Merge branch 'master' into bowtie2-test-fix

This commit is contained in:
Chris Cheshire 2022-05-13 12:05:48 +01:00 committed by GitHub
commit 9f6a1ae4a4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
16 changed files with 277 additions and 91 deletions

View file

@ -0,0 +1,40 @@
process GENOMESCOPE2 {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::genomescope2=2.0" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/genomescope2:2.0--py310r41hdfd78af_5':
'quay.io/biocontainers/genomescope2:2.0--py310r41hdfd78af_5' }"
input:
tuple val(meta), path(histogram)
output:
tuple val(meta), path("*_linear_plot.png") , emit: linear_plot_png
tuple val(meta), path("*_transformed_linear_plot.png"), emit: transformed_linear_plot_png
tuple val(meta), path("*_log_plot.png") , emit: log_plot_png
tuple val(meta), path("*_transformed_log_plot.png") , emit: transformed_log_plot_png
tuple val(meta), path("*_model.txt") , emit: model
tuple val(meta), path("*_summary.txt") , emit: summary
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
"""
genomescope2 \\
--input $histogram \\
$args \\
--output . \\
--name_prefix $prefix
cat <<-END_VERSIONS > versions.yml
'${task.process}':
genomescope2: \$( genomescope2 -v | sed 's/GenomeScope //' )
END_VERSIONS
"""
}

View file

@ -0,0 +1,67 @@
name: "genomescope2"
description: Estimate genome heterozygosity, repeat content, and size from sequencing reads using a kmer-based statistical approach
keywords:
- "genome size"
- "genome heterozygosity"
- "repeat content"
tools:
- "genomescope2":
description: "Reference-free profiling of polyploid genomes"
homepage: "http://qb.cshl.edu/genomescope/genomescope2.0/"
documentation: "https://github.com/tbenavi1/genomescope2.0/blob/master/README.md"
tool_dev_url: "https://github.com/tbenavi1/genomescope2.0"
doi: "https://doi.org/10.1038/s41467-020-14998-3"
licence: "['Apache License, Version 2.0 (Apache-2.0)']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- histogram:
type: file
description: A K-mer histogram file
pattern: "*.hist"
output:
- 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"
- linear_plot_png:
type: file
description: A genomescope2 linear plot in PNG format
pattern: "*_linear_plot.png"
- linear_plot_png:
type: file
description: A genomescope2 linear plot in PNG format
pattern: "*_linear_plot.png"
- transformed_linear_plot_png:
type: file
description: A genomescope2 transformed linear plot in PNG format
pattern: "*_transformed_linear_plot.png"
- log_plot_png:
type: file
description: A genomescope2 log plot in PNG format
pattern: "*_log_plot.png"
- transformed_log_plot_png:
type: file
description: A genomescope2 transformed log plot in PNG format
pattern: "*_transformed_log_plot.png"
- model:
type: file
description: Genomescope2 model fit summary
pattern: "*_model.txt"
- summary:
type: file
description: Genomescope2 histogram summary
pattern: "*_summary.txt"
authors:
- "@mahesh-panchal"

View file

@ -35,12 +35,13 @@ process RTGTOOLS_VCFEVAL {
def eval_regions = evaluation_regions ? "--evaluation-regions=$evaluation_regions" : ""
def truth_index = truth_vcf_tbi ? "" : "rtg index $truth_vcf"
def query_index = query_vcf_tbi ? "" : "rtg index $query_vcf"
def avail_mem = task.memory.toGiga() + "G"
"""
$truth_index
$query_index
rtg vcfeval \\
rtg RTG_MEM=$avail_mem vcfeval \\
$args \\
--baseline=$truth_vcf \\
$bed_regions \\

View file

@ -1,34 +0,0 @@
//
// Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
//
params.prefetch_options = [:]
params.fasterqdump_options = [:]
include { SRATOOLS_PREFETCH } from '../../../modules/sratools/prefetch/main' addParams( options: params.prefetch_options )
include { SRATOOLS_FASTERQDUMP } from '../../../modules/sratools/fasterqdump/main' addParams( options: params.fasterqdump_options )
workflow SRA_FASTQ {
take:
sra_ids // channel: [ val(meta), val(id) ]
main:
ch_versions = Channel.empty()
//
// Prefetch sequencing reads in SRA format.
//
SRATOOLS_PREFETCH ( sra_ids )
ch_versions = ch_versions.mix( SRATOOLS_PREFETCH.out.versions.first() )
//
// Convert the SRA format into one or more compressed FASTQ files.
//
SRATOOLS_FASTERQDUMP ( SRATOOLS_PREFETCH.out.sra )
ch_versions = ch_versions.mix( SRATOOLS_FASTERQDUMP.out.versions.first() )
emit:
reads = SRATOOLS_FASTERQDUMP.out.reads // channel: [ val(meta), [ reads ] ]
versions = ch_versions // channel: [ versions.yml ]
}

View file

@ -0,0 +1,38 @@
include { CUSTOM_SRATOOLSNCBISETTINGS } from '../../../modules/custom/sratoolsncbisettings/main'
include { SRATOOLS_PREFETCH } from '../../../modules/sratools/prefetch/main'
include { SRATOOLS_FASTERQDUMP } from '../../../modules/sratools/fasterqdump/main'
/**
* Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
*/
workflow SRAFASTQ {
take:
sra_ids // channel: [ val(meta), val(id) ]
main:
ch_versions = Channel.empty()
//
// Detect existing NCBI user settings or create new ones.
//
CUSTOM_SRATOOLSNCBISETTINGS()
def settings = CUSTOM_SRATOOLSNCBISETTINGS.out.ncbi_settings
ch_versions = ch_versions.mix( CUSTOM_SRATOOLSNCBISETTINGS.out.versions )
//
// Prefetch sequencing reads in SRA format.
//
SRATOOLS_PREFETCH ( sra_ids, settings )
ch_versions = ch_versions.mix( SRATOOLS_PREFETCH.out.versions.first() )
//
// Convert the SRA format into one or more compressed FASTQ files.
//
SRATOOLS_FASTERQDUMP ( SRATOOLS_PREFETCH.out.sra, settings )
ch_versions = ch_versions.mix( SRATOOLS_FASTERQDUMP.out.versions.first() )
emit:
reads = SRATOOLS_FASTERQDUMP.out.reads // channel: [ val(meta), [ reads ] ]
versions = ch_versions // channel: [ versions.yml ]
}

View file

@ -1,11 +1,14 @@
name: sra_fastq
description: Download FASTQ sequencing reads from the NCBI's Sequence Read Archive (SRA).
keywords:
- SRA
- NCBI
- sequencing
- FASTQ
- prefetch
- dump
- fasterq-dump
modules:
- custom/sratoolsncbisettings
- sratools/prefetch
- sratools/fasterqdump
input:
@ -17,7 +20,7 @@ input:
- id:
type: string
description: >
SRA identifier.
SRA run identifier.
# TODO Update when we decide on a standard for subworkflow docs
output:
- meta:

View file

@ -839,6 +839,10 @@ genmap/mappability:
- modules/genmap/mappability/**
- tests/modules/genmap/mappability/**
genomescope2:
- modules/genomescope2/**
- tests/modules/genomescope2/**
genrich:
- modules/genrich/**
- tests/modules/genrich/**
@ -1647,14 +1651,14 @@ samtools/bam2fq:
- modules/samtools/bam2fq/**
- tests/modules/samtools/bam2fq/**
samtools/convert:
- modules/samtools/convert/**
- tests/modules/samtools/convert/**
samtools/collatefastq:
- modules/samtools/collatefastq/**
- tests/modules/samtools/collatefastq/**
samtools/convert:
- modules/samtools/convert/**
- tests/modules/samtools/convert/**
samtools/depth:
- modules/samtools/depth/**
- tests/modules/samtools/depth/**

View file

@ -0,0 +1,19 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { MERYL_COUNT } from '../../../modules/meryl/count/main.nf'
include { MERYL_HISTOGRAM } from '../../../modules/meryl/histogram/main.nf'
include { GENOMESCOPE2 } from '../../../modules/genomescope2/main.nf'
workflow test_genomescope2 {
input = [
[ id:'test', single_end:false ], // meta map
file(params.test_data['bacteroides_fragilis']['illumina']['test1_1_fastq_gz'], checkIfExists: true)
]
MERYL_COUNT ( input )
MERYL_HISTOGRAM ( MERYL_COUNT.out.meryl_db )
GENOMESCOPE2 ( MERYL_HISTOGRAM.out.hist )
}

View file

@ -0,0 +1,13 @@
process {
publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
withName: 'MERYL.*' {
ext.args = 'k=21'
}
withName: 'GENOMESCOPE2' {
ext.args = '-k 21 -p 1'
}
}

View file

@ -0,0 +1,22 @@
- name: genomescope2 test_genomescope2
command: nextflow run tests/modules/genomescope2 -entry test_genomescope2 -c tests/config/nextflow.config
tags:
- genomescope2
files:
- path: output/genomescope2/test_linear_plot.png
md5sum: 94c165c5028156299a1d4d05766cac51
- path: output/genomescope2/test_log_plot.png
md5sum: 9d25ca463d92a0c73a893da7fd3979ba
- path: output/genomescope2/test_model.txt
md5sum: 3caf62f715f64a2f2b8fdff5d079cb84
- path: output/genomescope2/test_summary.txt
md5sum: 7452860e2cea99b85f3ff60daeac77f5
- path: output/genomescope2/test_transformed_linear_plot.png
md5sum: 99a64c1c18d8670f64cb863d4334abbb
- path: output/genomescope2/test_transformed_log_plot.png
md5sum: b4e029c9fb9987ca33b17392a691c1b4
- path: output/genomescope2/versions.yml
md5sum: 18afeb26f62a47f680b2bb3e27da9cbc
- path: output/meryl/test.hist
md5sum: f75362ab9cd70d96621b3690e952085f
- path: output/meryl/versions.yml

View file

@ -1,23 +0,0 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { SRA_FASTQ } from '../../../../subworkflows/nf-core/sra_fastq/main.nf' addParams( [:] )
workflow test_sra_fastq_single_end {
input = [
[ id:'test_single_end', single_end:true ], // meta map
'SRR13255544'
]
SRA_FASTQ ( input )
}
workflow test_sra_fastq_paired_end {
input = [
[ id:'test_paired_end', single_end:false ], // meta map
'SRR11140744'
]
SRA_FASTQ ( input )
}

View file

@ -1,27 +0,0 @@
- name: sra fastq single-end
command: nextflow run ./tests/subworkflows/nf-core/sra_fastq -entry test_sra_fastq_single_end -c tests/config/nextflow.config
tags:
- subworkflows
# - subworkflows/sra_fastq
# Modules
# - sratools
# - sratools/prefetch
# - sratools/fasterqdump
files:
- path: output/sratools/SRR13255544.fastq.gz
md5sum: 1054c7b71884acdb5eed8a378f18be82
- name: sra fastq paired-end
command: nextflow run ./tests/subworkflows/nf-core/sra_fastq -entry test_sra_fastq_paired_end -c tests/config/nextflow.config
tags:
- subworkflows
# - subworkflows/sra_fastq
# Modules
# - sratools
# - sratools/prefetch
# - sratools/fasterqdump
files:
- path: output/sratools/SRR11140744_1.fastq.gz
md5sum: 193809c784a4ea132ab2a253fa4f55b6
- path: output/sratools/SRR11140744_2.fastq.gz
md5sum: 3e3b3af3413f50a1685fd7b3f1456d4e

View file

@ -0,0 +1,29 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl = 2
include { SRAFASTQ } from '../../../../subworkflows/nf-core/srafastq/main.nf'
workflow test_srafastq_single_end {
input = Channel.of(
[
[ id:'test_single_end1', single_end:true ], // meta map
'DRR000774'
],
[
[ id:'test_single_end2', single_end:true ], // meta map
'DRR000775'
]
)
SRAFASTQ ( input )
}
workflow test_srafastq_paired_end {
input = [
[ id:'test_paired_end', single_end:false ], // meta map
'SRR11140744'
]
SRAFASTQ ( input )
}

View file

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

View file

@ -0,0 +1,29 @@
- name: srafastq single-end
command: nextflow run ./tests/subworkflows/nf-core/srafastq -entry test_srafastq_single_end -c tests/config/nextflow.config -c tests/subworkflows/nf-core/srafastq/nextflow.config
tags:
- subworkflows
# - subworkflows/srafastq
# Modules
# - sratools
# - sratools/prefetch
# - sratools/fasterqdump
files:
- path: output/sratools/DRR000774.fastq.gz
md5sum: 19029a1132115b55277a0d79ee089b49
- path: output/sratools/DRR000775.fastq.gz
md5sum: 59ff24c86ecb260752668c059c2a1eaf
- name: srafastq paired-end
command: nextflow run ./tests/subworkflows/nf-core/srafastq -entry test_srafastq_paired_end -c tests/config/nextflow.config -c tests/subworkflows/nf-core/srafastq/nextflow.config
tags:
- subworkflows
# - subworkflows/srafastq
# Modules
# - sratools
# - sratools/prefetch
# - sratools/fasterqdump
files:
- path: output/sratools/SRR11140744_1.fastq.gz
md5sum: 193809c784a4ea132ab2a253fa4f55b6
- path: output/sratools/SRR11140744_2.fastq.gz
md5sum: 3e3b3af3413f50a1685fd7b3f1456d4e