Skip to content

fix(custom/orfnormalise): treat ribotish GenomePos start as 0-based #12173

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

Open
pinin4fjords wants to merge 3 commits into
base: master
Choose a base branch
from
+65 −53
Open

fix(custom/orfnormalise): treat ribotish GenomePos start as 0-based #12173

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
8aa7c1f
fix(custom/orfnormalise): treat ribotish GenomePos start as 0-based
pinin4fjords Jun 26, 2026
6d272e8
refactor(custom/orfnormalise): drop dead ribotish Blocks branch
pinin4fjords Jun 30, 2026
67e70e8
Merge branch 'master' into custom/orfnormalise-ribotish-frame
pinin4fjords Jun 30, 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
20 changes: 11 additions & 9 deletions modules/nf-core/custom/orfnormalise/templates/orfnormalise.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -517,7 +517,8 @@ def _parse_ribotish_genpos(s):
m = _RIBOTISH_GENPOS_RE.match(s.strip())
if not m:
return None
return m.group(1), int(m.group(2)) - 1, int(m.group(3)), m.group(4)
# GenomePos is 0-based half-open (BED-style).
return m.group(1), int(m.group(2)), int(m.group(3)), m.group(4)


def parse_ribotish(path, transcripts, fields):
Expand Down Expand Up @@ -551,15 +552,16 @@ def parse_ribotish(path, transcripts, fields):
continue
chrom, start, end, strand = gp

blocks = parse_intervals(row.get("Blocks", ""), seps=(":", "-"))
if not blocks:
tx = transcripts.get(tid)
if tx is None:
# ribotish predict reports one genomic span (GenomePos), not
# per-exon blocks, so the exon structure is recovered by
# intersecting that span with the transcript's exons.
tx = transcripts.get(tid)
if tx is None:
blocks = [(start, end)]
else:
blocks = [(max(start, gs), min(end, ge)) for gs, ge in tx.exons if min(end, ge) > max(start, gs)]
if not blocks:
blocks = [(start, end)]
else:
blocks = [(max(start, gs), min(end, ge)) for gs, ge in tx.exons if min(end, ge) > max(start, gs)]
if not blocks:
blocks = [(start, end)]

rows.append(
{
Expand Down
22 changes: 16 additions & 6 deletions modules/nf-core/custom/orfnormalise/tests/main.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ nextflow_process {
"""
input[0] = channel.of([
[id: 'sample1'],
file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribocode.txt', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribocode.txt', checkIfExists: true),
'ribocode'
])
input[1] = channel.of([
Expand All @@ -39,6 +39,8 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() },
// every ORF must span a whole number of codons (frame guard)
{ assert path(process.out.bed12[0][1]).text.readLines().findAll { it.trim() }.every { it.split('\t')[10].split(',').findAll { s -> s }.collect { s -> s.toInteger() }.sum() % 3 == 0 } },
{ assert rows.size() > 0 },
{ assert rows.every { it[aa].toInteger() > 0 } },
{ assert rows.every { it[score] && it[score] != '' } },
Expand All @@ -57,7 +59,7 @@ nextflow_process {
"""
input[0] = channel.of([
[id: 'sample1'],
file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
'ribotish'
])
input[1] = channel.of([
Expand All @@ -80,6 +82,8 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() },
// every ORF must span a whole number of codons (frame guard)
{ assert path(process.out.bed12[0][1]).text.readLines().findAll { it.trim() }.every { it.split('\t')[10].split(',').findAll { s -> s }.collect { s -> s.toInteger() }.sum() % 3 == 0 } },
{ assert rows.size() > 0 },
{ assert rows.every { it[aa].toInteger() > 0 } },
{ assert rows.every { it[score] && it[score] != '' } },
Expand All @@ -95,7 +99,7 @@ nextflow_process {
"""
input[0] = channel.of([
[id: 'sample1'],
file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotricer.tsv', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotricer.tsv', checkIfExists: true),
'ribotricer'
])
input[1] = channel.of([
Expand Down Expand Up @@ -123,6 +127,8 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() },
// every ORF must span a whole number of codons (frame guard)
{ assert path(process.out.bed12[0][1]).text.readLines().findAll { it.trim() }.every { it.split('\t')[10].split(',').findAll { s -> s }.collect { s -> s.toInteger() }.sum() % 3 == 0 } },
{ assert rows.size() > 0 },
{ assert rows.every { it[aa].toInteger() > 0 } },
{ assert rows.every { it[score] && it[score] != '' } },
Expand All @@ -139,7 +145,7 @@ nextflow_process {
"""
input[0] = channel.of([
[id: 'sample1'],
file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.rpbp.predicted-orfs.bed.gz', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.rpbp.predicted-orfs.bed.gz', checkIfExists: true),
'rpbp'
])
input[1] = channel.of([
Expand All @@ -162,6 +168,8 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() },
// every ORF must span a whole number of codons (frame guard)
{ assert path(process.out.bed12[0][1]).text.readLines().findAll { it.trim() }.every { it.split('\t')[10].split(',').findAll { s -> s }.collect { s -> s.toInteger() }.sum() % 3 == 0 } },
{ assert rows.size() > 0 },
{ assert rows.every { it[aa].toInteger() > 0 } },
{ assert rows.every { it[score] && it[score] != '' && it[score].toDouble() > 0 } },
Expand All @@ -179,7 +187,7 @@ nextflow_process {
"""
input[0] = channel.of([
[id: 'cohort'],
file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/cohort.price.orfs.tsv', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/cohort.price.orfs.tsv', checkIfExists: true),
'price'
])
input[1] = channel.of([
Expand All @@ -206,6 +214,8 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(process.out).match() },
// every ORF must span a whole number of codons (frame guard)
{ assert path(process.out.bed12[0][1]).text.readLines().findAll { it.trim() }.every { it.split('\t')[10].split(',').findAll { s -> s }.collect { s -> s.toInteger() }.sum() % 3 == 0 } },
{ assert rows.size() > 0 },
{ assert rows.every { it[aa].toInteger() > 0 } },
{ assert rows.collect { it[cls] }.toSet().any { it != 'other' } },
Expand All @@ -222,7 +232,7 @@ nextflow_process {
"""
input[0] = channel.of([
[id: 'sample1'],
file('https://raw.githubusercontent.com/pinin4fjords/test-datasets/add-orf-prediction-fixtures/data/genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/riboseq_expression/orf_predictions/sample1.ribotish.pred.txt', checkIfExists: true),
'ribotish'
])
input[1] = channel.of([
Expand Down
32 changes: 16 additions & 16 deletions modules/nf-core/custom/orfnormalise/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,11 +42,11 @@
]
}
],
"timestamp": "2026-06-12T13:07:41.301245",
"meta": {
"nf-test": "0.9.5",
"nextflow": "25.10.4"
}
},
"timestamp": "2026-06-12T13:07:41.301245"
},
"homo_sapiens [chr20] - rpbp": {
"content": [
Expand Down Expand Up @@ -91,11 +91,11 @@
]
}
],
"timestamp": "2026-06-12T13:07:53.372563",
"meta": {
"nf-test": "0.9.5",
"nextflow": "25.10.4"
}
},
"timestamp": "2026-06-12T13:07:53.372563"
},
"homo_sapiens [chr20] - ribocode": {
"content": [
Expand Down Expand Up @@ -140,11 +140,11 @@
]
}
],
"timestamp": "2026-06-12T13:07:17.199267",
"meta": {
"nf-test": "0.9.5",
"nextflow": "25.10.4"
}
},
"timestamp": "2026-06-12T13:07:17.199267"
},
"homo_sapiens [chr20] - ribotish": {
"content": [
Expand All @@ -154,15 +154,15 @@
{
"id": "sample1"
},
"sample1.normalised.bed12:md5,83e35410ce60f5289a4956016ea81534"
"sample1.normalised.bed12:md5,1b3cb2249df360840aa062001653a85e"
]
],
"1": [
[
{
"id": "sample1"
},
"sample1.normalised.tsv:md5,b0ec626bdb9a80f7ae8450067fe059c8"
"sample1.normalised.tsv:md5,5b52abd1e50bab3722b50e4bbf379902"
]
],
"2": [
Expand All @@ -173,27 +173,27 @@
{
"id": "sample1"
},
"sample1.normalised.bed12:md5,83e35410ce60f5289a4956016ea81534"
"sample1.normalised.bed12:md5,1b3cb2249df360840aa062001653a85e"
]
],
"tsv": [
[
{
"id": "sample1"
},
"sample1.normalised.tsv:md5,b0ec626bdb9a80f7ae8450067fe059c8"
"sample1.normalised.tsv:md5,5b52abd1e50bab3722b50e4bbf379902"
]
],
"versions": [
"versions.yml:md5,e7fc396424c69f0969daec4a45c3de70"
]
}
],
"timestamp": "2026-06-12T13:07:28.989952",
"meta": {
"nf-test": "0.9.5",
"nextflow": "25.10.4"
}
"nf-test": "0.9.3",
"nextflow": "25.04.8"
},
"timestamp": "2026-06-26T13:34:16.887667785"
},
"homo_sapiens [chr19+chr22] - price": {
"content": [
Expand Down Expand Up @@ -238,10 +238,10 @@
]
}
],
"timestamp": "2026-06-12T13:07:59.997149",
"meta": {
"nf-test": "0.9.5",
"nextflow": "25.10.4"
}
},
"timestamp": "2026-06-12T13:07:59.997149"
}
}
Loading