Skip to content

Migrate ska/distance to topics #12778

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
mribeirodantas wants to merge 2 commits into
base: master
Choose a base branch
from
+71 −48
Open

Migrate ska/distance to topics #12778

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d29bdc7
Migrate ska/distance to topics
mribeirodantas Aug 24, 2026
391aa14
Make test pass both on macOS and Linux and different shells
mribeirodantas Aug 24, 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
12 changes: 1 addition & 11 deletions modules/nf-core/ska/distance/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ process SKA_DISTANCE {
tuple val(meta), path("*clusters.tsv") , emit: cluster_list , optional: true
tuple val(meta), path("*cluster*.txt") , emit: cluster_files, optional: true
tuple val(meta), path("*.dot") , emit: dot , optional: true
path "versions.yml" , emit: versions
tuple val("${task.process}"), val('ska'), eval("ska --version | grep Version | sed '1!d ; s/Version: //'"), emit: versions_ska, topic: versions

@LouisLeNezet LouisLeNezet Aug 24, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would the following works ?
We aim to avoid grep as it is sometimes not available depending on the platform and container.

Suggested change
tuple val("${task.process}"), val('ska'), eval("ska --version | grep Version | sed '1!d ; s/Version: //'"), emit: versions_ska, topic: versions
tuple val("${task.process}"), val('ska'), eval("ska --version | sed -n 's/Version: //p'"), emit: versions_ska, topic: versions


when:
task.ext.when == null || task.ext.when
Expand All @@ -31,11 +31,6 @@ process SKA_DISTANCE {
$arg_list \\
-o ${prefix} \\
$sketch_files

cat <<-END_VERSIONS > versions.yml
"${task.process}":
ska: \$(ska --version | grep Version |& sed '1!d ; s/Version: //')
END_VERSIONS
"""

stub:
Expand All @@ -53,10 +48,5 @@ process SKA_DISTANCE {
touch ${prefix}.cluster\${i}.txt
done
$output_dot

cat <<-END_VERSIONS > versions.yml
"${task.process}":
ska: \$(ska --version | grep Version |& sed '1!d ; s/Version: //')
END_VERSIONS
"""
}
33 changes: 24 additions & 9 deletions modules/nf-core/ska/distance/meta.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
name: "ska_distance"
description: Calculate pairwise distances and basic clustering from SKA sketches
keywords:
Expand All @@ -15,7 +14,8 @@ tools:
documentation: "https://github.com/simonrharris/SKA/wiki"
tool_dev_url: "https://github.com/simonrharris/SKA"
doi: "10.1101/453142"
licence: ["MIT"]
licence:
- "MIT"
identifier: ""

input:
Expand Down Expand Up @@ -47,7 +47,7 @@ output:
description: Pairwise distance table
pattern: "*distance.tsv"
ontologies:
- edam: "http://edamontology.org/format_3475"
- edam: "http://edamontology.org/format_3475" # TSV
cluster_list:
- - meta:
type: map
Expand Down Expand Up @@ -82,14 +82,29 @@ output:
description: DOT file for visualization
pattern: "*.dot"
ontologies: []
versions_ska:
- - ${task.process}:
type: string
description: The name of the process
- ska:
type: string
description: The name of the tool
- "ska --version | grep Version | sed '1!d ; s/Version: //'":
type: eval
description: The expression to obtain the version of the tool

topics:
versions:
- versions.yml:
type: file
description: File containing software versions
pattern: "versions.yml"
- - ${task.process}:
type: string
description: The name of the process
- ska:
type: string
description: The name of the tool
- "ska --version | grep Version | sed '1!d ; s/Version: //'":
type: eval
description: The expression to obtain the version of the tool

ontologies:
- edam: http://edamontology.org/format_3750 # YAML
authors:
- "@itrujnara"
maintainers:
Expand Down
10 changes: 6 additions & 4 deletions modules/nf-core/ska/distance/tests/main.nf.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,10 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(
process.out.versions,
path(process.out.distances[0][1]).csv(sep:"\t").rows,
process.out.versions_ska,
path(process.out.distances[0][1]).csv(sep:"\t").rows.collect { row ->
row.collectEntries { k, v -> [(k): (v in ['nan', '-nan'] ? 'nan' : v)] }
},
path(process.out.cluster_list[0][1]).csv(sep:"\t").rows,

@LouisLeNezet LouisLeNezet Aug 24, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is it necessary to check the content, or would a simple sanitizeOutput(process.out) be enough ?

process.out.dot
).match() }
Expand Down Expand Up @@ -102,9 +104,9 @@ nextflow_process {
assertAll(
{ assert process.success },
{ assert snapshot(
process.out.versions,
process.out.versions_ska,
path(process.out.distances[0][1]).csv(sep:"\t").columnNames.sort(),
path(process.out.distances[0][1]).csv(sep:"\t").rows[0].values().sort(),
path(process.out.distances[0][1]).csv(sep:"\t").rows[0].values().collect { v -> v in ['nan', '-nan'] ? 'nan' : v }.sort(),
path(process.out.cluster_list[0][1]).csv(sep:"\t").columnNames.sort(),
path(process.out.cluster_list[0][1]).csv(sep:"\t").columns["ID"].sort(),
path(process.out.cluster_list[0][1]).csv(sep:"\t").columns["Cluster__autocolour"].sort(),
Expand Down
64 changes: 40 additions & 24 deletions modules/nf-core/ska/distance/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,21 +37,29 @@
"test.dot:md5,d41d8cd98f00b204e9800998ecf8427e"
]
],
"versions": [
"versions.yml:md5,914078627d4223f14da56bb9dd72a667"
"versions_ska": [
[
"SKA_DISTANCE",
"ska",
"1.0"
]
]
}
],
"timestamp": "2026-08-23T21:13:57.031634",
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.10.3"
},
"timestamp": "2026-02-17T13:24:34.498999152"
"nf-test": "0.9.5",
"nextflow": "26.04.1"
}
},
"sarscov2 - plasmodium - skf": {
"content": [
[
"versions.yml:md5,914078627d4223f14da56bb9dd72a667"
[
"SKA_DISTANCE",
"ska",
"1.0"
]
],
[
{
Expand All @@ -61,7 +69,7 @@
"Matches": 0,
"Sample 2": "plasmodium_reduced",
"SNPs": 0,
"SNP distance": "-nan",
"SNP distance": "nan",
"Mash-like distance": 1
}
],
Expand All @@ -84,16 +92,20 @@
]
]
],
"timestamp": "2026-08-23T21:13:47.781661",
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.10.3"
},
"timestamp": "2026-02-17T13:24:29.184171536"
"nf-test": "0.9.5",
"nextflow": "26.04.1"
}
},
"sarscov2 - plasmodium - list": {
"content": [
[
"versions.yml:md5,914078627d4223f14da56bb9dd72a667"
[
"SKA_DISTANCE",
"ska",
"1.0"
]
],
[
"Jaccard Index",
Expand All @@ -112,7 +124,7 @@
0,
1,
2740,
"-nan",
"nan",
"plasmodium_reduced"
],
[
Expand All @@ -136,11 +148,11 @@
]
]
],
"timestamp": "2026-08-23T21:14:09.175944",
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.10.3"
},
"timestamp": "2026-02-17T14:36:59.237532349"
"nf-test": "0.9.5",
"nextflow": "26.04.1"
}
},
"sarscov2 - plasmodium - list - stub": {
"content": [
Expand Down Expand Up @@ -175,15 +187,19 @@
"dot": [

],
"versions": [
"versions.yml:md5,914078627d4223f14da56bb9dd72a667"
"versions_ska": [
[
"SKA_DISTANCE",
"ska",
"1.0"
]
]
}
],
"timestamp": "2026-08-23T21:14:20.454425",
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.10.3"
},
"timestamp": "2026-02-17T13:25:40.464938435"
"nf-test": "0.9.5",
"nextflow": "26.04.1"
}
}
}