Skip to content

feat(#6): extract GENOME_CLEAN + GENOME_CLEAN_BATCH → CLEAN_GENOMES subworkflow #20

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

Merged
hyphaltip merged 5 commits into from
Jun 29, 2026
Merged

feat(#6): extract GENOME_CLEAN + GENOME_CLEAN_BATCH → CLEAN_GENOMES subworkflow #20

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
58532d0
feat(#6): extract GENOME_CLEAN + GENOME_CLEAN_BATCH → modules/local/ …
hyphaltip Jun 29, 2026
9e4b3d1
feat(#7): extract MASKREPEAT_TANTAN_RUN → modules/local/ + MASK_GENOM…
hyphaltip Jun 29, 2026
ffbc841
feat(#8): extract SRA query/fetch processes → modules/local/ + FETCH_…
hyphaltip Jun 29, 2026
9cfc749
feat(#9): extract RNASEQ_PREPARE + FUNANNOTATE_TRAIN + FUNANNOTATE_PR…
hyphaltip Jun 29, 2026
f8c2063
feat(#10): extract FUNANNOTATE_ANNOTATE + FUNANNOTATE_UPDATE → ANNOTA…
hyphaltip Jun 29, 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
33 changes: 17 additions & 16 deletions conf/profile_annotate.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,7 @@ process {
queue = 'short'; cpus = 1; memory = '4 GB'; time = '30m'
}

withName: 'GENOME_CLEAN' {
withName: '.*:GENOME_CLEAN' {
// Full FCS-GX purge needs highmem (stages ~470 GB gx db into /dev/shm);
// with --skip_fcs it's a light decompress + length-filter.
queue = params.skip_fcs ? 'short' : 'highmem'
Expand All @@ -135,53 +135,54 @@ process {
time = params.skip_fcs ? '1h' : '6h'
}

withName: 'GENOME_CLEAN_BATCH' {
withName: '.*:GENOME_CLEAN_BATCH' {
// Stages the ~470 GB FCS-GX db into /dev/shm once, then cleans up to
// clean_batch_size genomes sequentially — needs highmem and a long walltime.
queue = 'highmem'; cpus = 16; memory = '500 GB'; time = '7d'
}

withName: 'MASKREPEAT_TANTAN_RUN' {
withName: '.*:MASKREPEAT_TANTAN_RUN' {
queue = 'short'; cpus = 8; memory = '16 GB'; time = '2h'
}

// SRA_QUERY (standalone, not in subworkflow) — matches bare name
withName: 'SRA_QUERY' {
queue = 'short'; cpus = 2; memory = '4 GB'; time = '60m'
maxForks = 10; errorStrategy = 'retry'; maxRetries = 2
}
withName: 'SRA_QUERY_BATCH' {
withName: '.*:SRA_QUERY_BATCH' {
queue = 'short'; cpus = 1; memory = '4 GB'; time = '2h'
maxForks = 10; errorStrategy = 'retry'; maxRetries = 2
}
withName: 'COLLECT_SRA_QUERY' {
withName: '.*:COLLECT_SRA_QUERY' {
queue = 'short'; cpus = 1; memory = '2 GB'; time = '20m'
}
withName: 'WRITE_EMPTY_READS' {
withName: '.*:WRITE_EMPTY_READS' {
queue = 'short'; cpus = 1; memory = '1 GB'; time = '5m'
}

withName: 'SRA_FETCH' {
withName: '.*:SRA_FETCH' {
errorStrategy = 'retry'; maxRetries = 3
queue = { task.attempt == 1 ? 'short' : 'epyc' }
memory = { task.attempt == 1 ? '48 GB' : '192 GB' }
time = { task.attempt == 1 ? '2h' : task.attempt == 2 ? '8h' : task.attempt == 3 ? '24h' : '48h' }
cpus = { task.attempt == 1 ? 24 : 32 }
}
withName: 'SRA_FETCH_SE' {
withName: '.*:SRA_FETCH_SE' {
errorStrategy = 'retry'; maxRetries = 3
queue = { task.attempt == 1 ? 'short' : 'epyc' }
memory = { task.attempt == 1 ? '48 GB' : '192 GB' }
time = { task.attempt == 1 ? '2h' : task.attempt == 2 ? '8h' : '24h' }
cpus = { task.attempt == 1 ? 24 : 32 }
}

withName: 'RNASEQ_PREPARE' {
withName: '.*:RNASEQ_PREPARE' {
queue = 'epyc'; cpus = 16
memory = { task.attempt == 1 ? '52 GB' : (48 + (task.attempt - 1) * 48) + ' GB' }
time = '120h'; maxRetries = 3
}

withName: 'FUNANNOTATE_TRAIN' {
withName: '.*:FUNANNOTATE_TRAIN' {
maxRetries = 3
queue = { task.attempt <= 2 ? 'epyc' : 'highmem' }
memory = { task.attempt == 1 ? '48 GB' : task.attempt == 2 ? '192 GB' : '256 GB' }
Expand All @@ -190,33 +191,33 @@ process {
clusterOptions = '-N 1 -n 1 --job-name=nf-TRAIN'
}

withName: 'FUNANNOTATE_PREDICT' {
withName: '.*:FUNANNOTATE_PREDICT' {
queue = 'epyc'
memory = { task.attempt == 1 ? '32 GB' : '64 GB' }
time = '72h'
cpus = { task.attempt == 1 ? 8 : 16 }
clusterOptions = '-N 1 -n 1 --job-name=nf-PREDICT'
}

withName: 'ANTISMASH_RUN' {
withName: '.*:ANTISMASH_RUN' {
queue = 'epyc'; cpus = 8; memory = '24 GB'; time = '8h'
}

withName: 'INTERPROSCAN_RUN' {
withName: '.*:INTERPROSCAN_RUN' {
queue = 'epyc'; cpus = 8; memory = '32 GB'; time = '60h'
}

withName: 'SIGNALP_RUN' {
withName: '.*:SIGNALP_RUN' {
// signalp6-gpu: GPU partition (gpu allows >2h; short_gpu if always ≤2h).
queue = 'gpu'
cpus = 16; memory = '64 GB'; time = '8h'
clusterOptions = '-N 1 -n 1 --gres=gpu:1'
}

withName: 'FUNANNOTATE_ANNOTATE' {
withName: '.*:FUNANNOTATE_ANNOTATE' {
queue = 'epyc'; cpus = 16; memory = '64 GB'; time = '24h'
}
withName: 'FUNANNOTATE_UPDATE' {
withName: '.*:FUNANNOTATE_UPDATE' {
queue = 'epyc'; cpus = 16; memory = '64 GB'; time = '48h'
}
}
Expand Down
Loading
Loading