From be1d35840d65ac0dfeccc13c511d99d2236f0f20 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Tue, 6 Apr 2021 17:48:16 +0200 Subject: [PATCH] Add EVA and EAGER@EVA --- .github/workflows/main.yml | 2 +- conf/eva.config | 2 +- conf/pipeline/eager/eva.config | 37 ++++++++++++++++++---------------- docs/eva.md | 2 +- docs/pipeline/eager/eva.md | 2 +- 5 files changed, 24 insertions(+), 21 deletions(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index c500dfb..96776a6 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -16,7 +16,7 @@ jobs: needs: test_all_profiles strategy: matrix: - profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'imperial', 'imperial_mb', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] + profile: ['abims', 'awsbatch', 'bi','bigpurple', 'binac', 'cbe', 'ccga_dx', 'ccga_med', 'cfc', 'cfc_dev', 'crick', 'denbi_qbic', 'ebc', 'eddie', 'eva', 'genotoul', 'genouest', 'gis', 'google', 'hebbe', 'icr_davros', 'ifb_core', 'imperial', 'imperial_mb', 'jax', 'kraken', 'mpcdf', 'munin', 'oist', 'pasteur', 'phoenix', 'prince', 'seg_globe', 'shh', 'uct_hpc', 'uppmax', 'utd_ganymede', 'uzh'] steps: - uses: actions/checkout@v1 - name: Install Nextflow diff --git a/conf/eva.config b/conf/eva.config index 497085d..c0a1d4f 100644 --- a/conf/eva.config +++ b/conf/eva.config @@ -49,4 +49,4 @@ profiles { debug { cleanup = false } -} +} \ No newline at end of file diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 46fddae..2e07d57 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -9,10 +9,12 @@ params { // Specific nf-core/eager process configuration process { + beforeScript = 'export _JAVA_OPTIONS="-XX:ParallelGCThreads=1 -XX:+PrintCommandLineFlags"' + maxRetries = 2 // Solution for clusterOptions comes from here: https://github.com/nextflow-io/nextflow/issues/332 + personal toMega conversion - clusterOptions = { "-S /bin/bash -j y -o output.log -l h_vmem=${task.memory.toMega().toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -j y -o output.log -l h_vmem=${task.memory.toGiga()}G,virtual_free=${task.memory.toGiga()}G" } withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } @@ -59,63 +61,64 @@ process { // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use withName: makeSeqDict { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -v JAVA_OPTS='-XX:ParallelGCThreads=1' -l h_vmem=${(task.memory.toGiga() + 3)}G,virtual_free=${(task.memory.toGiga() + 3)}G" } } withName: fastqc { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: adapter_removal { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(12000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(12000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: dedup { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: markduplicates { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(8000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(8000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() + 6)}G,virtual_free=${(task.memory.toGiga() + 6)}G" } } withName: malt { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: maltextract { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: multivcfanalyzer { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: mtnucratio { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: vcf2genome { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: qualimap { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(5000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(5000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() + 6)}G,virtual_free=${(task.memory.toGiga() + 6)}G" } } withName: damageprofiler { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(5000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(5000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() + 6)}G,virtual_free=${(task.memory.toGiga() + 6)}G" } } withName: circularmapper { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: circulargenerator { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(1000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } } withName: preseq { - clusterOptions = { "-S /bin/bash -l h_vmem=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M,virtual_free=${task.memory.toMega().plus(4000).toString().replaceAll(/[\sB]/,'')}M" } + clusterOptions = { "-S /bin/bash -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'ignore' } } } @@ -209,4 +212,4 @@ profiles { bwaalnl = 16500 } } -} +} \ No newline at end of file diff --git a/docs/eva.md b/docs/eva.md index 42575b2..9b83222 100644 --- a/docs/eva.md +++ b/docs/eva.md @@ -25,4 +25,4 @@ Note the following characteristics of this profile: ### debug -This simple profile just turns off automatic clean up of intermediate files. This can be useful for debugging. Specify e.g. with `-profile eva,archgen` +This simple profile just turns off automatic clean up of intermediate files. This can be useful for debugging. Specify e.g. with `-profile eva,archgen` \ No newline at end of file diff --git a/docs/pipeline/eager/eva.md b/docs/pipeline/eager/eva.md index a8dc563..71f4a2e 100644 --- a/docs/pipeline/eager/eva.md +++ b/docs/pipeline/eager/eva.md @@ -31,4 +31,4 @@ Specific configurations for eva has been made for eager. #### Pathogen - `pathogen_loose`: optimised for mapping of human aDNA reads (i.e. bwa aln defaults as `-l 16 -n 0.01`) -- `pathogen_strict`: optimised for mapping of human aDNA reads (i.e. bwa aln defaults as `-l 32, -n 0.1`) +- `pathogen_strict`: optimised for mapping of human aDNA reads (i.e. bwa aln defaults as `-l 32, -n 0.1`) \ No newline at end of file