Skip to content

Allow cellranger renaming to ignore irregular filename patterns #11646

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

Draft
tgelafr-pfzr wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

Allow cellranger renaming to ignore irregular filename patterns #11646

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b9e4d4a
Add logic for ignoring filename pattern and achieve parity between co…
tgelafr-pfzr May 12, 2026
99a64d0
Add tests, some debug
tgelafr-pfzr May 13, 2026
94d3751
Add tests for new renaming logic
May 14, 2026
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: 2 additions & 0 deletions modules/nf-core/cellranger/count/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ process CELLRANGER_COUNT {
input:
tuple val(meta), path(reads, stageAs: "fastq_???/*")
path reference
val skip_renaming
val ignore_filename_pattern
Comment on lines 7 to +11

output:
tuple val(meta), path("**/outs/**"), emit: outs
Expand Down
40 changes: 24 additions & 16 deletions modules/nf-core/cellranger/count/templates/cellranger_count.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,23 +38,31 @@ def chunk_iter(seq, size):
filename_pattern = r"([^a-zA-Z0-9])R1([^a-zA-Z0-9])"

for i, (r1, r2) in enumerate(chunk_iter(fastqs, 2), start=1):
# double escapes are required because nextflow processes this python 'template'
if re.sub(filename_pattern, r"\\1R2\\2", r1.name) != r2.name:
raise AssertionError(
dedent(
f"""\
We expect R1 and R2 of the same sample to have the same filename except for R1/R2.
This has been checked by replacing "R1" with "R2" in the first filename and comparing it to the second filename.
If you believe this check shouldn't have failed on your filenames, please report an issue on GitHub!

Files involved:
- {r1}
- {r2}
"""
if "${skip_renaming}" == "true": # nf variables are true/false, which are different from Python
resolved_name_r1 = r1.name
resolved_name_r2 = r2.name
else:
# double escapes are required because nextflow processes this python 'template'
if (re.sub(filename_pattern, r"\\1R2\\2", r1.name) != r2.name) and ("${ignore_filename_pattern}" == "false"):
raise AssertionError(
dedent(
f"""\
We expect R1 and R2 of the same sample to have the same filename except for R1/R2.
This has been checked by replacing "R1" with "R2" in the first filename and comparing it to the second filename.
If you believe this check shouldn't have failed on your filenames, please report an issue on GitHub!

Files involved:
- {r1}
- {r2}
Comment on lines +49 to +56
"""
)
)
)
r1.rename(fastq_all / f"{sample_id}_S1_L{i:03d}_R1_001.fastq.gz")
r2.rename(fastq_all / f"{sample_id}_S1_L{i:03d}_R2_001.fastq.gz")

resolved_name_r1 = f"{sample_id}_S1_L{i:03d}_R1_001.fastq.gz"
resolved_name_r2 = f"{sample_id}_S1_L{i:03d}_R2_001.fastq.gz"

r1.rename(fastq_all / resolved_name_r1)
r2.rename(fastq_all / resolved_name_r2)

# fmt: off
run(
Expand Down
81 changes: 81 additions & 0 deletions modules/nf-core/cellranger/count/tests/main.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,8 @@ nextflow_process {
]
]
input[1] = CELLRANGER_MKREF.out.reference
input[2] = false
input[3] = false
"""
}
}
Expand Down Expand Up @@ -90,6 +92,8 @@ nextflow_process {
]
]
input[1] = CELLRANGER_MKREF.out.reference
input[2] = false
input[3] = false
"""
}
}
Expand All @@ -102,5 +106,82 @@ nextflow_process {
}

}
test("10x example file - nonstandard filename renaming fails") {
config "./nextflow.config"
tag "cellranger_rename_logic"

when {
process {
"""
original_r1 = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/5k_cmvpos_tcells/fastqs/gex_1/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_1_S1_L001_R1_001.fastq.gz', checkIfExists: true)
original_r2 = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/5k_cmvpos_tcells/fastqs/gex_1/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_1_S1_L001_R2_001.fastq.gz', checkIfExists: true)

new_r1_loc = "${workDir}/fastqs/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_1.fastq.gz"
new_r2_loc = "${workDir}/fastqs/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_2.fastq.gz"

original_r1.copyTo(new_r1_loc)
original_r2.copyTo(new_r2_loc)

input[0] = [
[ id:'test_10x', single_end:false, strandedness:'auto' ], // meta map
[ file(new_r1_loc), file(new_r2_loc) ]
]
input[1] = CELLRANGER_MKREF.out.reference
input[2] = false
input[3] = false
"""
}
}

then { assert process.failed }
}
test("10x example file - nonstandard filename, rename succeeds with skipped validation") {
config "./nextflow.config"
tag "cellranger_rename_logic"

when {
process {
"""
original_r1 = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/5k_cmvpos_tcells/fastqs/gex_1/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_1_S1_L001_R1_001.fastq.gz', checkIfExists: true)
original_r2 = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/5k_cmvpos_tcells/fastqs/gex_1/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_1_S1_L001_R2_001.fastq.gz', checkIfExists: true)

new_r1_loc = "${workDir}/fastqs/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_1.fastq.gz"
new_r2_loc = "${workDir}/fastqs/subsampled_5k_human_antiCMV_T_TBNK_connect_GEX_2.fastq.gz"

original_r1.copyTo(new_r1_loc)
original_r2.copyTo(new_r2_loc)

input[0] = [
[ id:'test_10x', single_end:false, strandedness:'auto' ], // meta map
[ file(new_r1_loc), file(new_r2_loc) ]
]
input[1] = CELLRANGER_MKREF.out.reference
input[2] = false
input[3] = true
"""
}
}

then {
assertAll(
{ assert process.success },
{
assert snapshot(
process.out.versions_cellranger,
process.out.outs[0][1].findAll { file(it).name !in [
'web_summary.html', // unstable checksum
'possorted_genome_bam.bam.bai', // unstable checksum despite identical content, verified with samtools idxstats
'possorted_genome_bam.bam', // unstable checksum due to header
'barcodes.tsv.gz' // empty file in test data -> would raise linting error
]} + [
"possorted_genome_bam_samlines:" + sam(process.out.outs.get(0).get(1).find { file(it).name == "possorted_genome_bam.bam" }).getSamLinesMD5() // checksum is unstable when header is included
],
).match()
},
{ assert file(process.out.outs.get(0).get(1).find { file(it).name == 'web_summary.html' }).exists() },
{ assert file(process.out.outs.get(0).get(1).find { file(it).name == 'barcodes.tsv.gz' }).exists() },
{ assert file(process.out.outs.get(0).get(1).find { file(it).name == 'possorted_genome_bam.bam.bai' }).exists() },
)
}
}
}
31 changes: 27 additions & 4 deletions modules/nf-core/cellranger/count/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,11 +16,34 @@
"possorted_genome_bam_samlines:14b70a2253bcaf40b1c6428e5b66f7a0"
]
],
"timestamp": "2026-03-13T11:50:19.775498195",
"meta": {
"nf-test": "0.9.4",
"nextflow": "25.10.4"
}
},
"timestamp": "2026-03-13T11:50:19.775498195"
},
"10x example file - nonstandard filename, rename succeeds with skipped validation": {
"content": [
[
"versions.yml:md5,0d99b1cd733a51d67540d796e6b1e1f6"
],
[
"filtered_feature_bc_matrix.h5:md5,530804f5b2fdc9d262b4b6d32bde8b7b",
"features.tsv.gz:md5,9f93621be0bede2b75596ad255607633",
"matrix.mtx.gz:md5,925a0f46932cba157c44cb94e0c06314",
"metrics_summary.csv:md5,14a544ef1204f4f9d128bc15febb94cf",
"molecule_info.h5:md5,ac30e998aae699f09978be60d548635c",
"raw_feature_bc_matrix.h5:md5,803d3ffa688dccd898c073b300c23ff9",
"features.tsv.gz:md5,9f93621be0bede2b75596ad255607633",
"matrix.mtx.gz:md5,a030e644e8b57df71142e9e26c306b5e",
"possorted_genome_bam_samlines:14b70a2253bcaf40b1c6428e5b66f7a0"
]
],
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.04.8"
Comment on lines +43 to +44
},
"timestamp": "2026-05-14T14:00:50.314716225"
},
"10x example file - stub": {
"content": [
Expand Down Expand Up @@ -53,10 +76,10 @@
]
}
],
"timestamp": "2026-03-11T15:59:25.090371925",
"meta": {
"nf-test": "0.9.4",
"nextflow": "25.10.4"
}
},
"timestamp": "2026-03-11T15:59:25.090371925"
}
}
1 change: 1 addition & 0 deletions modules/nf-core/cellranger/multi/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ process CELLRANGER_MULTI {
path frna_sampleinfo , stageAs: "references/frna/*"
path ocm_barcodes , stageAs: "references/ocm/barcodes/*"
val skip_renaming
val ignore_filename_pattern

Comment on lines 26 to 30
output:
tuple val(meta), path("cellranger_multi_config.csv"), emit: config
Expand Down
2 changes: 1 addition & 1 deletion modules/nf-core/cellranger/multi/templates/cellranger_multi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ def chunk_iter(seq, size):

else:
# double escapes are required because nextflow processes this python 'template'
if re.sub(filename_pattern, r"\\1R2\\2", r1.name) != r2.name:
if (re.sub(filename_pattern, r"\\1R2\\2", r1.name) != r2.name) and ("${ignore_filename_pattern}" == "false"):
raise AssertionError(
dedent(
f"""\
Expand Down
Loading
Loading