Skip to content

Avoid redundant index steps for shared refs #9983

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
pmoris wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Avoid redundant index steps for shared refs #9983

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
235a316
Avoid redundant index steps for shared refs
pmoris Feb 12, 2026
e784cbf
Retain sample-level metadata in index output channel
pmoris Feb 13, 2026
da400bc
Update test snapshots
pmoris Feb 13, 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
42 changes: 23 additions & 19 deletions subworkflows/nf-core/fastq_decontaminate_deacon_hostile/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,18 +14,19 @@
[
{
"id": "test",
"single_end": true
"single_end": true,
"index_id": "genome"
},
"test.idx:md5,84e4985c91800686db9c9dca28fabd1a"
"genome.idx:md5,84e4985c91800686db9c9dca28fabd1a"
]
],
"test.json"
],
"timestamp": "2026-02-16T13:18:48.758651665",
"meta": {
"nf-test": "0.9.3",
"nf-test": "0.9.4",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:28:11.112943934"
}
},
"sarscov2 - fastq - single-end - hostile": {
"content": [
Expand Down Expand Up @@ -53,11 +54,11 @@
],
"test_single.json"
],
"timestamp": "2026-02-13T09:27:36.178537005",
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:27:36.178537005"
}
},
"sarscov2 - fastq - paired-end - deacon": {
"content": [
Expand All @@ -77,18 +78,19 @@
[
{
"id": "test",
"single_end": false
"single_end": false,
"index_id": "genome"
},
"test.idx:md5,84e4985c91800686db9c9dca28fabd1a"
"genome.idx:md5,84e4985c91800686db9c9dca28fabd1a"
]
],
"test.json"
],
"timestamp": "2026-02-16T13:18:57.869797967",
"meta": {
"nf-test": "0.9.3",
"nf-test": "0.9.4",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:28:24.987001016"
}
},
"sarscov2 - fastq - paired-end - hostile": {
"content": [
Expand Down Expand Up @@ -119,11 +121,11 @@
],
"test_paired.json"
],
"timestamp": "2026-02-13T09:27:57.460392559",
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:27:57.460392559"
}
},
"sarscov2 - fastq - single-end - deacon - stub": {
"content": [
Expand All @@ -147,7 +149,8 @@
[
{
"id": "test",
"single_end": true
"single_end": true,
"index_id": "genome"
},
"genome.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
]
Expand All @@ -174,7 +177,8 @@
[
{
"id": "test",
"single_end": true
"single_end": true,
"index_id": "genome"
},
"genome.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
]
Expand All @@ -196,10 +200,10 @@
]
}
],
"timestamp": "2026-02-16T13:19:06.320189196",
"meta": {
"nf-test": "0.9.3",
"nf-test": "0.9.4",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:28:38.421681888"
}
}
}
41 changes: 34 additions & 7 deletions subworkflows/nf-core/fastq_index_filter_deacon/main.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,30 +8,57 @@ workflow FASTQ_INDEX_FILTER_DEACON {

main:

ch_fasta = ch_fasta_reads
.map { meta, fasta, reads -> [ meta, fasta ] }
// Check if fastqs are single-end or paired-end and run Deacon accordingly
ch_reads = ch_fasta_reads
.map { meta, fasta, reads ->
if (meta.single_end) {
if (reads instanceof List && reads.size() != 1) {
error("Error: Check your meta.single_end value. Single-end reads should contain one file only.")
}
return [ meta, reads ]
return [ meta, fasta, reads ]
} else {
if (!(reads instanceof List) || reads.size() != 2) {
error("Error: Check your meta.single_end value. Paired-end reads should contain two files; a forward and a reverse.")
}
return [ meta, reads ]
return [ meta, fasta, reads ]
}
}

DEACON_INDEX ( ch_fasta )
// Extract unique reference fasta files and create fasta-specific metadata
// This ensures each unique reference is indexed only once
ch_unique_fastas = ch_reads
.map { _meta, fasta, _reads -> fasta }
.unique()
.map { fasta ->
def meta_fasta = [ id: fasta.baseName ]
[ meta_fasta, fasta ]
}

// Index unique FASTA files only
DEACON_INDEX ( ch_unique_fastas )

// Match indexes back to original samples
ch_indexes = DEACON_INDEX.out.index
.map { meta_fasta, index -> [ meta_fasta.id, index ] }
ch_reads_with_index = ch_reads
.map { meta, fasta, reads ->
[ fasta.baseName, meta, reads ]
}
.combine(ch_indexes, by: 0)
.map { _fasta_id, meta, reads, index ->
[ meta, index, reads ]
}

// Filter reads using the matched index
DEACON_FILTER(ch_reads_with_index)

// Create output channel with indexes, the original sample-level metadata and index id
ch_index_with_meta = ch_reads_with_index
.map { meta, index, _reads -> [ meta + [ index_id: index.baseName ], index ] }

DEACON_FILTER(DEACON_INDEX.out.index.join(ch_reads))

emit:
index = DEACON_INDEX.out.index // channel: [ val(meta), [ index ] ]
index = ch_index_with_meta // channel: [ val(meta), [ index ] ]
fastq_filtered = DEACON_FILTER.out.fastq_filtered // channel: [ val(meta), [ fastq ] ]
summary = DEACON_FILTER.out.log // channel: [ val(meta), [ log ] ]
}
34 changes: 19 additions & 15 deletions subworkflows/nf-core/fastq_index_filter_deacon/tests/main.nf.test.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,8 @@
[
{
"id": "test",
"single_end": true
"single_end": true,
"index_id": "genome"
},
"genome.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
]
Expand Down Expand Up @@ -42,7 +43,8 @@
[
{
"id": "test",
"single_end": true
"single_end": true,
"index_id": "genome"
},
"genome.idx:md5,d41d8cd98f00b204e9800998ecf8427e"
]
Expand All @@ -58,21 +60,22 @@
]
}
],
"timestamp": "2026-02-13T15:10:09.178241099",
"meta": {
"nf-test": "0.9.3",
"nf-test": "0.9.4",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:19:12.052209052"
}
},
"sarscov2 - fastq - paired-end": {
"content": [
[
[
{
"id": "test",
"single_end": false
"single_end": false,
"index_id": "genome"
},
"test.idx:md5,84e4985c91800686db9c9dca28fabd1a"
"genome.idx:md5,84e4985c91800686db9c9dca28fabd1a"
]
],
[
Expand All @@ -89,21 +92,22 @@
],
"test.json"
],
"timestamp": "2026-02-13T15:09:59.820753976",
"meta": {
"nf-test": "0.9.3",
"nf-test": "0.9.4",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:19:03.559444963"
}
},
"sarscov2 - fastq - single-end": {
"content": [
[
[
{
"id": "test",
"single_end": true
"single_end": true,
"index_id": "genome"
},
"test.idx:md5,84e4985c91800686db9c9dca28fabd1a"
"genome.idx:md5,84e4985c91800686db9c9dca28fabd1a"
]
],
[
Expand All @@ -117,10 +121,10 @@
],
"test.json"
],
"timestamp": "2026-02-13T15:09:50.38883241",
"meta": {
"nf-test": "0.9.3",
"nf-test": "0.9.4",
"nextflow": "25.10.2"
},
"timestamp": "2026-02-13T09:18:55.835377502"
}
}
}