
path "*.zip" , emit: str_table
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def avail_mem = 6
if (!task.memory) {
log.info '[GATK ComposeSTRTableFile] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" ComposeSTRTableFile \\
--reference $fasta \\
--output ${fasta.baseName}.zip \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
stub:
"""
touch test.zip
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
}

View file

@ -0,0 +1,43 @@
name: "gatk4_composestrtablefile"
description: This tool looks for low-complexity STR sequences along the reference that are later used to estimate the Dragstr model during single sample auto calibration CalibrateDragstrModel.
keywords:
- gatk4
- composestrtablefile
tools:
- gatk4:
description:
Genome Analysis Toolkit (GATK4). Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
with a primary focus on variant discovery and genotyping. Its powerful processing engine
and high-performance computing features make it capable of taking on projects of any size.
homepage: https://gatk.broadinstitute.org/hc/en-us
documentation: https://gatk.broadinstitute.org/hc/en-us/articles/4405451249819-ComposeSTRTableFile
tool_dev_url: https://github.com/broadinstitute/gatk
doi: 10.1158/1538-7445.AM2017-3590
licence: ["Apache-2.0"]
input:
- fasta:
type: file
description: FASTA reference file
pattern: "*.{fasta,fa}"
- fasta_fai:
type: file
description: index of the FASTA reference file
pattern: "*.fai"
- dict:
type: file
description: Sequence dictionary of the FASTA reference file
pattern: "*.dict"
output:
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- str_table:
type: file
description: A zipped folder containing the STR table files
pattern: "*.zip"
authors:
- "@nvnieuwk"

View file

@ -8,7 +8,7 @@ process GATK4_HAPLOTYPECALLER {
'quay.io/biocontainers/gatk4:4.2.6.1--hdfd78af_0' }"
input:
tuple val(meta), path(input), path(input_index), path(intervals)
tuple val(meta), path(input), path(input_index), path(intervals), path(dragstr_model)
path fasta
path fai
path dict
@ -28,6 +28,7 @@ process GATK4_HAPLOTYPECALLER {
def prefix = task.ext.prefix ?: "${meta.id}"
def dbsnp_command = dbsnp ? "--dbsnp $dbsnp" : ""
def interval_command = intervals ? "--intervals $intervals" : ""
def dragstr_command = dragstr_model ? "--dragstr-params-path $dragstr_model" : ""
def avail_mem = 3
if (!task.memory) {
@ -42,6 +43,7 @@ process GATK4_HAPLOTYPECALLER {
--reference $fasta \\
$dbsnp_command \\
$interval_command \\
$dragstr_command \\
--tmp-dir . \\
$args

View file

@ -32,6 +32,10 @@ input:
- intervals:
type: file
description: Bed file with the genomic regions included in the library (optional)
- dragstr_model:
type: file
description: Text file containing the DragSTR model of the used BAM/CRAM file (optional)
pattern: "*.txt"
- fasta:
type: file
description: The reference fasta file

View file

@ -13,6 +13,7 @@ process GATK4_MERGEVCFS {
output:
tuple val(meta), path('*.vcf.gz'), emit: vcf
tuple val(meta), path("*.tbi") , emit: tbi
path "versions.yml" , emit: versions
when:

View file

@ -35,6 +35,11 @@ output:
type: file
description: merged vcf file
pattern: "*.vcf.gz"
- tbi:
type: file
description: index files for the merged vcf files
pattern: "*.tbi"
- versions:
type: file
description: File containing software versions

View file

@ -21,12 +21,18 @@ process UNTAR {
def args = task.ext.args ?: ''
def args2 = task.ext.args2 ?: ''
untar = archive.toString() - '.tar.gz'
"""
mkdir output
tar \\
-C output --strip-components 1 \\
-xzvf \\
$args \\
$archive \\
$args2 \\
$args2
mv output ${untar}
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -743,6 +743,10 @@ gatk4/calculatecontamination:
- modules/gatk4/calculatecontamination/**
- tests/modules/gatk4/calculatecontamination/**
gatk4/calibratedragstrmodel:
- modules/gatk4/calibratedragstrmodel/**
- tests/modules/gatk4/calibratedragstrmodel/**
gatk4/cnnscorevariants:
- modules/gatk4/cnnscorevariants/**
- tests/modules/gatk4/cnnscorevariants/**
@ -751,6 +755,10 @@ gatk4/combinegvcfs:
- modules/gatk4/combinegvcfs/**
- tests/modules/gatk4/combinegvcfs/**
gatk4/composestrtablefile:
- modules/gatk4/composestrtablefile/**
- tests/modules/gatk4/composestrtablefile/**
gatk4/createsequencedictionary:
- modules/gatk4/createsequencedictionary/**
- tests/modules/gatk4/createsequencedictionary/**

View file

@ -23,6 +23,8 @@ params {
test_bed12 = "${test_data_dir}/genomics/sarscov2/genome/bed/test.bed12"
baits_bed = "${test_data_dir}/genomics/sarscov2/genome/bed/baits.bed"
reference_cnn = "${test_data_dir}/genomics/sarscov2/genome/cnn/reference.cnn"
kraken2 = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2"
kraken2_tar_gz = "${test_data_dir}/genomics/sarscov2/genome/db/kraken2.tar.gz"
@ -121,6 +123,7 @@ params {
genome_elfasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome.elfasta"
genome_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta"
genome_fasta_fai = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta.fai"
genome_strtablefile = "${test_data_dir}/genomics/homo_sapiens/genome/genome_strtablefile.zip"
genome_dict = "${test_data_dir}/genomics/homo_sapiens/genome/genome.dict"
genome_gff3 = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gff3"
genome_gtf = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gtf"
@ -146,6 +149,7 @@ params {
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 = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz"
genome_21_reference_cnn = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/reference_chr21.cnn"
dbsnp_146_hg38_elsites = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.elsites"
dbsnp_146_hg38_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz"
@ -262,6 +266,8 @@ params {
test_pileups_table = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
test2_pileups_table = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
test_paired_end_sorted_dragstrmodel = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_paired_end_sorted_dragstrmodel.txt"
test_genomicsdb_tar_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
test_pon_genomicsdb_tar_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_pon_genomicsdb.tar.gz"
@ -323,6 +329,8 @@ params {
test_sv_vcf = "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
test_pytor = "${test_data_dir}/genomics/homo_sapiens/illumina/pytor/test.pytor"
test_flowcell = "${test_data_dir}/genomics/homo_sapiens/illumina/bcl/flowcell.tar.gz"
}
'pacbio' {
primers = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"
@ -415,9 +423,6 @@ params {
'txt' {
hello = "${test_data_dir}/generic/txt/hello.txt"
}
'cnn' {
reference = "${test_data_dir}/generic/cnn/reference.cnn"
}
'cooler'{
test_pairix_pair_gz = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz"
test_pairix_pair_gz_px2 = "${test_data_dir}/genomics/homo_sapiens/cooler/cload/hg19/hg19.GM12878-MboI.pairs.subsample.blksrt.txt.gz.px2"

View file

@ -5,8 +5,9 @@ nextflow.enable.dsl = 2
include { CNVKIT_BATCH as CNVKIT_HYBRID } from '../../../../modules/cnvkit/batch/main.nf'
include { CNVKIT_BATCH as CNVKIT_WGS } from '../../../../modules/cnvkit/batch/main.nf'
include { CNVKIT_BATCH as CNVKIT_TUMORONLY } from '../../../../modules/cnvkit/batch/main.nf'
include { CNVKIT_BATCH as CNVKIT_GERMLINE } from '../../../../modules/cnvkit/batch/main.nf'
workflow test_cnvkit_hybrid {
workflow test_cnvkit_hybrid_somatic {
input = [
[ id:'test' ], // meta map
@ -16,10 +17,10 @@ workflow test_cnvkit_hybrid {
fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
targets = file(params.test_data['sarscov2']['genome']['baits_bed'], checkIfExists: true)
CNVKIT_HYBRID ( input, fasta, targets, [] )
CNVKIT_HYBRID ( input, fasta, [], targets, [] )
}
workflow test_cnvkit_wgs {
workflow test_cnvkit_wgs_somatic {
input = [
[ id:'test'], // meta map
@ -28,42 +29,71 @@ workflow test_cnvkit_wgs {
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
CNVKIT_WGS ( input, fasta, [], [] )
CNVKIT_WGS ( input, fasta, [], [], [] )
}
workflow test_cnvkit_cram {
workflow test_cnvkit_cram_wgs_somatic {
input = [
[ id:'test'], // meta map
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)
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
CNVKIT_WGS ( input, fasta, [], [] )
CNVKIT_WGS ( input, fasta, fasta_fai, [], [] )
}
workflow test_cnvkit_tumoronly {
workflow test_cnvkit_tumoronly_hybrid_bam {
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']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true),
[]
]
reference = file(params.test_data['generic']['cnn']['reference'], checkIfExists: true)
reference = file(params.test_data['homo_sapiens']['genome']['genome_21_reference_cnn'], checkIfExists: true)
CNVKIT_TUMORONLY ( input, [], [], reference )
CNVKIT_TUMORONLY ( input, [], [], [], reference )
}
workflow test_cnvkit_tumoronly_cram {
workflow test_cnvkit_tumoronly_hybrid_cram {
input = [
[ id:'test'], // meta map
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_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)
reference = file(params.test_data['homo_sapiens']['genome']['genome_21_reference_cnn'], checkIfExists: true)
CNVKIT_TUMORONLY ( input, fasta, [], reference )
CNVKIT_TUMORONLY ( input, fasta, [], [], reference )
}
workflow test_cnvkit_germline_hybrid_cram {
input = [
[ id:'test'], // meta map
[],
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_cram'], checkIfExists: true)
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
targets = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
CNVKIT_GERMLINE ( input, fasta, fasta_fai, targets, [])
}
workflow test_cnvkit_germline_hybrid_bam {
input = [
[ id:'test'], // meta map
[],
file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_recalibrated_sorted_bam'], checkIfExists: true)
]
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)
CNVKIT_GERMLINE ( input, fasta, [], targets, [])
}

View file

@ -1,5 +1,5 @@
- 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
- name: cnvkit batch test_cnvkit_hybrid_somatic
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_hybrid_somatic -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit
- cnvkit/batch
@ -26,8 +26,8 @@
- path: output/cnvkit/test.single_end.sorted.targetcoverage.cnn
md5sum: aa8a018b1d4d1e688c9f9f6ae01bf4d7
- 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
- name: cnvkit batch test_cnvkit_wgs_somatic
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_wgs_somatic -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit
- cnvkit/batch
@ -56,8 +56,8 @@
- path: output/cnvkit/test2.paired_end.sorted.targetcoverage.cnn
md5sum: 6ae6b3fce7299eedca6133d911c38fe1
- 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
- name: cnvkit batch test_cnvkit_cram_wgs_somatic
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_cram_wgs_somatic -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit
- cnvkit/batch
@ -86,22 +86,98 @@
- path: output/cnvkit/test2.paired_end.sorted.targetcoverage.cnn
md5sum: 6ae6b3fce7299eedca6133d911c38fe1
- 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
- name: cnvkit batch test_cnvkit_tumoronly_hybrid_bam
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly_hybrid_bam -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/reference.antitarget-tmp.bed
- path: output/cnvkit/reference.target-tmp.bed
md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
- path: output/cnvkit/reference_chr21.antitarget-tmp.bed
md5sum: 3d4d20f9f23b39970865d29ef239d20b
- path: output/cnvkit/reference_chr21.target-tmp.bed
md5sum: 657b25dbda8516624efa8cb2cf3716ca
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
md5sum: 067115082c4af4b64d58c0dc3a3642e4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
md5sum: f6adc75a0a86b7a921eca1b79a394cb0
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
md5sum: f7caeca04aba28b125ce26b511f42afb
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
md5sum: d9bdb71ce807051369577ee7f807a40c
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
md5sum: 2b56aac606ba6183d018b30ca58afcec
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
md5sum: e6d0190c1c37ce6e41f76ca5b24ccca3
- 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
- name: cnvkit batch test_cnvkit_tumoronly_hybrid_cram
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_tumoronly_hybrid_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
- path: output/cnvkit/reference.target-tmp.bed
md5sum: 26d25ff2d6c45b6d92169b3559c6acdb
- path: output/cnvkit/reference_chr21.antitarget-tmp.bed
md5sum: 3d4d20f9f23b39970865d29ef239d20b
- path: output/cnvkit/reference_chr21.target-tmp.bed
md5sum: 657b25dbda8516624efa8cb2cf3716ca
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
md5sum: 067115082c4af4b64d58c0dc3a3642e4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
md5sum: f6adc75a0a86b7a921eca1b79a394cb0
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
md5sum: f7caeca04aba28b125ce26b511f42afb
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
md5sum: d9bdb71ce807051369577ee7f807a40c
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
md5sum: 2b56aac606ba6183d018b30ca58afcec
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
md5sum: e6d0190c1c37ce6e41f76ca5b24ccca3
- name: cnvkit batch test_cnvkit_germline_hybrid_cram
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_germline_hybrid_cram -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/multi_intervals.antitarget.bed
md5sum: 3d4d20f9f23b39970865d29ef239d20b
- path: output/cnvkit/multi_intervals.target.bed
md5sum: 86d30493bb2e619a93f4ebc2923d29f3
- path: output/cnvkit/reference.cnn
md5sum: a09ee4be5dda1cf0f68073bdb3aad8ec
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
md5sum: 067115082c4af4b64d58c0dc3a3642e4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
md5sum: 68b62b75cd91b2ffe5633686fb943490
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
md5sum: df196edd72613c59186f4d87df3dc4a4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
md5sum: 3b4fc0cc73be78f978cfe2422470753e
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
md5sum: 4e67451dbcb6601fc3fa5dd7e570f1d4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
md5sum: b4a49faf170e436ec32dcc21ccc3ce8f
- name: cnvkit batch test_cnvkit_germline_hybrid_bam
command: nextflow run ./tests/modules/cnvkit/batch -entry test_cnvkit_germline_hybrid_bam -c ./tests/config/nextflow.config -c ./tests/modules/cnvkit/batch/nextflow.config
tags:
- cnvkit
- cnvkit/batch
files:
- path: output/cnvkit/multi_intervals.antitarget.bed
md5sum: 3d4d20f9f23b39970865d29ef239d20b
- path: output/cnvkit/multi_intervals.target.bed
md5sum: 86d30493bb2e619a93f4ebc2923d29f3
- path: output/cnvkit/reference.cnn
md5sum: a09ee4be5dda1cf0f68073bdb3aad8ec
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.antitargetcoverage.cnn
md5sum: 067115082c4af4b64d58c0dc3a3642e4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.bintest.cns
md5sum: 68b62b75cd91b2ffe5633686fb943490
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.call.cns
md5sum: df196edd72613c59186f4d87df3dc4a4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cnr
md5sum: 3b4fc0cc73be78f978cfe2422470753e
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.cns
md5sum: 4e67451dbcb6601fc3fa5dd7e570f1d4
- path: output/cnvkit/test2.paired_end.recalibrated.sorted.targetcoverage.cnn
md5sum: b4a49faf170e436ec32dcc21ccc3ce8f

View file

@ -12,7 +12,7 @@ workflow test_deeptools_bamcoverage_bam {
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
]
DEEPTOOLS_BAMCOVERAGE ( input )
DEEPTOOLS_BAMCOVERAGE ( input, [], [] )
}
workflow test_deeptools_bamcoverage_cram {
@ -22,6 +22,20 @@ workflow test_deeptools_bamcoverage_cram {
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true)
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
DEEPTOOLS_BAMCOVERAGE ( input )
DEEPTOOLS_BAMCOVERAGE ( input, fasta, fasta_fai)
}
workflow test_deeptools_bamcoverage_cram_no_fasta_fai {
input = [
[ id:'test', single_end:false ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true)
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
DEEPTOOLS_BAMCOVERAGE ( input, fasta, [])
}

View file

@ -1,21 +1,26 @@
- name: deeptools bamcoverage test_deeptools_bamcoverage_bam
command: nextflow run tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_bam -c tests/config/nextflow.config
command: nextflow run ./tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_bam -c ./tests/config/nextflow.config -c ./tests/modules/deeptools/bamcoverage/nextflow.config
tags:
- deeptools
- deeptools/bamcoverage
- deeptools
files:
- path: output/deeptools/test.bigWig
md5sum: 95fe9383a9e6c02aea6b785cf074274f
- path: output/deeptools/versions.yml
md5sum: 68c94e73b7a8c0935578bad61fea54c1
- name: deeptools bamcoverage test_deeptools_bamcoverage_cram
command: nextflow run tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_cram -c tests/config/nextflow.config
command: nextflow run ./tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_cram -c ./tests/config/nextflow.config -c ./tests/modules/deeptools/bamcoverage/nextflow.config
tags:
- deeptools
- deeptools/bamcoverage
- deeptools
files:
- path: output/deeptools/test.bigWig
md5sum: 95fe9383a9e6c02aea6b785cf074274f
- name: deeptools bamcoverage test_deeptools_bamcoverage_cram_no_fasta_fai
command: nextflow run ./tests/modules/deeptools/bamcoverage -entry test_deeptools_bamcoverage_cram_no_fasta_fai -c ./tests/config/nextflow.config -c ./tests/modules/deeptools/bamcoverage/nextflow.config
tags:
- deeptools/bamcoverage
- deeptools
files:
- path: output/deeptools/test.bigWig
md5sum: 95fe9383a9e6c02aea6b785cf074274f
- path: output/deeptools/versions.yml
md5sum: 665bbd2979c49bf3974a24bd44a88e94

View file

@ -3,5 +3,6 @@ process {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
ext.args = "--min_length 10"
ext.prefix = "test_lr"
}

View file

@ -3,7 +3,7 @@
tags:
- filtlong
files:
- path: output/filtlong/test_lr_filtlong.fastq.gz
- path: output/filtlong/test_lr.fastq.gz
contains:
- "@00068f7a-51b3-4933-8fc6-7d6e29181ff9"
@ -12,7 +12,7 @@
tags:
- filtlong
files:
- path: output/filtlong/test_lr_filtlong.fastq.gz
- path: output/filtlong/test_lr.fastq.gz
contains:
- "@00068f7a-51b3-4933-8fc6-7d6e29181ff9"
@ -21,6 +21,6 @@
tags:
- filtlong
files:
- path: output/filtlong/test_lr_filtlong.fastq.gz
- path: output/filtlong/test_lr.fastq.gz
contains:
- "@00068f7a-51b3-4933-8fc6-7d6e29181ff9"

View file

@ -0,0 +1,44 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { GATK4_CALIBRATEDRAGSTRMODEL } from '../../../../modules/gatk4/calibratedragstrmodel/main.nf'
workflow test_gatk4_calibratedragstrmodel_bam {
input = [
[ id:'test', single_end:false ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
strtablefile = file(params.test_data['homo_sapiens']['genome']['genome_strtablefile'], checkIfExists: true)
GATK4_CALIBRATEDRAGSTRMODEL ( input, fasta, fasta_fai, dict, strtablefile )
}
workflow test_gatk4_calibratedragstrmodel_cram {
input = [
[ id:'test', single_end:false ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true)
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
strtablefile = file(params.test_data['homo_sapiens']['genome']['genome_strtablefile'], checkIfExists: true)
GATK4_CALIBRATEDRAGSTRMODEL ( input, fasta, fasta_fai, dict, strtablefile )
}

View file

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

View file

@ -0,0 +1,17 @@
- name: gatk4 calibratedragstrmodel test_gatk4_calibratedragstrmodel_bam
command: nextflow run ./tests/modules/gatk4/calibratedragstrmodel -entry test_gatk4_calibratedragstrmodel_bam -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/calibratedragstrmodel/nextflow.config
tags:
- gatk4
- gatk4/calibratedragstrmodel
files:
- path: output/gatk4/test.txt
md5sum: 0a1a1583b157fa2251dd931ed165da4f
- name: gatk4 calibratedragstrmodel test_gatk4_calibratedragstrmodel_cram
command: nextflow run ./tests/modules/gatk4/calibratedragstrmodel -entry test_gatk4_calibratedragstrmodel_cram -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/calibratedragstrmodel/nextflow.config
tags:
- gatk4
- gatk4/calibratedragstrmodel
files:
- path: output/gatk4/test.txt
md5sum: 1aa7ab38023f724877b3323c5e6b9a4e

View file

@ -0,0 +1,16 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { GATK4_COMPOSESTRTABLEFILE } from '../../../../modules/gatk4/composestrtablefile/main.nf'
workflow test_gatk4_composestrtablefile {
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
fasta_fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
GATK4_COMPOSESTRTABLEFILE ( fasta, fasta_fai, dict )
}

View file

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

View file

@ -0,0 +1,7 @@
- name: gatk4 composestrtablefile test_gatk4_composestrtablefile
command: nextflow run ./tests/modules/gatk4/composestrtablefile -entry test_gatk4_composestrtablefile -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/composestrtablefile/nextflow.config
tags:
- gatk4/composestrtablefile
- gatk4
files:
- path: output/gatk4/genome.zip

View file

@ -8,6 +8,7 @@ workflow test_gatk4_haplotypecaller {
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),
[],
[]
]
fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
@ -21,6 +22,7 @@ workflow test_gatk4_haplotypecaller_cram {
input = [ [ id:'test' ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true),
[],
[]
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
@ -34,7 +36,8 @@ workflow test_gatk4_haplotypecaller_intervals_dbsnp {
input = [ [ id:'test' ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true),
file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)
file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true),
[]
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
@ -45,3 +48,20 @@ workflow test_gatk4_haplotypecaller_intervals_dbsnp {
GATK4_HAPLOTYPECALLER ( input, fasta, fai, dict, sites, sites_tbi )
}
workflow test_gatk4_haplotypecaller_dragstr_model {
input = [ [ id:'test' ], // meta map
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram'], checkIfExists: true),
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_cram_crai'], checkIfExists: true),
[],
file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_dragstrmodel'], checkIfExists: true)
]
fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
dict = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
sites = []
sites_tbi = []
GATK4_HAPLOTYPECALLER ( input, fasta, fai, dict, sites, sites_tbi )
}

View file

@ -6,7 +6,6 @@
files:
- path: output/gatk4/test.vcf.gz
- path: output/gatk4/test.vcf.gz.tbi
- path: output/gatk4/versions.yml
- name: gatk4 haplotypecaller test_gatk4_haplotypecaller_cram
command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_cram -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
@ -16,7 +15,6 @@
files:
- path: output/gatk4/test.vcf.gz
- path: output/gatk4/test.vcf.gz.tbi
- path: output/gatk4/versions.yml
- name: gatk4 haplotypecaller test_gatk4_haplotypecaller_intervals_dbsnp
command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_intervals_dbsnp -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
@ -26,4 +24,12 @@
files:
- path: output/gatk4/test.vcf.gz
- path: output/gatk4/test.vcf.gz.tbi
- path: output/gatk4/versions.yml
- name: gatk4 haplotypecaller test_gatk4_haplotypecaller_dragstr_model
command: nextflow run ./tests/modules/gatk4/haplotypecaller -entry test_gatk4_haplotypecaller_dragstr_model -c ./tests/config/nextflow.config -c ./tests/modules/gatk4/haplotypecaller/nextflow.config
tags:
- gatk4/haplotypecaller
- gatk4
files:
- path: output/gatk4/test.vcf.gz
- path: output/gatk4/test.vcf.gz.tbi

View file

@ -6,6 +6,8 @@
files:
- path: output/gatk4/test.vcf.gz
md5sum: 5b289bda88d3a3504f2e19ee8cff177c
- path: output/gatk4/test.vcf.gz.tbi
md5sum: a81673763b13086cfce9a23e72a35a16
- path: output/gatk4/versions.yml
- name: gatk4 mergevcfs test_gatk4_mergevcfs_no_dict

View file

@ -12,3 +12,13 @@ workflow test_untar {
UNTAR ( input )
}
workflow test_untar_different_output_path {
input = [
[],
file(params.test_data['homo_sapiens']['illumina']['test_flowcell'], checkIfExists: true)
]
UNTAR ( input )
}

View file

@ -1,5 +1,5 @@
- name: untar
command: nextflow run ./tests/modules/untar -entry test_untar -c ./tests/config/nextflow.config -c ./tests/modules/untar/nextflow.config
- name: untar test_untar
command: nextflow run ./tests/modules/untar -entry test_untar -c ./tests/config/nextflow.config -c ./tests/modules/untar/nextflow.config
tags:
- untar
files:
@ -9,3 +9,11 @@
md5sum: a033d00cf6759407010b21700938f543
- path: output/untar/kraken2/taxo.k2d
md5sum: 094d5891cdccf2f1468088855c214b2c
- name: untar test_untar_different_output_path
command: nextflow run ./tests/modules/untar -entry test_untar_different_output_path -c ./tests/config/nextflow.config -c ./tests/modules/untar/nextflow.config
tags:
- untar
files:
- path: output/untar/flowcell/RunInfo.xml
md5sum: 03038959f4dd181c86bc97ae71fe270a