From b4d5330c0e7d41fb3511e6f2d1e938374ae9dece Mon Sep 17 00:00:00 2001 From: Praveen Date: Tue, 14 Dec 2021 03:52:37 +0100 Subject: [PATCH 01/65] Added rnavar pipeline config for Munin --- conf/pipeline/rnavar/munin.config | 42 +++++++++++++++++++++++++++ docs/pipeline/rnavar/munin.md | 48 +++++++++++++++++++++++++++++++ pipeline/rnavar.config | 13 +++++++++ 3 files changed, 103 insertions(+) create mode 100644 conf/pipeline/rnavar/munin.config create mode 100644 docs/pipeline/rnavar/munin.md create mode 100644 pipeline/rnavar.config diff --git a/conf/pipeline/rnavar/munin.config b/conf/pipeline/rnavar/munin.config new file mode 100644 index 0000000..a970fe8 --- /dev/null +++ b/conf/pipeline/rnavar/munin.config @@ -0,0 +1,42 @@ +// rnavar/munin specific profile config + +params { + // Specific nf-core/configs params + config_profile_contact = 'Praveen Raj (@praveenraj2018)' + config_profile_description = 'nf-core/rnavar MUNIN profile provided by nf-core/configs' + config_profile_url = 'https://ki.se/forskning/barntumorbanken' + + // Specific nf-core/rnavar params + + igenomes_ignore = true + + // Genome references + fasta = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa' + fasta_fai = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai' + gtf = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf' + gene_bed = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed' + + // Known genome resources + dbsnp = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz' + dbsnp_tbi = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi' + known_indels = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz' + known_indels_tbi = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi' + + // STAR index + star_index = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/' + + // Annotation settings + annotation_cache = true + cadd_cache = true + cadd_indels = '/data1/cache/CADD/v1.4/InDels.tsv.gz' + cadd_indels_tbi = '/data1/cache/CADD/v1.4/InDels.tsv.gz.tbi' + cadd_wg_snvs = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz' + cadd_wg_snvs_tbi = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz.tbi' + snpeff_cache = '/data1/cache/snpEff/' + snpeff_db = 'GRCh38.99' + vep_cache = '/data1/cache/VEP/' + vep_genome = 'GRCh38' + vep_species = 'homo_sapiens' + vep_cache_version = '99' + +} diff --git a/docs/pipeline/rnavar/munin.md b/docs/pipeline/rnavar/munin.md new file mode 100644 index 0000000..2938fb2 --- /dev/null +++ b/docs/pipeline/rnavar/munin.md @@ -0,0 +1,48 @@ +# nf-core/configs: MUNIN rnavar specific configuration + +Extra specific configuration for rnavar pipeline + +## Usage + +To use, run the pipeline with `-profile munin`. + +This will download and launch the rnavar specific [`munin.config`](../../../conf/pipeline/rnavar/munin.config) which has been pre-configured with a setup suitable for the `MUNIN` cluster. + +Example: `nextflow run nf-core/rnavar -profile munin` + +## rnavar specific configurations for MUNIN + +Specific configurations for `MUNIN` has been made for rnavar. + +Genome references + +`fasta` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa` +`fasta_fai` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai` +`gtf` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf` +`gene_bed` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed` + +Known genome resources + +`dbsnp set to` `/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz` +`dbsnp_tbi set` to `/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi` +`known_indels set` to `/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz` +`known_indels_tbi` set to `/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi` + +STAR index + +`star_index` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/` + +Variant annotation configurations + +* Params `annotation_cache` and `cadd_cache` set to `true` +* Params `snpeff_db` set to `GRCh38.99` +* Params `vep_cache_version` set to `99` +* Params `vep_genome` set to `GRCh38` +* Path to `snpeff_cache`: `/data1/cache/snpEff/` +* Path to `vep_cache`: `/data1/cache/VEP/` +* Path to `pon`: `/data1/PON/vcfs/BTB.PON.vcf.gz` +* Path to `pon_index`: `/data1/PON/vcfs/BTB.PON.vcf.gz.tbi` +* Path to `cadd_indels`: `/data1/cache/CADD/v1.4/InDels.tsv.gz` +* Path to `cadd_indels_tbi`: `/data1/cache/CADD/v1.4/InDels.tsv.gz.tbi` +* Path to `cadd_wg_snvs`: `/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz` +* Path to `cadd_wg_snvs_tbi`: `/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz.tbi` diff --git a/pipeline/rnavar.config b/pipeline/rnavar.config new file mode 100644 index 0000000..108088f --- /dev/null +++ b/pipeline/rnavar.config @@ -0,0 +1,13 @@ +/* + * ------------------------------------------------- + * nfcore/rnavar custom profile Nextflow config file + * ------------------------------------------------- + * Config options for custom environments. + * Cluster-specific config options should be saved + * in the conf/pipeline/rnavar folder and imported + * under a profile name here. + */ + +profiles { + munin { includeConfig "${params.custom_config_base}/conf/pipeline/rnavar/munin.config" } +} From cc1fe5b5a0fcb1350e29991f137d72249e537cd2 Mon Sep 17 00:00:00 2001 From: Praveen Date: Tue, 14 Dec 2021 03:58:54 +0100 Subject: [PATCH 02/65] Addressed review feedback --- conf/pipeline/rnavar/munin.config | 44 +++++++++++++++---------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/conf/pipeline/rnavar/munin.config b/conf/pipeline/rnavar/munin.config index a970fe8..70e3ac6 100644 --- a/conf/pipeline/rnavar/munin.config +++ b/conf/pipeline/rnavar/munin.config @@ -8,35 +8,35 @@ params { // Specific nf-core/rnavar params - igenomes_ignore = true + igenomes_ignore = true // Genome references - fasta = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa' - fasta_fai = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai' - gtf = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf' - gene_bed = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed' + fasta = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa' + fasta_fai = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai' + gtf = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf' + gene_bed = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed' // Known genome resources - dbsnp = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz' - dbsnp_tbi = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi' - known_indels = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz' - known_indels_tbi = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi' + dbsnp = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz' + dbsnp_tbi = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi' + known_indels = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz' + known_indels_tbi = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi' // STAR index - star_index = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/' + star_index = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/' // Annotation settings - annotation_cache = true - cadd_cache = true - cadd_indels = '/data1/cache/CADD/v1.4/InDels.tsv.gz' - cadd_indels_tbi = '/data1/cache/CADD/v1.4/InDels.tsv.gz.tbi' - cadd_wg_snvs = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz' - cadd_wg_snvs_tbi = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz.tbi' - snpeff_cache = '/data1/cache/snpEff/' - snpeff_db = 'GRCh38.99' - vep_cache = '/data1/cache/VEP/' - vep_genome = 'GRCh38' - vep_species = 'homo_sapiens' - vep_cache_version = '99' + annotation_cache = true + cadd_cache = true + cadd_indels = '/data1/cache/CADD/v1.4/InDels.tsv.gz' + cadd_indels_tbi = '/data1/cache/CADD/v1.4/InDels.tsv.gz.tbi' + cadd_wg_snvs = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz' + cadd_wg_snvs_tbi = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz.tbi' + snpeff_cache = '/data1/cache/snpEff/' + snpeff_db = 'GRCh38.99' + vep_cache = '/data1/cache/VEP/' + vep_genome = 'GRCh38' + vep_species = 'homo_sapiens' + vep_cache_version = '99' } From 4c6e7262c2edc5908d6696c05ceeedc94892bdc2 Mon Sep 17 00:00:00 2001 From: Praveen Date: Tue, 14 Dec 2021 04:04:17 +0100 Subject: [PATCH 03/65] Updated README.md --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index c0a4378..97fa54a 100644 --- a/README.md +++ b/README.md @@ -190,6 +190,8 @@ Currently documentation is available for the following pipelines within specific * sarek * [MUNIN](docs/pipeline/sarek/munin.md) * [UPPMAX](docs/pipeline/sarek/uppmax.md) +* rnavar + * [MUNIN](docs/pipeline/rnavar/munin.md) ### Pipeline-specific documentation From 5e92e2ef11237dea90f1279758f17243f76b34e8 Mon Sep 17 00:00:00 2001 From: "Maxime U. Garcia" Date: Tue, 14 Dec 2021 16:10:31 +0100 Subject: [PATCH 04/65] Update conf/pipeline/rnavar/munin.config --- conf/pipeline/rnavar/munin.config | 42 +++++++++++++++---------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/conf/pipeline/rnavar/munin.config b/conf/pipeline/rnavar/munin.config index 70e3ac6..9a96357 100644 --- a/conf/pipeline/rnavar/munin.config +++ b/conf/pipeline/rnavar/munin.config @@ -11,32 +11,32 @@ params { igenomes_ignore = true // Genome references - fasta = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa' - fasta_fai = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai' - gtf = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf' - gene_bed = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed' + fasta = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa' + fasta_fai = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai' + gtf = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf' + gene_bed = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed' // Known genome resources - dbsnp = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz' - dbsnp_tbi = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi' - known_indels = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz' - known_indels_tbi = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi' + dbsnp = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz' + dbsnp_tbi = '/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi' + known_indels = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz' + known_indels_tbi = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi' // STAR index - star_index = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/' + star_index = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/' // Annotation settings - annotation_cache = true - cadd_cache = true - cadd_indels = '/data1/cache/CADD/v1.4/InDels.tsv.gz' - cadd_indels_tbi = '/data1/cache/CADD/v1.4/InDels.tsv.gz.tbi' - cadd_wg_snvs = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz' - cadd_wg_snvs_tbi = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz.tbi' - snpeff_cache = '/data1/cache/snpEff/' - snpeff_db = 'GRCh38.99' - vep_cache = '/data1/cache/VEP/' - vep_genome = 'GRCh38' - vep_species = 'homo_sapiens' - vep_cache_version = '99' + annotation_cache = true + cadd_cache = true + cadd_indels = '/data1/cache/CADD/v1.4/InDels.tsv.gz' + cadd_indels_tbi = '/data1/cache/CADD/v1.4/InDels.tsv.gz.tbi' + cadd_wg_snvs = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz' + cadd_wg_snvs_tbi = '/data1/cache/CADD/v1.4/whole_genome_SNVs.tsv.gz.tbi' + snpeff_cache = '/data1/cache/snpEff/' + snpeff_db = 'GRCh38.99' + vep_cache = '/data1/cache/VEP/' + vep_genome = 'GRCh38' + vep_species = 'homo_sapiens' + vep_cache_version = '99' } From 0557f4e0622915bf07801e6d268e08b56e53b6d0 Mon Sep 17 00:00:00 2001 From: praveenraj2018 <43108054+praveenraj2018@users.noreply.github.com> Date: Tue, 14 Dec 2021 21:15:12 +0100 Subject: [PATCH 05/65] Renamed star_index directory --- conf/pipeline/rnavar/munin.config | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/conf/pipeline/rnavar/munin.config b/conf/pipeline/rnavar/munin.config index 9a96357..c2c8335 100644 --- a/conf/pipeline/rnavar/munin.config +++ b/conf/pipeline/rnavar/munin.config @@ -23,8 +23,9 @@ params { known_indels_tbi = '/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi' // STAR index - star_index = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/' - + star_index = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/STAR.2.7.9a_2x151bp/' + read_length = 151 + // Annotation settings annotation_cache = true cadd_cache = true From 00a3ed0fa60b055e005b8e75eb05c127d3b75d11 Mon Sep 17 00:00:00 2001 From: praveenraj2018 <43108054+praveenraj2018@users.noreply.github.com> Date: Tue, 14 Dec 2021 21:24:18 +0100 Subject: [PATCH 06/65] Formatting --- docs/pipeline/rnavar/munin.md | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/docs/pipeline/rnavar/munin.md b/docs/pipeline/rnavar/munin.md index 2938fb2..e4fd11f 100644 --- a/docs/pipeline/rnavar/munin.md +++ b/docs/pipeline/rnavar/munin.md @@ -16,21 +16,22 @@ Specific configurations for `MUNIN` has been made for rnavar. Genome references -`fasta` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa` -`fasta_fai` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai` -`gtf` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf` -`gene_bed` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed` +* Path to `fasta`: `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa` +* Path to `fasta_fai`: `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai` +* Path to `gtf`: `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf` +* Path to `gene_bed`: `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.bed` Known genome resources -`dbsnp set to` `/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz` -`dbsnp_tbi set` to `/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi` -`known_indels set` to `/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz` -`known_indels_tbi` set to `/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi` +* Path to `dbsnp`: `/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz` +* Path to `dbsnp_tbi`: `/data1/references/annotations/GATK_bundle/dbsnp_146.hg38.vcf.gz.tbi` +* Path to `known_indels`: `/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz` +* Path to `known_indels_tbi`: `/data1/references/annotations/GATK_bundle/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz.tbi` STAR index -`star_index` set to `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/star150bp.idx/` +* Path to `star_index`: `/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/STAR.2.7.9a_2x151bp/` +* Params `read_length` set to `151` Variant annotation configurations From 306c802b4ec66abd722402a8d5ad7ccf3d2a1b08 Mon Sep 17 00:00:00 2001 From: Venkat Malladi Date: Thu, 16 Dec 2021 09:27:23 -0600 Subject: [PATCH 07/65] Fix name of Params --- conf/azurebatch.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/azurebatch.config b/conf/azurebatch.config index 0fbb5c4..bdf13de 100644 --- a/conf/azurebatch.config +++ b/conf/azurebatch.config @@ -1,6 +1,6 @@ //Nextflow config file for running on Azure batch params { - config_profile_description = 'AWSBATCH Cloud Profile' + config_profile_description = 'Azure BATCH Cloud Profile' config_profile_contact = 'Venkat Malladi (@vsmalladi)' config_profile_url = 'https://azure.microsoft.com/services/batch/' From 87e4ece034fcb076d81bbc2798e1ecbd94871da4 Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Fri, 17 Dec 2021 00:36:51 -0500 Subject: [PATCH 08/65] Add files via upload --- conf/nihbiowulf.config | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 conf/nihbiowulf.config diff --git a/conf/nihbiowulf.config b/conf/nihbiowulf.config new file mode 100644 index 0000000..5c035ba --- /dev/null +++ b/conf/nihbiowulf.config @@ -0,0 +1,38 @@ +//Profile config names for nf-core/configs +params { + config_profile_description = 'National Institutes of Health, USA: Biowulf nf-core config' + config_profile_contact = 'Kevin Brick (@kevbrick)' + config_profile_url = 'https://hpc.nih.gov/apps/nextflow.html' + max_memory = 224.GB + max_cpus = 32 + max_time = 72.h + + igenomes_base = '/fdb/igenomes/' +} + +process { + scratch = '/lscratch/$SLURM_JOBID' + maxForks = 100 +} + +profiles { + local { + process.executor = 'local' + } + + slurm { + process.executor = 'slurm' + executor.$slurm.pollInterval = '1 min' + executor.$slurm.queueStatInterval = '5 min' + executor.queueSize = 100 + executor.$slurm.submitRateLimit = '6/1min' + process.clusterOptions = ' --gres=lscratch:600 --signal USR2@20' + } +} + +singularity { + enabled = true + autoMounts = true + envWhitelist='https_proxy,http_proxy,ftp_proxy,DISPLAY,SLURM_JOBID' + runOptions = ' -B /lscratch -B /fdb/igenomes/ --env TMPDIR="/lscratch/$SLURM_JOBID" ' +} \ No newline at end of file From 9cf4f69ff31533c840abafc5812502c91e71cb3b Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Fri, 17 Dec 2021 00:37:11 -0500 Subject: [PATCH 09/65] Add files via upload --- docs/nihbiowulf.md | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 docs/nihbiowulf.md diff --git a/docs/nihbiowulf.md b/docs/nihbiowulf.md new file mode 100644 index 0000000..f83894d --- /dev/null +++ b/docs/nihbiowulf.md @@ -0,0 +1,24 @@ +# nf-core/configs: nihbiowulf Configuration +nf-core pipelines have been configured for use on the Biowulf cluster at the NIH. + +To use, run the pipeline with `-profile nihbiowulf`. This will download and launch the [`profile.config`](../conf/profile.config) which has been pre-configured with a setup suitable for the Biowulf cluster at NIH. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. + +## Below are non-mandatory information e.g. on modules to load etc + +Before running the pipeline you will need to load Nextflow and Singularity using the environment module system on Biowulf. You can do this by issuing the commands below: + +```bash +## Load Nextflow and Singularity environment modules +module purge +module load nextflow +module load singularity +``` + +## Below are non-mandatory information on iGenomes specific configuration + +A partial local copy of the iGenomes resource is available on Biowulf. This is a copy of the Illumina iGenomes resource from several years ago and is not up-to-date with the s3-hosted nf-core iGenomes. There are some structural differences of note. In particular, if using BWA, the igenomes.conf should be modified to specify the BWA version folder, otherwise the BWA module will fail to find an appropriate index. To date, this is the only issue, however functionality has not been extensively tested with iGenomes on Biowulf. Nonetheless, you should, in theory, be able to run the pipeline against any reference available in the `igenomes.config` specific to the nf-core pipeline. + +You can do this by simply using the `--genome ` parameter. + +>NB: You will need an account to use the HPC cluster on Biowulf in order to run the pipeline. If in doubt contact CIT. +>NB: Nextflow will need to submit the jobs via the job scheduler to the HPC cluster. The master process submitting jobs should be run either as a batch job or on an interactive node - not on the biowulf login node. If in doubt contact Biowulf staff. From de6d3bdd5f98143dadaa8fd3b239013a76604ac8 Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Fri, 17 Dec 2021 00:38:07 -0500 Subject: [PATCH 10/65] Update nfcore_custom.config --- nfcore_custom.config | 1 + 1 file changed, 1 insertion(+) diff --git a/nfcore_custom.config b/nfcore_custom.config index 4ceb1a7..f580206 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -47,6 +47,7 @@ profiles { maestro { includeConfig "${params.custom_config_base}/conf/maestro.config" } mpcdf { includeConfig "${params.custom_config_base}/conf/mpcdf.config" } munin { includeConfig "${params.custom_config_base}/conf/munin.config" } + nihbiowulf { includeConfig "${params.custom_config_base}/conf/nihbiowulf.config" } nu_genomics { includeConfig "${params.custom_config_base}/conf/nu_genomics.config" } oist { includeConfig "${params.custom_config_base}/conf/oist.config" } pasteur { includeConfig "${params.custom_config_base}/conf/pasteur.config" } From e523e28861485ff5405bcccef3ead387276344ba Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Fri, 17 Dec 2021 00:39:21 -0500 Subject: [PATCH 11/65] Update README.md --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 97fa54a..f2accc6 100644 --- a/README.md +++ b/README.md @@ -119,6 +119,7 @@ Currently documentation is available for the following systems: * [MPCDF](docs/mpcdf.md) * [MUNIN](docs/munin.md) * [NU_GENOMICS](docs/nu_genomics.md) +* [NIHBIOWULF](docs/nihbiowulf.md) * [OIST](docs/oist.md) * [PASTEUR](docs/pasteur.md) * [PHOENIX](docs/phoenix.md) From 74448de49e6ed9088f8055458af6470c6466ec7e Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Fri, 17 Dec 2021 00:40:43 -0500 Subject: [PATCH 12/65] Update main.yml add nihbiowulf --- .github/workflows/main.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index d040466..a3b41fd 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -54,6 +54,7 @@ jobs: - 'mpcdf' - 'munin' - 'nu_genomics' + - 'nihbiowulf' - 'oist' - 'pasteur' - 'phoenix' From 05f7b5957342dbdd935f2249b09a17df919977a7 Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Fri, 17 Dec 2021 00:44:39 -0500 Subject: [PATCH 13/65] Update nihbiowulf.md --- docs/nihbiowulf.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/nihbiowulf.md b/docs/nihbiowulf.md index f83894d..b19927e 100644 --- a/docs/nihbiowulf.md +++ b/docs/nihbiowulf.md @@ -1,4 +1,5 @@ # nf-core/configs: nihbiowulf Configuration + nf-core pipelines have been configured for use on the Biowulf cluster at the NIH. To use, run the pipeline with `-profile nihbiowulf`. This will download and launch the [`profile.config`](../conf/profile.config) which has been pre-configured with a setup suitable for the Biowulf cluster at NIH. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. From afb6fbb7671b67d81f0321f9a9b28d9cb21ae782 Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Fri, 17 Dec 2021 00:46:50 -0500 Subject: [PATCH 14/65] Trailing spaces --- docs/nihbiowulf.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/nihbiowulf.md b/docs/nihbiowulf.md index b19927e..c563b00 100644 --- a/docs/nihbiowulf.md +++ b/docs/nihbiowulf.md @@ -17,7 +17,7 @@ module load singularity ## Below are non-mandatory information on iGenomes specific configuration -A partial local copy of the iGenomes resource is available on Biowulf. This is a copy of the Illumina iGenomes resource from several years ago and is not up-to-date with the s3-hosted nf-core iGenomes. There are some structural differences of note. In particular, if using BWA, the igenomes.conf should be modified to specify the BWA version folder, otherwise the BWA module will fail to find an appropriate index. To date, this is the only issue, however functionality has not been extensively tested with iGenomes on Biowulf. Nonetheless, you should, in theory, be able to run the pipeline against any reference available in the `igenomes.config` specific to the nf-core pipeline. +A partial local copy of the iGenomes resource is available on Biowulf. This is a copy of the Illumina iGenomes resource from several years ago and is not up-to-date with the s3-hosted nf-core iGenomes. There are some structural differences of note. In particular, if using BWA, the igenomes.conf should be modified to specify the BWA version folder, otherwise the BWA module will fail to find an appropriate index. To date, this is the only issue, however functionality has not been extensively tested with iGenomes on Biowulf. Nonetheless, you should, in theory, be able to run the pipeline against any reference available in the `igenomes.config` specific to the nf-core pipeline. You can do this by simply using the `--genome ` parameter. From 82c7d553a770bcdb56f408b4bec0b889b892e78e Mon Sep 17 00:00:00 2001 From: Kevin Brick Date: Mon, 20 Dec 2021 11:29:09 -0500 Subject: [PATCH 15/65] Update bind-paths --- conf/nihbiowulf.config | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/conf/nihbiowulf.config b/conf/nihbiowulf.config index 5c035ba..6159f0d 100644 --- a/conf/nihbiowulf.config +++ b/conf/nihbiowulf.config @@ -34,5 +34,9 @@ singularity { enabled = true autoMounts = true envWhitelist='https_proxy,http_proxy,ftp_proxy,DISPLAY,SLURM_JOBID' - runOptions = ' -B /lscratch -B /fdb/igenomes/ --env TMPDIR="/lscratch/$SLURM_JOBID" ' -} \ No newline at end of file + + //As names change, the bind paths required may change too. To chack that everything is being captured: + //Run '. /usr/local/current/singularity/app_conf/sing_binds' to populate $SINGULARITY_BINDPATH + //Check that each folder in $SINGULARITY_BINDPATH is listed with -B in the runOptions below. If not, add it. + runOptions = ' -B /gs10 -B /gs11 -B /gs12 -B /gs4 -B /gs6 -B /gs7 -B /gs8 -B /gs9 -B /vf -B /spin1 -B /data -B /fdb -B /lscratch -B /fdb/igenomes/ --env TMPDIR="/lscratch/$SLURM_JOBID" ' +} From 53ab5ee34f8c49b6b050dcb413d52f7399cb9fdd Mon Sep 17 00:00:00 2001 From: praveenraj2018 <43108054+praveenraj2018@users.noreply.github.com> Date: Tue, 21 Dec 2021 15:21:59 +0100 Subject: [PATCH 16/65] Updated sentieon version through a new module file A local module file has been created to run the latest version of Sentieon. Doing this change, as the new version of Sentieon has only a dependency library update, hence it should not break the Sentieon pipeline. Tested locally with a test.conf having the new process block. --- conf/pipeline/sarek/munin.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/pipeline/sarek/munin.config b/conf/pipeline/sarek/munin.config index 7276a27..6a73b8c 100644 --- a/conf/pipeline/sarek/munin.config +++ b/conf/pipeline/sarek/munin.config @@ -23,7 +23,7 @@ params { // Specific nf-core/sarek process configuration process { withLabel:sentieon { - module = {params.sentieon ? 'sentieon/201911.00' : null} + module = {params.sentieon ? 'sentieon/202112.00' : null} container = {params.sentieon ? null : container} } } From 0f56588accdb577e51b78a730330d6e133ab2ec1 Mon Sep 17 00:00:00 2001 From: ameynert Date: Thu, 6 Jan 2022 10:15:34 +0000 Subject: [PATCH 17/65] Added memory & cluster options specification for eddie sarek config --- conf/pipeline/sarek/eddie.config | 2 ++ 1 file changed, 2 insertions(+) diff --git a/conf/pipeline/sarek/eddie.config b/conf/pipeline/sarek/eddie.config index 9629337..1928a9a 100644 --- a/conf/pipeline/sarek/eddie.config +++ b/conf/pipeline/sarek/eddie.config @@ -2,6 +2,8 @@ process { withName:MapReads { cpus = 16 + memory = 128.GB + clusterOptions = {"-l h_vmem=${(task.memory + 8.GB).bytes/task.cpus}"} } withName:BuildDict { cpus = 1 From 5fd5c43906dd676932e63a41fcddf000bb226639 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 14 Jan 2022 07:03:05 +0100 Subject: [PATCH 18/65] Update eva.config --- conf/pipeline/eager/eva.config | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 466a4c1..4c2922d 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -100,6 +100,10 @@ process { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } memory = { check_max( 4.GB * task.attempt, 'memory' ) } } + + withName: metagenomic_complexity_filter { + clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + } withName: malt { clusterOptions = { "-S /bin/bash -V -l h_vmem=1000G,virtual_free=1000G" } @@ -258,6 +262,10 @@ profiles { memory = { check_max( 4.GB * task.attempt, 'memory' ) } } + withName: metagenomic_complexity_filter { + clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + } + withName: malt { clusterOptions = { "-S /bin/bash -V -l h_vmem=1000G,virtual_free=1000G" } cpus = { check_max( 32, 'cpus' ) } @@ -425,6 +433,10 @@ profiles { time = 1440.h } + withName: metagenomic_complexity_filter { + clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + } + withName: malt { clusterOptions = { "-S /bin/bash -V -l h_vmem=1000G,virtual_free=1000G" } cpus = { check_max( 32, 'cpus' ) } From f26c465bd431d4cfaa58c53038605c42e7c94464 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Mon, 17 Jan 2022 11:27:10 +0000 Subject: [PATCH 19/65] Add Nextclade genome details to viralrecon genome config --- conf/pipeline/viralrecon/genomes.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/conf/pipeline/viralrecon/genomes.config b/conf/pipeline/viralrecon/genomes.config index 3e3e299..16d2cb0 100644 --- a/conf/pipeline/viralrecon/genomes.config +++ b/conf/pipeline/viralrecon/genomes.config @@ -13,10 +13,16 @@ params { // Please use 'MN908947.3' if possible because all primer sets are available / have been pre-prepared relative to that assembly fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.gff.gz' + nextclade_dataset_name = 'sars-cov-2' + nextclade_dataset_reference = 'MN908947' + nextclade_dataset_tag = '2022-01-05T19:54:31Z' } 'MN908947.3' { fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.fna.gz' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz' + nextclade_dataset_name = 'sars-cov-2' + nextclade_dataset_reference = 'MN908947' + nextclade_dataset_tag = '2022-01-05T19:54:31Z' primer_sets { artic { '1' { From cd6b8e0f172397fae376cb95b10a2e80b65abb09 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Mon, 17 Jan 2022 16:51:55 +0000 Subject: [PATCH 20/65] Add --nextclade_dataset params --- conf/pipeline/viralrecon/genomes.config | 2 ++ 1 file changed, 2 insertions(+) diff --git a/conf/pipeline/viralrecon/genomes.config b/conf/pipeline/viralrecon/genomes.config index 16d2cb0..9cf864a 100644 --- a/conf/pipeline/viralrecon/genomes.config +++ b/conf/pipeline/viralrecon/genomes.config @@ -13,6 +13,7 @@ params { // Please use 'MN908947.3' if possible because all primer sets are available / have been pre-prepared relative to that assembly fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.gff.gz' + nextclade_dataset = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-05T19_54_31Z.tar.gz' nextclade_dataset_name = 'sars-cov-2' nextclade_dataset_reference = 'MN908947' nextclade_dataset_tag = '2022-01-05T19:54:31Z' @@ -20,6 +21,7 @@ params { 'MN908947.3' { fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.fna.gz' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz' + nextclade_dataset = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-05T19_54_31Z.tar.gz' nextclade_dataset_name = 'sars-cov-2' nextclade_dataset_reference = 'MN908947' nextclade_dataset_tag = '2022-01-05T19:54:31Z' From 5c1afd56bfa04b26ca499f0a343a8e800e5ae492 Mon Sep 17 00:00:00 2001 From: Praveen Raj S <43108054+praveenraj2018@users.noreply.github.com> Date: Thu, 20 Jan 2022 22:25:31 +0100 Subject: [PATCH 21/65] Added genome parameter Added genome parameter to the config file --- conf/pipeline/rnavar/munin.config | 1 + 1 file changed, 1 insertion(+) diff --git a/conf/pipeline/rnavar/munin.config b/conf/pipeline/rnavar/munin.config index c2c8335..c573781 100644 --- a/conf/pipeline/rnavar/munin.config +++ b/conf/pipeline/rnavar/munin.config @@ -11,6 +11,7 @@ params { igenomes_ignore = true // Genome references + genome = 'GRCh38' fasta = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa' fasta_fai = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai' gtf = '/data1/references/CTAT_GenomeLib_v37_Mar012021/GRCh38_gencode_v37_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_annot.gtf' From 9792226f5cecebf400205d435461ab3d047bed50 Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Thu, 27 Jan 2022 12:45:41 +0000 Subject: [PATCH 22/65] Update genomes.config --- conf/pipeline/viralrecon/genomes.config | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/conf/pipeline/viralrecon/genomes.config b/conf/pipeline/viralrecon/genomes.config index 9cf864a..8682942 100644 --- a/conf/pipeline/viralrecon/genomes.config +++ b/conf/pipeline/viralrecon/genomes.config @@ -13,18 +13,18 @@ params { // Please use 'MN908947.3' if possible because all primer sets are available / have been pre-prepared relative to that assembly fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.gff.gz' - nextclade_dataset = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-05T19_54_31Z.tar.gz' + nextclade_dataset = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-18T12_00_00Z.tar.gz' nextclade_dataset_name = 'sars-cov-2' nextclade_dataset_reference = 'MN908947' - nextclade_dataset_tag = '2022-01-05T19:54:31Z' + nextclade_dataset_tag = '2022-01-18T12:00:00Z' } 'MN908947.3' { fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.fna.gz' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz' - nextclade_dataset = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-05T19_54_31Z.tar.gz' + nextclade_dataset = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/nextclade_sars-cov-2_MN908947_2022-01-18T12_00_00Z.tar.gz' nextclade_dataset_name = 'sars-cov-2' nextclade_dataset_reference = 'MN908947' - nextclade_dataset_tag = '2022-01-05T19:54:31Z' + nextclade_dataset_tag = '2022-01-18T12:00:00Z' primer_sets { artic { '1' { From 8739aabbf026ebe1655ed0471dacef9ec4c3cbd0 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Wed, 2 Feb 2022 08:00:13 +0100 Subject: [PATCH 23/65] Bump markduplicates by default --- conf/pipeline/eager/eva.config | 3 +++ 1 file changed, 3 insertions(+) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 4c2922d..7ba59fa 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -86,6 +86,7 @@ process { withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + memory = { check_max( 20.GB * task.attempt, 'memory' ) } } withName: library_merge { @@ -247,6 +248,7 @@ profiles { withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + memory = { check_max( 32.GB * task.attempt, 'memory' ) } } withName: library_merge { @@ -412,6 +414,7 @@ profiles { withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + memory = { check_max( 48.GB * task.attempt, 'memory' ) } } withName: library_merge { From cc380ce9a1b92011fc1991dd1a6ffaf33f0e5710 Mon Sep 17 00:00:00 2001 From: Michael Borg Date: Wed, 2 Feb 2022 13:33:03 +0100 Subject: [PATCH 24/65] Update mpcdf.config Added polling frequencies to the config as requested by MPCDF admin. Also updated the number of (real) cores on Raven. --- conf/mpcdf.config | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/conf/mpcdf.config b/conf/mpcdf.config index 3027d63..281e7bf 100644 --- a/conf/mpcdf.config +++ b/conf/mpcdf.config @@ -18,6 +18,8 @@ profiles { executor { queueSize = 8 + pollInterval = '1 min' + queueStatInterval = '5 min' } // Set $NXF_SINGULARITY_CACHEDIR in your ~/.bash_profile @@ -46,6 +48,8 @@ profiles { executor { queueSize = 8 + pollInterval = '1 min' + queueStatInterval = '5 min' } // Set $NXF_SINGULARITY_CACHEDIR in your ~/.bash_profile @@ -58,7 +62,7 @@ profiles { params { config_profile_description = 'MPCDF raven profile (unofficially) provided by nf-core/configs.' max_memory = 368.GB - max_cpus = 192 + max_cpus = 72 max_time = 24.h } } From 7c1c4c7fa441f1ef3c3eb124cab50134f5e7ca1e Mon Sep 17 00:00:00 2001 From: rbpisupati Date: Wed, 2 Feb 2022 22:42:13 +0100 Subject: [PATCH 25/65] changes to cbe module loading --- conf/cbe.config | 4 ++-- docs/cbe.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/conf/cbe.config b/conf/cbe.config index 0a5763f..e8d7bc0 100755 --- a/conf/cbe.config +++ b/conf/cbe.config @@ -9,11 +9,11 @@ process { executor = 'slurm' queue = { task.memory <= 170.GB ? 'c' : 'm' } clusterOptions = { task.time <= 8.h ? '--qos short': task.time <= 48.h ? '--qos medium' : '--qos long' } - module = 'anaconda3/2019.10' + module = ['build-env/.f2021', 'build-env/f2021', 'anaconda3/2021.11'] } singularity { - enabled = true + // enabled = true cacheDir = '/resources/containers' } diff --git a/docs/cbe.md b/docs/cbe.md index aa6c60d..217e1f2 100644 --- a/docs/cbe.md +++ b/docs/cbe.md @@ -2,7 +2,7 @@ All nf-core pipelines have been successfully configured for use on the CLIP BATCH ENVIRONMENT (CBE) cluster at the Vienna BioCenter (VBC). -To use, run the pipeline with `-profile cbe`. This will download and launch the [`cbe.config`](../conf/cbe.config) which has been pre-configured with a setup suitable for the CBE cluster. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. +To use, run the pipeline with `-profile cbe`. This will download and launch the [`cbe.config`](../conf/cbe.config) which has been pre-configured with a setup suitable for the CBE cluster. This profile sets needed slurm environment. Additionally you need to add `sigularity`, `docker` or `conda` to the profile to be able to run the pipeline. If `-profile cbe,singularity` is given, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. Before running the pipeline you will need to load Nextflow using the environment module system on CBE. You can do this by issuing the commands below: From 50aafc64101de813ac6740c554214202d76fa611 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Thu, 3 Feb 2022 17:03:10 +0100 Subject: [PATCH 26/65] Update eva.config --- conf/pipeline/eager/eva.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 7ba59fa..b512921 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -3,7 +3,7 @@ params { // Specific nf-core/configs params config_profile_contact = 'James Fellows Yates (@jfy133)' - config_profile_description = 'nf-core/eager EVA profile provided by nf-core/configs' + config_profile_description = 'nf-core/eager EVA profile provided by nf-core/configs DEV' } // Specific nf-core/eager process configuration From 453080f28210b38e4b0465d4bb3fb387a1489e3a Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 3 Feb 2022 18:26:30 +0000 Subject: [PATCH 27/65] Update imperial.config Removed my contact details. Users can request help on the nf-core slack. --- conf/imperial.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/imperial.config b/conf/imperial.config index eeb98ae..312544a 100644 --- a/conf/imperial.config +++ b/conf/imperial.config @@ -3,7 +3,7 @@ params { // Config Params config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_contact = 'NA' config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' // Resources From 731f86e7f1a9bbad9fe968fd613876a5580eaccd Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 3 Feb 2022 18:27:49 +0000 Subject: [PATCH 28/65] Update imperial_mb.config Removed my contact details. Users can request help on the nf-core slack. --- conf/imperial_mb.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/imperial_mb.config b/conf/imperial_mb.config index a89ffcd..afd88c1 100644 --- a/conf/imperial_mb.config +++ b/conf/imperial_mb.config @@ -3,7 +3,7 @@ params { // Config Params config_profile_description = 'Imperial College London - MEDBIO QUEUE - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_contact = 'NA' config_profile_url = 'https://www.imperial.ac.uk/bioinformatics-data-science-group/resources/uk-med-bio/' // Resources From 2bdf5863d93a849abd39859fac36e4f36f904c1f Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 3 Feb 2022 18:28:11 +0000 Subject: [PATCH 29/65] Update imperial.config Removed my contact details. Users can request help on the nf-core slack. --- conf/pipeline/scflow/imperial.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/conf/pipeline/scflow/imperial.config b/conf/pipeline/scflow/imperial.config index 7f46466..78a4a8b 100644 --- a/conf/pipeline/scflow/imperial.config +++ b/conf/pipeline/scflow/imperial.config @@ -3,7 +3,7 @@ params { // Config Params config_profile_description = 'Imperial College London - HPC - nf-core/scFlow Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_contact = 'NA' // Analysis Resource Params ctd_folder = "/rds/general/user/$USER/projects/ukdrmultiomicsproject/live/Analyses/scFlowResources/refs/ctd" @@ -15,4 +15,4 @@ singularity { autoMounts = true cacheDir = "/rds/general/user/$USER/projects/ukdrmultiomicsproject/live/.singularity-cache" runOptions = "-B /rds/,/rdsgpfs/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" -} \ No newline at end of file +} From 81a273c730505b421ca05e0485eca7282d18d5e6 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 3 Feb 2022 18:31:02 +0000 Subject: [PATCH 30/65] Update imperial_mb.config Dropped support for pqmedbio-large which is not currently available. --- conf/imperial_mb.config | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/conf/imperial_mb.config b/conf/imperial_mb.config index afd88c1..72bc412 100644 --- a/conf/imperial_mb.config +++ b/conf/imperial_mb.config @@ -37,8 +37,8 @@ process { //queue = 'med-bio' //!! this is an alias and shouldn't be used - withLabel:process_large { - queue = 'pqmedbio-large' - } + //withLabel:process_large { + //queue = 'pqmedbio-large' //!! this queue is unavailable as of Feb 2022 + //} } From 86a9042eace4dd244ef22e3054bd0c9889cad4e1 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 4 Feb 2022 09:25:01 +0100 Subject: [PATCH 31/65] Update eva.config --- conf/pipeline/eager/eva.config | 3 +++ 1 file changed, 3 insertions(+) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index b512921..c469697 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -134,6 +134,7 @@ process { withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + memory = { check_max( 8.GB * task.attempt, 'memory' ) } } withName: circularmapper { @@ -301,6 +302,7 @@ profiles { withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + memory = { check_max( 16.GB * task.attempt, 'memory' ) } } withName: circularmapper { @@ -468,6 +470,7 @@ profiles { withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + memory = { check_max( 32.GB * task.attempt, 'memory' ) } } withName: circularmapper { From 81fe720b00322ea60d6d55b23fe645ada3d0968f Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Fri, 4 Feb 2022 09:31:33 +0100 Subject: [PATCH 32/65] Update eva.config --- conf/pipeline/eager/eva.config | 3 +++ 1 file changed, 3 insertions(+) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index c469697..1530757 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -87,6 +87,7 @@ process { withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } memory = { check_max( 20.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1, 143,137, 140] ? 'retry' : 'finish' } } withName: library_merge { @@ -250,6 +251,7 @@ profiles { withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } memory = { check_max( 32.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [143,137, 140] ? 'retry' : 'finish' } } withName: library_merge { @@ -417,6 +419,7 @@ profiles { withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } memory = { check_max( 48.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [143,137, 140] ? 'retry' : 'finish' } } withName: library_merge { From b5ab4a8258c24001defadf1ea8cc5579020ccee6 Mon Sep 17 00:00:00 2001 From: phue Date: Fri, 4 Feb 2022 10:13:12 +0100 Subject: [PATCH 33/65] Revert "changes to cbe module loading" This reverts commit 7c1c4c7fa441f1ef3c3eb124cab50134f5e7ca1e. --- conf/cbe.config | 4 ++-- docs/cbe.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/conf/cbe.config b/conf/cbe.config index e8d7bc0..0a5763f 100755 --- a/conf/cbe.config +++ b/conf/cbe.config @@ -9,11 +9,11 @@ process { executor = 'slurm' queue = { task.memory <= 170.GB ? 'c' : 'm' } clusterOptions = { task.time <= 8.h ? '--qos short': task.time <= 48.h ? '--qos medium' : '--qos long' } - module = ['build-env/.f2021', 'build-env/f2021', 'anaconda3/2021.11'] + module = 'anaconda3/2019.10' } singularity { - // enabled = true + enabled = true cacheDir = '/resources/containers' } diff --git a/docs/cbe.md b/docs/cbe.md index 217e1f2..aa6c60d 100644 --- a/docs/cbe.md +++ b/docs/cbe.md @@ -2,7 +2,7 @@ All nf-core pipelines have been successfully configured for use on the CLIP BATCH ENVIRONMENT (CBE) cluster at the Vienna BioCenter (VBC). -To use, run the pipeline with `-profile cbe`. This will download and launch the [`cbe.config`](../conf/cbe.config) which has been pre-configured with a setup suitable for the CBE cluster. This profile sets needed slurm environment. Additionally you need to add `sigularity`, `docker` or `conda` to the profile to be able to run the pipeline. If `-profile cbe,singularity` is given, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. +To use, run the pipeline with `-profile cbe`. This will download and launch the [`cbe.config`](../conf/cbe.config) which has been pre-configured with a setup suitable for the CBE cluster. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. Before running the pipeline you will need to load Nextflow using the environment module system on CBE. You can do this by issuing the commands below: From 52b6f7da211d1fc123cf100a340c9b45564e88e2 Mon Sep 17 00:00:00 2001 From: phue Date: Fri, 4 Feb 2022 10:18:59 +0100 Subject: [PATCH 34/65] update anaconda module not sure why a binary distribution needs a buildenv at all, but well --- conf/cbe.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/cbe.config b/conf/cbe.config index 89da3db..a8bf05d 100755 --- a/conf/cbe.config +++ b/conf/cbe.config @@ -8,7 +8,7 @@ params { process { executor = 'slurm' queue = { task.memory <= 170.GB ? 'c' : 'm' } - module = 'anaconda3/2019.10' + module = ['build-env/.f2021', 'build-env/f2021', 'anaconda3/2021.11'] // --signal option will be handled by nextflow after 21.10.0 release (see https://github.com/nextflow-io/nextflow/issues/2163) clusterOptions = { '--signal B:USR2 ' << ( (queue == 'c' & task.time <= 1.h) ? '--qos rapid' : ( task.time <= 8.h ? '--qos short': ( task.time <= 48.h ? '--qos medium' : '--qos long' ) ) ) } From a6dd3aa0f1fedba102d4e1ef1f587671e5e6331c Mon Sep 17 00:00:00 2001 From: phue Date: Fri, 4 Feb 2022 10:21:52 +0100 Subject: [PATCH 35/65] cbe: update recommended nextflow version in docs otherwise, the new anaconda requirements will cause conflicts --- docs/cbe.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cbe.md b/docs/cbe.md index aa6c60d..b7628d0 100644 --- a/docs/cbe.md +++ b/docs/cbe.md @@ -9,7 +9,7 @@ Before running the pipeline you will need to load Nextflow using the environment ```bash ## Load Nextflow environment module module purge -module load nextflow/19.04.0 +module load nextflow/21.10.6 ``` A local copy of the [AWS-iGenomes](https://registry.opendata.aws/aws-igenomes/) resource has been made available on CBE so you should be able to run the pipeline against any reference available in the `igenomes.config` specific to the nf-core pipeline. You can do this by simply using the `--genome ` parameter. From 49810a69b399c32c52bf96fa20813c049b646922 Mon Sep 17 00:00:00 2001 From: phue Date: Fri, 4 Feb 2022 10:31:58 +0100 Subject: [PATCH 36/65] cbe: add gpu support just in case.. note that this will need --nv in containerOptions in order to mount cuda libs into the container --- conf/cbe.config | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/conf/cbe.config b/conf/cbe.config index a8bf05d..1cdccba 100755 --- a/conf/cbe.config +++ b/conf/cbe.config @@ -9,9 +9,7 @@ process { executor = 'slurm' queue = { task.memory <= 170.GB ? 'c' : 'm' } module = ['build-env/.f2021', 'build-env/f2021', 'anaconda3/2021.11'] - - // --signal option will be handled by nextflow after 21.10.0 release (see https://github.com/nextflow-io/nextflow/issues/2163) - clusterOptions = { '--signal B:USR2 ' << ( (queue == 'c' & task.time <= 1.h) ? '--qos rapid' : ( task.time <= 8.h ? '--qos short': ( task.time <= 48.h ? '--qos medium' : '--qos long' ) ) ) } + clusterOptions = { ( task.queue == 'g' ? '--gres gpu:1 ' : '' ) << ( (task.queue == 'c' & task.time <= 1.h) ? '--qos rapid' : ( task.time <= 8.h ? '--qos short': ( task.time <= 48.h ? '--qos medium' : '--qos long' ) ) ) } } singularity { From 7bf6f284fac8b90dc674fb766c3b0bf03943b764 Mon Sep 17 00:00:00 2001 From: phue Date: Fri, 4 Feb 2022 10:33:00 +0100 Subject: [PATCH 37/65] cbe: lower the threshold for switching to m queue --- conf/cbe.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/cbe.config b/conf/cbe.config index 1cdccba..fbc0812 100755 --- a/conf/cbe.config +++ b/conf/cbe.config @@ -7,7 +7,7 @@ params { process { executor = 'slurm' - queue = { task.memory <= 170.GB ? 'c' : 'm' } + queue = { task.memory <= 120.GB ? 'c' : 'm' } module = ['build-env/.f2021', 'build-env/f2021', 'anaconda3/2021.11'] clusterOptions = { ( task.queue == 'g' ? '--gres gpu:1 ' : '' ) << ( (task.queue == 'c' & task.time <= 1.h) ? '--qos rapid' : ( task.time <= 8.h ? '--qos short': ( task.time <= 48.h ? '--qos medium' : '--qos long' ) ) ) } } From dbb71161c5428e77d8c4f6f8e347fa4b269fb139 Mon Sep 17 00:00:00 2001 From: Stevin Wilson Date: Fri, 4 Feb 2022 15:31:51 -0500 Subject: [PATCH 38/65] Added ARTIC v4.1 primer set information --- conf/pipeline/viralrecon/genomes.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/conf/pipeline/viralrecon/genomes.config b/conf/pipeline/viralrecon/genomes.config index 8682942..baad834 100644 --- a/conf/pipeline/viralrecon/genomes.config +++ b/conf/pipeline/viralrecon/genomes.config @@ -51,6 +51,12 @@ params { primer_bed = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V4/SARS-CoV-2.scheme.bed' scheme = 'SARS-CoV-2' } + '4.1' { + fasta = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V4.1/SARS-CoV-2.reference.fasta' + gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz' + primer_bed = 'https://github.com/artic-network/artic-ncov2019/raw/master/primer_schemes/nCoV-2019/V4.1/SARS-CoV-2.scheme.bed' + scheme = 'SARS-CoV-2' + } '1200' { fasta = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/primer_schemes/artic/nCoV-2019/V1200/nCoV-2019.reference.fasta' gff = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz' From aa525c6ebf6d28da67fc442d9d5d2b50d8b0be01 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Sun, 6 Feb 2022 09:07:53 +0100 Subject: [PATCH 39/65] Allow exit code 1 retry for all java processes --- conf/pipeline/eager/eva.config | 51 ++++++++++++++++++++++++++++++---- 1 file changed, 46 insertions(+), 5 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 1530757..7b7cef0 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -62,14 +62,17 @@ process { withName: makeSeqDict { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: fastqc { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: adapter_removal { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: samtools_flagstat { @@ -82,12 +85,13 @@ process { withName: dedup { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } memory = { check_max( 20.GB * task.attempt, 'memory' ) } - errorStrategy = { task.exitStatus in [1, 143,137, 140] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: library_merge { @@ -115,35 +119,43 @@ process { withName: maltextract { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: multivcfanalyzer { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: mtnucratio { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: vcf2genome { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } - memory = { check_max( 8.GB * task.attempt, 'memory' ) } + memory = { check_max( 8.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circularmapper { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circulargenerator { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: preseq { @@ -153,6 +165,7 @@ process { withName: genotyping_ug { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } } @@ -226,14 +239,17 @@ profiles { withName: makeSeqDict { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: fastqc { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: adapter_removal { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: samtools_flagstat { @@ -246,12 +262,13 @@ profiles { withName: dedup { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } memory = { check_max( 32.GB * task.attempt, 'memory' ) } - errorStrategy = { task.exitStatus in [143,137, 140] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: library_merge { @@ -275,6 +292,7 @@ profiles { clusterOptions = { "-S /bin/bash -V -l h_vmem=1000G,virtual_free=1000G" } cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 955.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName:hostremoval_input_fastq { @@ -284,39 +302,48 @@ profiles { withName: maltextract { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: multivcfanalyzer { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: mtnucratio { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: vcf2genome { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } - memory = { check_max( 16.GB * task.attempt, 'memory' ) } + memory = { check_max( 16.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circularmapper { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circulargenerator { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: genotyping_ug { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: preseq { @@ -394,14 +421,17 @@ profiles { withName: makeSeqDict { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: fastqc { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: adapter_removal { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: samtools_flagstat { @@ -414,12 +444,13 @@ profiles { withName: dedup { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: markduplicates { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } memory = { check_max( 48.GB * task.attempt, 'memory' ) } - errorStrategy = { task.exitStatus in [143,137, 140] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: library_merge { @@ -449,43 +480,53 @@ profiles { clusterOptions = { "-S /bin/bash -V -l h_vmem=1000G,virtual_free=1000G" } cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 955.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: maltextract { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: multivcfanalyzer { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: mtnucratio { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: vcf2genome { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: damageprofiler { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } memory = { check_max( 32.GB * task.attempt, 'memory' ) } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circularmapper { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: circulargenerator { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: genotyping_ug { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } } withName: preseq { From 8c5a54ac9ff8696c19afe252d774a445ff1c4987 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Sun, 6 Feb 2022 19:37:53 +0100 Subject: [PATCH 40/65] Update conf/pipeline/eager/eva.config --- conf/pipeline/eager/eva.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 7b7cef0..d13a71a 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -3,7 +3,7 @@ params { // Specific nf-core/configs params config_profile_contact = 'James Fellows Yates (@jfy133)' - config_profile_description = 'nf-core/eager EVA profile provided by nf-core/configs DEV' + config_profile_description = 'nf-core/eager EVA profile provided by nf-core/configs' } // Specific nf-core/eager process configuration From 2b06293f64b8f81fe4ae8799e13d38ab5bcd7f67 Mon Sep 17 00:00:00 2001 From: "James A. Fellows Yates" Date: Tue, 8 Feb 2022 11:15:17 +0100 Subject: [PATCH 41/65] Read add empty BAM exit code for qualitmap 255 --- conf/pipeline/eager/eva.config | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index d13a71a..d436895 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -139,7 +139,7 @@ process { withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 2)}G,virtual_free=${(task.memory.toGiga() * 2)}G" } - errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : task.exitStatus in [255] ? 'ignore' : 'finish' } } withName: damageprofiler { @@ -322,7 +322,7 @@ profiles { withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 3)}G,virtual_free=${(task.memory.toGiga() * 3)}G" } - errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : task.exitStatus in [255] ? 'ignore' : 'finish' } } withName: damageprofiler { @@ -505,7 +505,7 @@ profiles { withName: qualimap { clusterOptions = { "-S /bin/bash -V -l h_vmem=${(task.memory.toGiga() * 6)}G,virtual_free=${(task.memory.toGiga() * 6)}G" } - errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : 'finish' } + errorStrategy = { task.exitStatus in [1,143,137,104,134,139,140] ? 'retry' : task.exitStatus in [255] ? 'ignore' : 'finish' } } withName: damageprofiler { From fa4075c2a0302995efdb0558ddafcbbe0b82ecfa Mon Sep 17 00:00:00 2001 From: "Thiseas C. Lamnidis" Date: Thu, 10 Feb 2022 10:00:18 +0100 Subject: [PATCH 42/65] Removed all time limits --- conf/pipeline/eager/eva.config | 23 ----------------------- 1 file changed, 23 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index d436895..67c3b5a 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,43 +19,36 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 256.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use @@ -196,43 +189,36 @@ profiles { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.5.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 6.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 12.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 6.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 12.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 24.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 256.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } // Fixes for SGE and Java incompatibility due to (and also some samtools?!) using more memory than you tell it to use @@ -297,7 +283,6 @@ profiles { withName:hostremoval_input_fastq { memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = 1440.h } withName: maltextract { @@ -378,43 +363,36 @@ profiles { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 2.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 512.GB * task.attempt, 'memory' ) } - time = { task.attempt == 3 ? 1440.h : task.attempt == 2 ? 48.h : 2.h } } // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use @@ -469,7 +447,6 @@ profiles { withName:hostremoval_input_fastq { memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = 1440.h } withName: metagenomic_complexity_filter { From c0ee3225ad976f9f25e73948fbfa2fb13a7d9d88 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 10 Feb 2022 11:02:52 +0100 Subject: [PATCH 43/65] Add times for 365d --- conf/pipeline/eager/eva.config | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 67c3b5a..e6f673e 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,36 +19,43 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_large'{ - cpus = { check_max( 8, 'cpus' ) } - memory = { check_max( 16.GB * task.attempt, 'memory' ) } + cpus = { check_max( 8, 'cpus' ) } + memory = { check_max( 16.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 256.GB * task.attempt, 'memory' ) } + time = '365.d' } // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use From 39c2d9b25b96e49bc58672a3ff3fedccc443edf2 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 10 Feb 2022 11:19:16 +0100 Subject: [PATCH 44/65] Oops --- conf/pipeline/eager/eva.config | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index e6f673e..12bb4da 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,43 +19,42 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } - time = '365.d' + time = '365d' } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = '365.d' + time = '365d' } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = '365.d' + time = '365d' } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = '365.d' + time = '365d' } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = '365.d' + time = '365d' } withLabel:'mc_large'{ - cpus = { check_max( 8, 'cpus' ) } - memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = '365.d' + cpus = { check_max( 8, 'cpus' ) } + memory = { check_max( 16.GB * task.attempt, 'memory' ) } + time = '365d' } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 256.GB * task.attempt, 'memory' ) } - time = '365.d' } // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use From dd94895f168f2764f6580ca6a0f468af478ce2c3 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 10 Feb 2022 11:22:45 +0100 Subject: [PATCH 45/65] remove quotes --- conf/pipeline/eager/eva.config | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 12bb4da..64138af 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,37 +19,37 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } - time = '365d' + time = 365d } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = '365d' + time = 365d } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = '365d' + time = 365d } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = '365d' + time = 365d } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = '365d' + time = 365d } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = '365d' + time = 365d } withLabel:'mc_huge'{ From dbd78f8075c9d4a3483cd3da23a4a38b1ac97af6 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 10 Feb 2022 11:26:18 +0100 Subject: [PATCH 46/65] Re add `.` --- conf/pipeline/eager/eva.config | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 64138af..669097d 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,37 +19,37 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } - time = 365d + time = 365.d } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = 365d + time = 365.d } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = 365d + time = 365.d } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = 365d + time = 365.d } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = 365d + time = 365.d } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = 365d + time = 365.d } withLabel:'mc_huge'{ From d7d0f5ceccea4d28ceab5c5e4c1fa75642955073 Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 10 Feb 2022 11:32:49 +0100 Subject: [PATCH 47/65] Change base time --- conf/eva.config | 2 +- conf/pipeline/eager/eva.config | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/conf/eva.config b/conf/eva.config index 8b52dda..432b667 100644 --- a/conf/eva.config +++ b/conf/eva.config @@ -30,7 +30,7 @@ profiles { config_profile_description = 'MPI-EVA archgen profile, provided by nf-core/configs.' max_memory = 256.GB max_cpus = 32 - max_time = 720.h + max_time = 365.d //Illumina iGenomes reference file path } diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 669097d..67c3b5a 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,37 +19,31 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } - time = 365.d } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = 365.d } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = 365.d } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } - time = 365.d } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } - time = 365.d } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } - time = 365.d } withLabel:'mc_huge'{ From 88ddc9eee7a158200cd5e2423ad5d721c4eeaebe Mon Sep 17 00:00:00 2001 From: James Fellows Yates Date: Thu, 10 Feb 2022 11:34:57 +0100 Subject: [PATCH 48/65] fffff --- conf/pipeline/eager/eva.config | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/conf/pipeline/eager/eva.config b/conf/pipeline/eager/eva.config index 67c3b5a..eccccbb 100644 --- a/conf/pipeline/eager/eva.config +++ b/conf/pipeline/eager/eva.config @@ -19,36 +19,43 @@ process { withLabel:'sc_tiny'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 1.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'sc_small'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'sc_medium'{ cpus = { check_max( 1, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_small'{ cpus = { check_max( 2, 'cpus' ) } memory = { check_max( 4.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_medium' { cpus = { check_max( 4, 'cpus' ) } memory = { check_max( 8.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_large'{ cpus = { check_max( 8, 'cpus' ) } memory = { check_max( 16.GB * task.attempt, 'memory' ) } + time = '365.d' } withLabel:'mc_huge'{ cpus = { check_max( 32, 'cpus' ) } memory = { check_max( 256.GB * task.attempt, 'memory' ) } + time = '365.d' } // Fixes for SGE and Java incompatibility due to Java using more memory than you tell it to use From fe5474a029c63b7bf22426fe56b570a615fd81dd Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 10 Feb 2022 23:02:47 +0000 Subject: [PATCH 49/65] Update imperial.config Multiple process level updates reflecting the latest job sizing guidelines for the Imperial HPC --- conf/imperial.config | 71 +++++++++++++++++++++++++++++++------------- 1 file changed, 50 insertions(+), 21 deletions(-) diff --git a/conf/imperial.config b/conf/imperial.config index 312544a..e2a3aca 100644 --- a/conf/imperial.config +++ b/conf/imperial.config @@ -1,37 +1,66 @@ //Profile config names for nf-core/configs params { - // Config Params - config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'NA' - config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' + // Config Params + config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' + config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' - // Resources - max_memory = 256.GB - max_cpus = 32 - max_time = 72.h + // Resources + max_memory = 480.GB + max_cpus = 40 + max_time = 1000.h } executor { - $pbspro { - queueSize = 50 - } + $pbspro { + queueSize = 50 + } - $local { - cpus = 2 - queueSize = 1 - memory = '32 GB' - } + $local { + cpus = 2 + queueSize = 1 + memory = '6 GB' + } } singularity { - enabled = true - autoMounts = true - runOptions = "-B /rds/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" + enabled = true + autoMounts = true + runOptions = "-B /rds/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" } process { + executor = 'pbspro' - executor = 'pbspro' - + // Process-specific resource requirements + withLabel:process_low { + // TARGET QUEUE: throughput + cpus = { check_max( 2 * task.attempt, 'cpus' ) } + memory = { check_max( 12.GB * task.attempt, 'memory' ) } + time = { check_max( 4.h * task.attempt, 'time' ) } + } + withLabel:process_medium { + // TARGET QUEUE: throughput + cpus = { check_max( 8, 'cpus' ) } + memory = { check_max( 32.GB * task.attempt, 'memory' ) } + time = { check_max( 8.h * task.attempt, 'time' ) } + } + withLabel:process_high { + // TARGET QUEUE: general + cpus = { check_max( 32, 'cpus' ) } + memory = { check_max( 62.GB * task.attempt, 'memory' ) } + time = { check_max( 16.h * task.attempt, 'time' ) } + } + withLabel:process_long { + // TARGET QUEUE: long + cpus = { check_max( 8, 'cpus' ) } + memory = { check_max( 96.GB, 'memory' ) } + time = { check_max( 72.h * task.attempt, 'time' ) } + } + withLabel:process_high_memory { + // TARGET QUEUE: large memory + cpus = { check_max( 10 * task.attempt, 'cpus' ) } + memory = { check_max( 120.GB * task.attempt, 'memory' ) } + time = { check_max( 12.h * task.attempt, 'time' ) } + } } From e1d0bf0cd2b4156a6dd8922630bdb8521744a973 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 10 Feb 2022 23:44:49 +0000 Subject: [PATCH 50/65] Delete imperial_mb.config Separate config for the medbio queue now deprecated in favour of an internal profile within the main imperial.config --- conf/imperial_mb.config | 44 ----------------------------------------- 1 file changed, 44 deletions(-) delete mode 100644 conf/imperial_mb.config diff --git a/conf/imperial_mb.config b/conf/imperial_mb.config deleted file mode 100644 index 72bc412..0000000 --- a/conf/imperial_mb.config +++ /dev/null @@ -1,44 +0,0 @@ -//Profile config names for nf-core/configs - -params { - // Config Params - config_profile_description = 'Imperial College London - MEDBIO QUEUE - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'NA' - config_profile_url = 'https://www.imperial.ac.uk/bioinformatics-data-science-group/resources/uk-med-bio/' - - // Resources - max_memory = 640.GB - max_cpus = 32 - max_time = 168.h -} - -executor { - $pbspro { - queueSize = 50 - } - - $local { - cpus = 2 - queueSize = 1 - memory = '32 GB' - } -} - -singularity { - enabled = true - autoMounts = true - runOptions = "-B /rds/,/rdsgpfs/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" -} - -process { - - executor = 'pbspro' - queue = 'pqmedbio-tput' - - //queue = 'med-bio' //!! this is an alias and shouldn't be used - - //withLabel:process_large { - //queue = 'pqmedbio-large' //!! this queue is unavailable as of Feb 2022 - //} - -} From 38a05a6531051067a4c97e2fa8561899cfdf61fd Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 10 Feb 2022 23:46:14 +0000 Subject: [PATCH 51/65] Update imperial.config Reworked to use internal profiles for the Imperial HPC and the MedBio cluster. --- conf/imperial.config | 114 ++++++++++++++++++++++++++----------------- 1 file changed, 70 insertions(+), 44 deletions(-) diff --git a/conf/imperial.config b/conf/imperial.config index e2a3aca..26742f2 100644 --- a/conf/imperial.config +++ b/conf/imperial.config @@ -1,14 +1,76 @@ //Profile config names for nf-core/configs -params { - // Config Params - config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' - config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' +profiles { + imperial { + params { + // Config Params + config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' + config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' - // Resources - max_memory = 480.GB - max_cpus = 40 - max_time = 1000.h + // Resources + max_memory = 480.GB + max_cpus = 40 + max_time = 1000.h + } + + process { + executor = 'pbspro' + + // Process-specific resource requirements + withLabel:process_low { + // TARGET QUEUE: throughput + cpus = { 2 * task.attempt } + memory = { 12.GB * task.attempt } + time = { 4.h * task.attempt } + } + withLabel:process_medium { + // TARGET QUEUE: throughput + cpus = 8 + memory = { 32.GB * task.attempt } + time = { 8.h * task.attempt } + } + withLabel:process_high { + // TARGET QUEUE: general + cpus = 32 + memory = { 62.GB * task.attempt } + time = { 16.h * task.attempt } + } + withLabel:process_long { + // TARGET QUEUE: long + cpus = 8 + memory = 96.GB + time = { 72.h * task.attempt } + } + withLabel:process_high_memory { + // TARGET QUEUE: large memory + cpus = { 10 * task.attempt } + memory = { 120.GB * task.attempt } + time = { 12.h * task.attempt } + } + } + } + medbio { + params { + // Config Params + config_profile_description = 'Imperial College London - MEDBIO QUEUE - HPC Profile -- provided by nf-core/configs.' + config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_url = 'https://www.imperial.ac.uk/bioinformatics-data-science-group/resources/uk-med-bio/' + + // Resources + max_memory = 480.GB + max_cpus = 40 + max_time = 1000.h + } + + process { + executor = 'pbspro' + + queue = 'pqmedbio-tput' + + //queue = 'med-bio' //!! this is an alias and shouldn't be used + } + } } executor { @@ -28,39 +90,3 @@ singularity { autoMounts = true runOptions = "-B /rds/,/rds/general/user/$USER/ephemeral/tmp/:/tmp,/rds/general/user/$USER/ephemeral/tmp/:/var/tmp" } - -process { - executor = 'pbspro' - - // Process-specific resource requirements - withLabel:process_low { - // TARGET QUEUE: throughput - cpus = { check_max( 2 * task.attempt, 'cpus' ) } - memory = { check_max( 12.GB * task.attempt, 'memory' ) } - time = { check_max( 4.h * task.attempt, 'time' ) } - } - withLabel:process_medium { - // TARGET QUEUE: throughput - cpus = { check_max( 8, 'cpus' ) } - memory = { check_max( 32.GB * task.attempt, 'memory' ) } - time = { check_max( 8.h * task.attempt, 'time' ) } - } - withLabel:process_high { - // TARGET QUEUE: general - cpus = { check_max( 32, 'cpus' ) } - memory = { check_max( 62.GB * task.attempt, 'memory' ) } - time = { check_max( 16.h * task.attempt, 'time' ) } - } - withLabel:process_long { - // TARGET QUEUE: long - cpus = { check_max( 8, 'cpus' ) } - memory = { check_max( 96.GB, 'memory' ) } - time = { check_max( 72.h * task.attempt, 'time' ) } - } - withLabel:process_high_memory { - // TARGET QUEUE: large memory - cpus = { check_max( 10 * task.attempt, 'cpus' ) } - memory = { check_max( 120.GB * task.attempt, 'memory' ) } - time = { check_max( 12.h * task.attempt, 'time' ) } - } -} From 14c7662762601298ecd9fc18dbd173212c742be8 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Thu, 10 Feb 2022 23:49:43 +0000 Subject: [PATCH 52/65] Update imperial.md Updated docs to reflect restructuring for internal profiles --- docs/imperial.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/imperial.md b/docs/imperial.md index 43fc117..fe7883a 100644 --- a/docs/imperial.md +++ b/docs/imperial.md @@ -8,9 +8,11 @@ Before running the pipeline you will need to load Nextflow using the environment ```bash ## Load Nextflow and Singularity environment modules -module load Nextflow +module load anaconda3/personal +conda install -c bioconda nextflow ``` >NB: You will need an account to use the HPC cluster CX1 in order to run the pipeline. If in doubt contact IT. >NB: Nextflow will need to submit the jobs via the job scheduler to the HPC cluster and as such the commands above will have to be executed on one of the login nodes. If in doubt contact IT. >NB: To submit jobs to the Imperial College MEDBIO cluster, use `-profile imperial_mb` instead. +>NB: You will need a restricted access account to use the HPC cluster MEDBIO. From 5aa1abda26f4d14598bc47b587d4a010c9719a13 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 00:07:05 +0000 Subject: [PATCH 53/65] Delete imperial_mb.md Deprecated in favour of internal profiles within the single imperial.config --- docs/imperial_mb.md | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 docs/imperial_mb.md diff --git a/docs/imperial_mb.md b/docs/imperial_mb.md deleted file mode 100644 index d7f7f15..0000000 --- a/docs/imperial_mb.md +++ /dev/null @@ -1,16 +0,0 @@ -# nf-core/configs: Imperial MEDBIO HPC Configuration - -All nf-core pipelines have been successfully configured for use on the MEDBIO cluster at Imperial College London HPC. - -To use, run the pipeline with `-profile imperial_mb`. This will download and launch the [`imperial_mb.config`](../conf/imperial_mb.config) which has been pre-configured with a setup suitable for the MEDBIO cluster. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. - -Before running the pipeline you will need to load Nextflow using the environment module system on the head node. You can do this by issuing the commands below: - -```bash -## Load Nextflow and Singularity environment modules -module load Nextflow -``` - ->NB: You will need an account to use the HPC cluster MEDBIO in order to run the pipeline. Access to the MEDBIO queue is exclusive. If in doubt contact IT. ->NB: Nextflow will need to submit the jobs via the job scheduler to the HPC cluster and as such the commands above will have to be executed on one of the login nodes. If in doubt contact IT. ->NB: To submit jobs to the standard CX1 cluster at Imperial College, use `-profile imperial` instead. From 34d9e7a967132e5006362c938ad8d3a609bc5fc6 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 00:08:08 +0000 Subject: [PATCH 54/65] Update imperial.md Updated docs to reflect use of internal profiles --- docs/imperial.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/imperial.md b/docs/imperial.md index fe7883a..158827c 100644 --- a/docs/imperial.md +++ b/docs/imperial.md @@ -2,7 +2,7 @@ All nf-core pipelines have been successfully configured for use on the CX1 cluster at Imperial College London HPC. -To use, run the pipeline with `-profile imperial`. This will download and launch the [`imperial.config`](../conf/imperial.config) which has been pre-configured with a setup suitable for the CX1 cluster. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. +To use, run the pipeline with `-profile imperial,standard`. This will download and launch the [`imperial.config`](../conf/imperial.config) which has been pre-configured with a setup suitable for the CX1 cluster. Using this profile, a docker image containing all of the required software will be downloaded, and converted to a Singularity image before execution of the pipeline. Before running the pipeline you will need to load Nextflow using the environment module system on the CX1 cluster. You can do this by issuing the commands below: @@ -14,5 +14,5 @@ conda install -c bioconda nextflow >NB: You will need an account to use the HPC cluster CX1 in order to run the pipeline. If in doubt contact IT. >NB: Nextflow will need to submit the jobs via the job scheduler to the HPC cluster and as such the commands above will have to be executed on one of the login nodes. If in doubt contact IT. ->NB: To submit jobs to the Imperial College MEDBIO cluster, use `-profile imperial_mb` instead. +>NB: To submit jobs to the Imperial College MEDBIO cluster, use `-profile imperial,medbio` instead. >NB: You will need a restricted access account to use the HPC cluster MEDBIO. From c5e4ac2025a633e7ba2820d4381a0e7a65dc5852 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 00:25:44 +0000 Subject: [PATCH 55/65] Update scflow.config Removed line corresponding to profile deprecated by change to internal profiles --- pipeline/scflow.config | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/pipeline/scflow.config b/pipeline/scflow.config index 8c4697f..0ff19ea 100644 --- a/pipeline/scflow.config +++ b/pipeline/scflow.config @@ -10,5 +10,4 @@ profiles { imperial { includeConfig "${params.custom_config_base}/conf/pipeline/scflow/imperial.config" } - imperial_mb { includeConfig "${params.custom_config_base}/conf/pipeline/scflow/imperial.config" } // intended -} \ No newline at end of file +} From b99b74b2d38045f4737e24f385c4f141ce4a0c24 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 00:26:45 +0000 Subject: [PATCH 56/65] Update imperial.config Fixed indent --- conf/imperial.config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/conf/imperial.config b/conf/imperial.config index 26742f2..9f560e0 100644 --- a/conf/imperial.config +++ b/conf/imperial.config @@ -68,7 +68,7 @@ profiles { queue = 'pqmedbio-tput' - //queue = 'med-bio' //!! this is an alias and shouldn't be used + //queue = 'med-bio' //!! this is an alias and shouldn't be used } } } From f33bc965d65fc2527da7dd7510add7072118292b Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 09:32:50 +0000 Subject: [PATCH 57/65] Update nfcore_custom.config Removed deprecated medbio config --- nfcore_custom.config | 1 - 1 file changed, 1 deletion(-) diff --git a/nfcore_custom.config b/nfcore_custom.config index f580206..a242948 100644 --- a/nfcore_custom.config +++ b/nfcore_custom.config @@ -41,7 +41,6 @@ profiles { icr_davros { includeConfig "${params.custom_config_base}/conf/icr_davros.config" } ifb_core { includeConfig "${params.custom_config_base}/conf/ifb_core.config" } imperial { includeConfig "${params.custom_config_base}/conf/imperial.config" } - imperial_mb { includeConfig "${params.custom_config_base}/conf/imperial_mb.config" } jax { includeConfig "${params.custom_config_base}/conf/jax.config" } lugh { includeConfig "${params.custom_config_base}/conf/lugh.config" } maestro { includeConfig "${params.custom_config_base}/conf/maestro.config" } From 8937699abe617297743272e5baf2f90bd86b45d3 Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 09:33:54 +0000 Subject: [PATCH 58/65] Update README.md Added imperial docs link --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index f2accc6..d0e703f 100644 --- a/README.md +++ b/README.md @@ -113,6 +113,7 @@ Currently documentation is available for the following systems: * [HASTA](docs/hasta.md) * [HEBBE](docs/hebbe.md) * [ICR_DAVROS](docs/icr_davros.md) +* [IMPERIAL](docs/imperial.md) * [JAX](docs/jax.md) * [LUGH](docs/lugh.md) * [MAESTRO](docs/maestro.md) From 683564de1baac42ffc789232e0944d9edd80055b Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 09:35:18 +0000 Subject: [PATCH 59/65] Update main.yml Removed deprecated imperial medbio from GHA --- .github/workflows/main.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml index a3b41fd..9f260cd 100644 --- a/.github/workflows/main.yml +++ b/.github/workflows/main.yml @@ -47,7 +47,6 @@ jobs: - 'icr_davros' - 'ifb_core' - 'imperial' - - 'imperial_mb' - 'jax' - 'lugh' - 'maestro' From 3ce32f50c45b44ca1226f1a60b6cf821a26315df Mon Sep 17 00:00:00 2001 From: Combiz Khozoie <31043044+combiz@users.noreply.github.com> Date: Fri, 11 Feb 2022 11:02:40 +0000 Subject: [PATCH 60/65] Update imperial.config Moved params configs from internal profile to universal --- conf/imperial.config | 36 ++++++++++++------------------------ 1 file changed, 12 insertions(+), 24 deletions(-) diff --git a/conf/imperial.config b/conf/imperial.config index 9f560e0..729d623 100644 --- a/conf/imperial.config +++ b/conf/imperial.config @@ -1,19 +1,19 @@ //Profile config names for nf-core/configs +params { + // Config Params + config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' + config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' + config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' + + // Resources + max_memory = 480.GB + max_cpus = 40 + max_time = 1000.h +} + profiles { imperial { - params { - // Config Params - config_profile_description = 'Imperial College London - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' - config_profile_url = 'https://www.imperial.ac.uk/admin-services/ict/self-service/research-support/rcs/' - - // Resources - max_memory = 480.GB - max_cpus = 40 - max_time = 1000.h - } - process { executor = 'pbspro' @@ -51,18 +51,6 @@ profiles { } } medbio { - params { - // Config Params - config_profile_description = 'Imperial College London - MEDBIO QUEUE - HPC Profile -- provided by nf-core/configs.' - config_profile_contact = 'Combiz Khozoie (c.khozoie@imperial.ac.uk)' - config_profile_url = 'https://www.imperial.ac.uk/bioinformatics-data-science-group/resources/uk-med-bio/' - - // Resources - max_memory = 480.GB - max_cpus = 40 - max_time = 1000.h - } - process { executor = 'pbspro' From fcc856c8da5f76446b5fba182061008566046f3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matthias=20H=C3=B6rtenhuber?= Date: Fri, 11 Feb 2022 11:03:18 +0000 Subject: [PATCH 61/65] update node version for markdownlint --- .github/workflows/linting.yml | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index f6a2458..0fa938a 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -7,9 +7,7 @@ jobs: runs-on: ubuntu-18.04 steps: - uses: actions/checkout@v1 - - uses: actions/setup-node@v1 - with: - node-version: '10' + - uses: actions/setup-node@v2 - name: Install markdownlint run: | npm install -g markdownlint-cli From b98ab26662f3683a898078d235bccc782f3178b3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matthias=20H=C3=B6rtenhuber?= Date: Fri, 11 Feb 2022 14:09:16 +0100 Subject: [PATCH 62/65] fix markdownlint errors --- docs/czbiohub.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/czbiohub.md b/docs/czbiohub.md index 03f0edd..376460b 100644 --- a/docs/czbiohub.md +++ b/docs/czbiohub.md @@ -125,7 +125,7 @@ For Human and Mouse, we use [GENCODE](https://www.gencodegenes.org/) gene annota ## High Priority Queue -If you would like to run with the _High Priority_ queue, specify the `highpriority` config profile after `czbiohub_aws`. When applied after the main `czbiohub_aws` config, it overwrites the process `queue` identifier. +If you would like to run with the *High Priority* queue, specify the `highpriority` config profile after `czbiohub_aws`. When applied after the main `czbiohub_aws` config, it overwrites the process `queue` identifier. To use it, submit your run with with `-profile czbiohub_aws,highpriority`. From 90936a5518854d651f50f96b2c80014cccba96a3 Mon Sep 17 00:00:00 2001 From: Praveen Raj S <43108054+praveenraj2018@users.noreply.github.com> Date: Mon, 14 Feb 2022 12:45:20 +0100 Subject: [PATCH 63/65] Added: runOptions to singularity To bind external mount directories at runtime. --- conf/munin.config | 1 + 1 file changed, 1 insertion(+) diff --git a/conf/munin.config b/conf/munin.config index 3902e29..9d08ec5 100644 --- a/conf/munin.config +++ b/conf/munin.config @@ -22,6 +22,7 @@ process { singularity { enabled = true + runOptions = "--bind /media/BTB_2021_01" cacheDir = '/data1/containers/' } From 41e00ae8f90836d6c4e1678e851424671d8f310f Mon Sep 17 00:00:00 2001 From: "Maxime U. Garcia" Date: Mon, 14 Feb 2022 13:11:46 +0100 Subject: [PATCH 64/65] Update conf/munin.config --- conf/munin.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/conf/munin.config b/conf/munin.config index 9d08ec5..6b854fb 100644 --- a/conf/munin.config +++ b/conf/munin.config @@ -21,9 +21,9 @@ process { } singularity { - enabled = true + cacheDir = '/data1/containers/' + enabled = true runOptions = "--bind /media/BTB_2021_01" - cacheDir = '/data1/containers/' } // To use docker, use nextflow run -profile munin,docker From dcba537d15673112d95a7797cbf252c0a03b1589 Mon Sep 17 00:00:00 2001 From: Mei Wu <25568561+projectoriented@users.noreply.github.com> Date: Mon, 21 Feb 2022 16:19:17 +0100 Subject: [PATCH 65/65] picard md is single threaded --- conf/pipeline/raredisease/hasta.config | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/conf/pipeline/raredisease/hasta.config b/conf/pipeline/raredisease/hasta.config index 2c6ed48..96e3332 100644 --- a/conf/pipeline/raredisease/hasta.config +++ b/conf/pipeline/raredisease/hasta.config @@ -1,8 +1,7 @@ process { withName:'PICARD_MARKDUPLICATES' { - cpus = { check_max( 13 * task.attempt, 'cpus' ) } - memory = { check_max( 130.GB * task.attempt, 'memory' ) } + memory = { check_max( 90.GB * task.attempt, 'memory' ) } } withName:'DEEPVARIANT' { cpus = { check_max( 16 * task.attempt, 'cpus' ) }