From 2af0e07c19a07106da0ddcd334431940aaa65260 Mon Sep 17 00:00:00 2001 From: LysianeBouchard Date: Tue, 17 Dec 2024 22:43:12 -0500 Subject: [PATCH] fix: CLIN-3453 add missing resources for exomiser process in config --- CHANGELOG.md | 1 + modules/local/exomiser/main.nf | 2 +- nextflow.config | 13 +++++++++++-- nextflow_schema.json | 2 +- 4 files changed, 14 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6d67a30..0375bcb 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -17,6 +17,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### `Fixed` - [#50](https://github.com/Ferlab-Ste-Justine/Post-processing-Pipeline/pull/50) Use container tag 1.20 for splitMultiAllelics process +- [#51](https://github.com/Ferlab-Ste-Justine/Post-processing-Pipeline/pull/51) Add missing ressources for exomiser process in configuration ### `Known issues` - The nf-core modules that we are using have a potential performance flaw. Typically, the regex used to describe the output files also match the input files (ex: "*.vcf"), which can cause unnecessary file transfers. This has already proven to cause issues on fusion. One fix could be to transfer the whole modules to local to perform the small change necessary to fix this. diff --git a/modules/local/exomiser/main.nf b/modules/local/exomiser/main.nf index 2a4b6e5..4b82784 100644 --- a/modules/local/exomiser/main.nf +++ b/modules/local/exomiser/main.nf @@ -1,6 +1,6 @@ process EXOMISER { - label 'process_low' + label 'process_medium' input: tuple val(meta), path(vcfFile), path(phenoFile), path(analysisFile) diff --git a/nextflow.config b/nextflow.config index 393eb34..d8aaa3b 100644 --- a/nextflow.config +++ b/nextflow.config @@ -58,7 +58,7 @@ params { //Resources optionsreferenceGenome //defaults expecting to be overwritten max_cpus = 16 - max_disk = '80.GB' + max_disk = '200.GB' max_time = '12.h' max_memory = '120.GB' @@ -223,7 +223,8 @@ env { } process { - disk = 40.GB + disk = 40.GB + withName: 'variantRecalibratorSNP|variantRecalibratorIndel|applyVQSRIndel|applyVQSRSNP|gatherVCF' { container = 'broadinstitute/gatk:4.5.0.0' } @@ -295,6 +296,14 @@ process { disk = { check_max( 80.GB * task.attempt, 'disk' ) } time = { check_max( 10.h * task.attempt, 'time' ) } } + withName: 'EXOMISER' { + errorStrategy = 'retry' + maxRetries = 2 + cpus = { check_max( 6 * task.attempt, 'cpus' ) } + memory = { check_max( 36.GB * task.attempt, 'memory' ) } + disk = { check_max( 150.GB * task.attempt, 'disk' ) } + time = { check_max( 10.h * task.attempt, 'time' ) } + } withName: 'writemeta' { container = 'ubuntu:24.10' } diff --git a/nextflow_schema.json b/nextflow_schema.json index 56a73e1..85edda0 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -170,7 +170,7 @@ }, "max_disk": { "type": "string", - "default": "80.GB", + "default": "200.GB", "description": "Maximum amount of disk space that can be requested for any single job.", "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$", "help_text": "Use to set an upper-limit for the disk space requirement for each process. Should be a string in the format integer-unit e.g. `--max_disk '8.GB'`"