Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Diamond/blastp updates #7381

Merged
merged 16 commits into from
Jan 30, 2025
Merged

Diamond/blastp updates #7381

Show file tree
Hide file tree
Changes from 8 commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
a547b87
version bump
vagkaratzas Jan 28, 2025
06d1bfa
remove unnecessary unzipping of gz fasta files
vagkaratzas Jan 28, 2025
7e3563b
label updated to process_high
vagkaratzas Jan 28, 2025
d7751f6
db from arg and switch changed to if else
vagkaratzas Jan 28, 2025
bfbd61a
stub updated with if else
vagkaratzas Jan 28, 2025
db9c72e
Merge branch 'master' into diamond/blastp
vagkaratzas Jan 28, 2025
62fc882
allowing gz outputs, test names updated and added stub test
vagkaratzas Jan 28, 2025
d756499
test for --compress flag added
vagkaratzas Jan 28, 2025
01bc4b0
meta.yml updated to include new gz outputs
vagkaratzas Jan 28, 2025
977b9ad
Merge branch 'master' into diamond/blastp
vagkaratzas Jan 30, 2025
06af373
outfmt instead of out_ext input arg, meta updated
vagkaratzas Jan 30, 2025
68d5789
Update modules/nf-core/diamond/blastp/main.nf
erikrikarddaniel Jan 30, 2025
3c6bd34
Update modules/nf-core/diamond/blastp/main.nf
erikrikarddaniel Jan 30, 2025
96d4027
Merge branch 'master' into diamond/blastp
erikrikarddaniel Jan 30, 2025
2df2b9c
Merge branch 'master' into diamond/blastp
vagkaratzas Jan 30, 2025
e096e23
Merge branch 'master' into diamond/blastp
vagkaratzas Jan 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion modules/nf-core/diamond/blastp/environment.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,4 @@ channels:
- conda-forge
- bioconda
dependencies:
- bioconda::diamond=2.1.8
- bioconda::diamond=2.1.11
99 changes: 51 additions & 48 deletions modules/nf-core/diamond/blastp/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
process DIAMOND_BLASTP {
tag "$meta.id"
label 'process_medium'
label 'process_high'

conda "${moduleDir}/environment.yml"
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/diamond:2.1.8--h43eeafb_0' :
'biocontainers/diamond:2.1.8--h43eeafb_0' }"
'https://depot.galaxyproject.org/singularity/diamond:2.1.11--h5ca1c30_0' :
'biocontainers/diamond:2.1.11--h5ca1c30_0' }"

input:
tuple val(meta) , path(fasta)
Expand All @@ -14,50 +14,49 @@ process DIAMOND_BLASTP {
val blast_columns

output:
tuple val(meta), path('*.blast'), optional: true, emit: blast
tuple val(meta), path('*.xml') , optional: true, emit: xml
tuple val(meta), path('*.txt') , optional: true, emit: txt
tuple val(meta), path('*.daa') , optional: true, emit: daa
tuple val(meta), path('*.sam') , optional: true, emit: sam
tuple val(meta), path('*.tsv') , optional: true, emit: tsv
tuple val(meta), path('*.paf') , optional: true, emit: paf
path "versions.yml" , emit: versions
tuple val(meta), path('*.{blast,blast.gz}'), optional: true, emit: blast
tuple val(meta), path('*.{xml,xml.gz}') , optional: true, emit: xml
tuple val(meta), path('*.{txt,txt.gz}') , optional: true, emit: txt
tuple val(meta), path('*.{daa,daa.gz}') , optional: true, emit: daa
tuple val(meta), path('*.{sam,sam.gz}') , optional: true, emit: sam
tuple val(meta), path('*.{tsv,tsv.gz}') , optional: true, emit: tsv
tuple val(meta), path('*.{paf,paf.gz}') , optional: true, emit: paf
path "versions.yml" , emit: versions

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

script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def is_compressed = fasta.getExtension() == "gz" ? true : false
def fasta_name = is_compressed ? fasta.getBaseName() : fasta
def columns = blast_columns ? "${blast_columns}" : ''
switch ( out_ext ) {
case "blast": outfmt = 0; break
case "xml": outfmt = 5; break
case "txt": outfmt = 6; break
case "daa": outfmt = 100; break
case "sam": outfmt = 101; break
case "tsv": outfmt = 102; break
case "paf": outfmt = 103; break
default:
outfmt = '6';
out_ext = 'txt';
log.warn("Unknown output file format provided (${out_ext}): selecting DIAMOND default of tabular BLAST output (txt)");
break
if (out_ext == "blast") {
outfmt = 0
} else if (out_ext == "xml") {
outfmt = 5
} else if (out_ext == "txt") {
outfmt = 6
} else if (out_ext == "daa") {
outfmt = 100
} else if (out_ext == "sam") {
outfmt = 101
} else if (out_ext == "tsv") {
outfmt = 102
} else if (out_ext == "paf") {
outfmt = 103
} else {
outfmt = '6'
out_ext = 'txt'
log.warn("Unknown output file format provided (${out_ext}): selecting DIAMOND default of tabular BLAST output (txt)")
erikrikarddaniel marked this conversation as resolved.
Show resolved Hide resolved
}
"""
if [ "${is_compressed}" == "true" ]; then
gzip -c -d ${fasta} > ${fasta_name}
fi

DB=`find -L ./ -name "*.dmnd" | sed 's/\\.dmnd\$//'`
if ( args =~ /--compress\s+1/ ) out_ext += '.gz'

"""
diamond \\
blastp \\
--threads ${task.cpus} \\
--db \$DB \\
--query ${fasta_name} \\
--db ${db} \\
--query ${fasta} \\
--outfmt ${outfmt} ${columns} \\
${args} \\
--out ${prefix}.${out_ext}
Expand All @@ -69,21 +68,25 @@ process DIAMOND_BLASTP {
"""

stub:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
switch ( out_ext ) {
case "blast": outfmt = 0; break
case "xml": outfmt = 5; break
case "txt": outfmt = 6; break
case "daa": outfmt = 100; break
case "sam": outfmt = 101; break
case "tsv": outfmt = 102; break
case "paf": outfmt = 103; break
default:
outfmt = '6';
out_ext = 'txt';
log.warn("Unknown output file format provided (${out_ext}): selecting DIAMOND default of tabular BLAST output (txt)");
break
if (out_ext == "blast") {
outfmt = 0
} else if (out_ext == "xml") {
outfmt = 5
} else if (out_ext == "txt") {
outfmt = 6
} else if (out_ext == "daa") {
outfmt = 100
} else if (out_ext == "sam") {
outfmt = 101
} else if (out_ext == "tsv") {
outfmt = 102
} else if (out_ext == "paf") {
outfmt = 103
} else {
outfmt = '6'
out_ext = 'txt'
log.warn("Unknown output file format provided (${out_ext}): selecting DIAMOND default of tabular BLAST output (txt)")
erikrikarddaniel marked this conversation as resolved.
Show resolved Hide resolved
}

"""
Expand Down
77 changes: 54 additions & 23 deletions modules/nf-core/diamond/blastp/tests/main.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,12 +23,9 @@ nextflow_process {
}
}

test("Should search for protein hits against a DIAMOND db and return a tab separated output file of hits") {
test("sarscov2 - proteome - txt") {

when {
params {
outdir = "$outputDir"
}
process {
"""
input[0] = [ [id:'test'], file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true) ]
Expand All @@ -42,22 +39,15 @@ nextflow_process {
then {
assertAll(
{ assert process.success },
{ assert snapshot(
process.out.txt,
process.out.versions
).match()
}
{ assert snapshot(process.out).match() }
)
}

}

test("Should search for zipped protein hits against a DIAMOND db and return a tab separated output file of hits") {
test("sarscov2 - proteome - gz - txt") {

when {
params {
outdir = "$outputDir"
}
process {
"""
input[0] = [ [id:'test'], file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta.gz', checkIfExists: true) ]
Expand All @@ -71,22 +61,15 @@ nextflow_process {
then {
assertAll(
{ assert process.success },
{ assert snapshot(
process.out.txt,
process.out.versions
).match("gz_txt")
}
{ assert snapshot(process.out).match("gz_txt")}
)
}

}

test("Should search for protein hits against a DIAMOND db and return a daa format file of hits") {
test("sarscov2 - proteome - daa") {

when {
params {
outdir = "$outputDir"
}
process {
"""
input[0] = [ [id:'test'], file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true) ]
Expand All @@ -101,7 +84,55 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert process.out.daa },
{ assert snapshot(process.out.versions).match() }
{ assert snapshot(process.out.versions).match("daa") }
)
}

}

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

config "./nextflow.config"

when {
process {
"""
input[0] = [ [id:'test'], file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true) ]
input[1] = DIAMOND_MAKEDB.out.db
input[2] = 'txt'
input[3] = 'qseqid qlen'
"""
}
}

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

}

test("sarscov2 - proteome - stub") {

options "-stub"

when {
process {
"""
input[0] = [ [id:'test'], file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true) ]
input[1] = DIAMOND_MAKEDB.out.db
input[2] = 'txt'
input[3] = 'qseqid qlen'
"""
}
}

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

Expand Down
Loading
Loading