From b4d5330c0e7d41fb3511e6f2d1e938374ae9dece Mon Sep 17 00:00:00 2001 From: Praveen Date: Tue, 14 Dec 2021 03:52:37 +0100 Subject: [PATCH 1/4] 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 2/4] 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 3/4] 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 4/4] 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' }