Skip to content

Commit

Permalink
Merge branch 'master' into fix/cat-fastq
Browse files Browse the repository at this point in the history
  • Loading branch information
@nvnieuwk
nvnieuwk authored Feb 25, 2025
2 parents e8c180b + 26b0fc1 commit 21412d1
Show file tree
Hide file tree
Showing 26 changed files with 1,491 additions and 650 deletions.
7 changes: 7 additions & 0 deletions modules/nf-core/hmmer/hmmpress/environment.yml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
---
# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
channels:
- conda-forge
- bioconda
dependencies:
- bioconda::hmmer=3.4
48 changes: 48 additions & 0 deletions modules/nf-core/hmmer/hmmpress/main.nf
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
process HMMER_HMMPRESS {
tag "$meta.id"
label 'process_single'

conda "${moduleDir}/environment.yml"
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/hmmer:3.4--hdbdd923_1' :
'biocontainers/hmmer:3.4--hdbdd923_1' }"

input:
tuple val(meta), path(hmmfile)

output:
tuple val(meta), path("*.h3?"), emit: compressed_db
path "versions.yml" , emit: versions

when:
task.ext.when == null || task.ext.when

script:
def args = task.ext.args ?: ''

"""
hmmpress \\
$args \\
${hmmfile}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
hmmer: \$(echo \$(hmmpress -h | grep HMMER | sed 's/# HMMER //' | sed 's/ .*//' 2>&1))
END_VERSIONS
"""

stub:
def prefix = task.ext.prefix ?: "stub"

"""
touch ${prefix}.h3m
touch ${prefix}.h3i
touch ${prefix}.h3f
touch ${prefix}.h3p
cat <<-END_VERSIONS > versions.yml
"${task.process}":
hmmer: \$(echo \$(hmmpress -h | grep HMMER | sed 's/# HMMER //' | sed 's/ .*//' 2>&1))
END_VERSIONS
"""
}
47 changes: 47 additions & 0 deletions modules/nf-core/hmmer/hmmpress/meta.yml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
name: "hmmer_hmmpress"
description: compress and index profile database for hmmscan
keywords:
- hidden Markov model
- HMM
- hmmer
- hmmpress
- hmmscan
tools:
- "hmmer":
description: "Biosequence analysis using profile hidden Markov models"
homepage: "http://hmmer.org"
documentation: "http://hmmer.org/documentation.html"
tool_dev_url: "https://github.com/EddyRivasLab/hmmer"
doi: "10.1371/journal.pcbi.1002195"
licence: ["BSD"]
identifier: biotools:hmmer
input:
- - meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- hmmfile:
type: file
description: HMMER flatfile database of HMM profiles
pattern: "*"
output:
- compressed_db:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- "*.h3?":
type: list
description: Binary files with compressed profiles and their index
pattern: "*.h3?"
- versions:
- versions.yml:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@ochkalova"
maintainers:
- "@ochkalova"
66 changes: 66 additions & 0 deletions modules/nf-core/hmmer/hmmpress/tests/main.nf.test
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@

nextflow_process {

name "Test Process HMMER_HMMPRESS"
script "../main.nf"
process "HMMER_HMMPRESS"

tag "modules"
tag "modules_nfcore"
tag "hmmer"
tag "hmmer/hmmpress"
tag "gunzip"

setup {
run("GUNZIP") {
script "../../../gunzip"

process {
"""
input[0] = [
[ id:'test' ],
file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.hmm.gz', checkIfExists: true)
]
"""
}
}
}

test("sarscov2 - proteome - hmm - gz") {

when {
process {
"""
input[0] = GUNZIP.out.gunzip
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() }
)
}
}

test("sarscov2 - proteome - hmm - gz - stub") {
options '-stub'

when {
process {
"""
input[0] = GUNZIP.out.gunzip
"""
}
}

then {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() }
)
}
}

}
88 changes: 88 additions & 0 deletions modules/nf-core/hmmer/hmmpress/tests/main.nf.test.snap
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,88 @@
{
"sarscov2 - proteome - hmm - gz": {
"content": [
{
"0": [
[
{
"id": "test"
},
[
"proteome.hmm.h3f:md5,d0640e710a5eec56aa95a64e6dcb9971",
"proteome.hmm.h3i:md5,1e68ee61bfe47697e3df24b5551dbb82",
"proteome.hmm.h3m:md5,9fa27bd2fda0e8c037852301245dcbfb",
"proteome.hmm.h3p:md5,e73ab76f194340b797e8485464caa369"
]
]
],
"1": [
"versions.yml:md5,f5473ee4ad53142d92c79b5a0fe94bf6"
],
"compressed_db": [
[
{
"id": "test"
},
[
"proteome.hmm.h3f:md5,d0640e710a5eec56aa95a64e6dcb9971",
"proteome.hmm.h3i:md5,1e68ee61bfe47697e3df24b5551dbb82",
"proteome.hmm.h3m:md5,9fa27bd2fda0e8c037852301245dcbfb",
"proteome.hmm.h3p:md5,e73ab76f194340b797e8485464caa369"
]
]
],
"versions": [
"versions.yml:md5,f5473ee4ad53142d92c79b5a0fe94bf6"
]
}
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.10.4"
},
"timestamp": "2025-02-25T14:43:13.712539"
},
"sarscov2 - proteome - hmm - gz - stub": {
"content": [
{
"0": [
[
{
"id": "test"
},
[
"stub.h3f:md5,d41d8cd98f00b204e9800998ecf8427e",
"stub.h3i:md5,d41d8cd98f00b204e9800998ecf8427e",
"stub.h3m:md5,d41d8cd98f00b204e9800998ecf8427e",
"stub.h3p:md5,d41d8cd98f00b204e9800998ecf8427e"
]
]
],
"1": [
"versions.yml:md5,f5473ee4ad53142d92c79b5a0fe94bf6"
],
"compressed_db": [
[
{
"id": "test"
},
[
"stub.h3f:md5,d41d8cd98f00b204e9800998ecf8427e",
"stub.h3i:md5,d41d8cd98f00b204e9800998ecf8427e",
"stub.h3m:md5,d41d8cd98f00b204e9800998ecf8427e",
"stub.h3p:md5,d41d8cd98f00b204e9800998ecf8427e"
]
]
],
"versions": [
"versions.yml:md5,f5473ee4ad53142d92c79b5a0fe94bf6"
]
}
],
"meta": {
"nf-test": "0.9.0",
"nextflow": "24.10.4"
},
"timestamp": "2025-02-25T14:43:19.740161"
}
}
49 changes: 45 additions & 4 deletions modules/nf-core/quilt/quilt/main.nf
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,8 @@ process QUILT_QUILT {
'biocontainers/r-quilt:1.0.5--r43h06b5641_0' }"

input:
tuple val(meta), path(bams), path(bais), path(bamlist), path(reference_haplotype_file), path(reference_legend_file), val(chr), val(regions_start), val(regions_end), val(ngen), val(buffer), path(genetic_map_file)
tuple val(meta2), path(posfile), path(phasefile)
tuple val(meta3), path(fasta)
tuple val(meta), path(bams), path(bais), path(bamlist), path(samplename), path(reference_haplotype_file), path(reference_legend_file), path(posfile), path(phasefile), path(genfile), val(chr), val(regions_start), val(regions_end), val(ngen), val(buffer), path(genetic_map_file)
tuple val(meta2), path(fasta)

output:
tuple val(meta), path("*.vcf.gz"), emit: vcf
Expand All @@ -23,15 +22,17 @@ process QUILT_QUILT {
task.ext.when == null || task.ext.when

script:
def args = task.ext.args ?: ''
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def suffix = task.ext.suffix ?: "vcf.gz"
def extensions = bams.collect { it.extension }
def extension = extensions.flatten().unique()
def list_command = extension == ["bam"] ? "--bamlist=" :
extension == ["cram"] ? "--reference=${fasta} --cramlist=" : ""
def genetic_map_file_command = genetic_map_file ? "--genetic_map_file=${genetic_map_file}" : ""
def posfile_command = posfile ? "--posfile=${posfile}" : ""
def phasefile_command = phasefile ? "--phasefile=${phasefile}" : ""
def samplename_command = samplename ? "--sampleNames_file=${samplename}" : ""
if (!(args ==~ /.*--seed.*/)) {args += " --seed=1"}

"""
Expand All @@ -48,6 +49,7 @@ process QUILT_QUILT {
$genetic_map_file_command \\
$posfile_command \\
$phasefile_command \\
$samplename_command \\
--chr=$chr \\
--regionStart=$regions_start \\
--regionEnd=$regions_end \\
Expand All @@ -57,9 +59,48 @@ process QUILT_QUILT {
--outputdir="." \\
--reference_haplotype_file=$reference_haplotype_file \\
--reference_legend_file=$reference_legend_file \\
--output_filename=${prefix}.${suffix} \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
r-base: \$(Rscript -e "cat(strsplit(R.version[['version.string']], ' ')[[1]][3])")
r-quilt: \$(Rscript -e "cat(as.character(utils::packageVersion(\\"QUILT\\")))")
END_VERSIONS
"""

stub:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def suffix = task.ext.suffix ?: "vcf.gz"
def create_cmd = suffix.endsWith(".gz") ? "echo '' | gzip >" : "touch"
def make_plots = args.contains("--make_plots=TRUE")
def save_ref = args.contains("--save_prepared_reference=TRUE")
def nGibbsSamples = args.contains("--nGibbsSamples=") ? args.split("--nGibbsSamples=")[1].split(" ")[0] : 7
def n_seek_its = args.contains("--n_seek_its=") ? args.split("--n_seek_its=")[1].split(" ")[0] : 3

"""
${create_cmd} ${prefix}.${suffix}
touch ${prefix}.${suffix}.tbi
if [ "${save_ref}" == true ]
then
mkdir -p RData
touch "RData/QUILT_prepared_reference.${chr}.${regions_start}.${regions_end}.RData"
fi
if [ "${make_plots}" == true ]
then
mkdir -p plots
for nGibbs in {0..${nGibbsSamples}}
do
touch "plots/haps.${prefix}.${chr}.${regions_start}.${regions_end}_igs.\$((nGibbs+1)).0.truth.png"
for its in {1..${n_seek_its}}
do
touch "plots/haps.${prefix}.${chr}.${regions_start}.${regions_end}_igs.\$((nGibbs+1)).it\$its.gibbs.png"
done
done
fi
cat <<-END_VERSIONS > versions.yml
"${task.process}":
r-base: \$(Rscript -e "cat(strsplit(R.version[['version.string']], ' ')[[1]][3])")
Expand Down
Loading

0 comments on commit 21412d1

Please sign in to comment.