From 178cc0ff089b7f616bf764b308dbf614cb4bbc23 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 20 Dec 2022 11:02:53 +0100 Subject: [PATCH 01/29] updates tiddit --- CHANGELOG.md | 7 +++++++ definitions/rd_dna_parameters.yaml | 2 +- lib/MIP/Constants.pm | 2 +- templates/mip_install_config.yaml | 4 ++-- 4 files changed, 11 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 305ec7aa5..802de3669 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,13 @@ All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/). +## Develop + +Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update +### Tools + +Tiddit 3.3.2 -> 3.4.0 + ## [11.1.1] - Updates chromgraph to version 1.3.1 diff --git a/definitions/rd_dna_parameters.yaml b/definitions/rd_dna_parameters.yaml index f6d96dccb..1a3240afd 100755 --- a/definitions/rd_dna_parameters.yaml +++ b/definitions/rd_dna_parameters.yaml @@ -1001,7 +1001,7 @@ sv_svdb_query_overlap: associated_recipe: - sv_annotate data_type: SCALAR - default: 0.5 + default: 0.8 type: recipe_argument sv_vcfanno_config: associated_recipe: diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm index 71547bd02..3fadd84df 100644 --- a/lib/MIP/Constants.pm +++ b/lib/MIP/Constants.pm @@ -82,7 +82,7 @@ Readonly our %ANALYSIS => ( ); ## Set MIP version -Readonly our $MIP_VERSION => q{11.1.1}; +Readonly our $MIP_VERSION => q{11.1.1-develop}; ## Cli Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160; diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index f25b6ddb6..2e1365c53 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -125,7 +125,7 @@ container: mip: executable: mip: - uri: docker.io/clinicalgenomics/mip:v11.1.1 + uri: docker.io/clinicalgenomics/mip:develop multiqc: executable: multiqc: @@ -221,7 +221,7 @@ container: tiddit: executable: tiddit: - uri: quay.io/biocontainers/tiddit:3.3.2--py39h5094d80_0 + uri: quay.io/repository/biocontainers/tiddit:3.4.0--py310hc2b7f4b_0 trim-galore: executable: trim_galore: From 33496460232541cce92768aaf0bcb3ba9b2656a6 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 20 Dec 2022 11:50:27 +0100 Subject: [PATCH 02/29] fix path to tiddit container --- templates/mip_install_config.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index 2e1365c53..00928fb08 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -221,7 +221,7 @@ container: tiddit: executable: tiddit: - uri: quay.io/repository/biocontainers/tiddit:3.4.0--py310hc2b7f4b_0 + uri: quay.io/biocontainers/tiddit:3.4.0--py310hc2b7f4b_0 trim-galore: executable: trim_galore: From 6e1e35bcc13b68939028966b457b0bc0287f2f87 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 20 Dec 2022 12:06:27 +0100 Subject: [PATCH 03/29] changed mip develop version syntax --- lib/MIP/Constants.pm | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm index 3fadd84df..8f8c7e6ad 100644 --- a/lib/MIP/Constants.pm +++ b/lib/MIP/Constants.pm @@ -82,7 +82,7 @@ Readonly our %ANALYSIS => ( ); ## Set MIP version -Readonly our $MIP_VERSION => q{11.1.1-develop}; +Readonly our $MIP_VERSION => q{11.1.2}; ## Cli Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160; From ecc7bf52e8037915d711340fa20ab362af697bc0 Mon Sep 17 00:00:00 2001 From: jemten Date: Thu, 22 Dec 2022 10:48:51 +0100 Subject: [PATCH 04/29] updates variant catalog for expansionhunter --- CHANGELOG.md | 4 ++ definitions/rd_dna_parameters.yaml | 2 +- lib/MIP/Constants.pm | 2 +- ...pansionhunter_variant_catalog_-4.0.2-.json | 0 .../mip_download_rd_dna_config_-1.0-.yaml | 45 +++++++------------ templates/mip_install_config.yaml | 2 +- 6 files changed, 22 insertions(+), 33 deletions(-) delete mode 100644 t/data/references/grch37_expansionhunter_variant_catalog_-4.0.2-.json diff --git a/CHANGELOG.md b/CHANGELOG.md index 305ec7aa5..0a88f165e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,10 @@ All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/). +## Develop + +Updates expansionhunter variant catalog + ## [11.1.1] - Updates chromgraph to version 1.3.1 diff --git a/definitions/rd_dna_parameters.yaml b/definitions/rd_dna_parameters.yaml index f6d96dccb..7e38d9c7b 100755 --- a/definitions/rd_dna_parameters.yaml +++ b/definitions/rd_dna_parameters.yaml @@ -866,7 +866,7 @@ expansionhunter_variant_catalog_file_path: associated_recipe: - expansionhunter data_type: SCALAR - default: grch37_expansionhunter_variant_catalog_-4.0.2-.json + default: grch37_expansionhunter_variant_catalog_-5.0.0-.json exists_check: file is_reference: 1 reference: reference_dir diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm index 71547bd02..8f8c7e6ad 100644 --- a/lib/MIP/Constants.pm +++ b/lib/MIP/Constants.pm @@ -82,7 +82,7 @@ Readonly our %ANALYSIS => ( ); ## Set MIP version -Readonly our $MIP_VERSION => q{11.1.1}; +Readonly our $MIP_VERSION => q{11.1.2}; ## Cli Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160; diff --git a/t/data/references/grch37_expansionhunter_variant_catalog_-4.0.2-.json b/t/data/references/grch37_expansionhunter_variant_catalog_-4.0.2-.json deleted file mode 100644 index e69de29bb..000000000 diff --git a/templates/mip_download_rd_dna_config_-1.0-.yaml b/templates/mip_download_rd_dna_config_-1.0-.yaml index e5daeb2e6..585795270 100644 --- a/templates/mip_download_rd_dna_config_-1.0-.yaml +++ b/templates/mip_download_rd_dna_config_-1.0-.yaml @@ -41,9 +41,8 @@ reference: - 20150915 - 20200310 expansionhunter: - - 3.0.1 - - 3.1.2 - 4.0.2 + - 5.0.0 gatk_mitochondrial_ref: - v0_m_amb - v0_m_ann @@ -445,20 +444,6 @@ reference_feature: url_prefix: https://raw.githubusercontent.com/dellytools/delly/master/excludeTemplates/ expansionhunter: grch37: - 3.0.1: - file: variant_catalog_grch37.json - file_check: variant_catalog_grch37.json.md5 - outfile: grch37_expansionhunter_variant_catalog_-3.0.1-.json - outfile_check: grch37_expansionhunter_variant_catalog_-3.0.1-.json.md5 - outfile_check_method: md5sum - url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v3.0.1/ - 3.1.2: - file: variant_catalog_grch37.json - file_check: variant_catalog_grch37.json.md5 - outfile: grch37_expansionhunter_variant_catalog_-3.1.2-.json - outfile_check: grch37_expansionhunter_variant_catalog_-3.1.2-.json.md5 - outfile_check_method: md5sum - url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v3.1.2/ 4.0.2: file: variant_catalog_grch37.json file_check: variant_catalog_grch37.json.md5 @@ -466,21 +451,14 @@ reference_feature: outfile_check: grch37_expansionhunter_variant_catalog_-4.0.2-.json.md5 outfile_check_method: md5sum url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v4.0.2/ - grch38: - 3.0.1: - file: variant_catalog_grch38.json - file_check: variant_catalog_grch38.json.md5 - outfile: grch38_expansionhunter_variant_catalog_-3.0.1-.json - outfile_check: grch38_expansionhunter_variant_catalog_-3.0.1-.json.md5 - outfile_check_method: md5sum - url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v3.0.1/ - 3.1.2: - file: variant_catalog_hg38.json - file_check: variant_catalog_hg38.json.md5 - outfile: grch38_expansionhunter_variant_catalog_-3.1.2-.json - outfile_check: grch38_expansionhunter_variant_catalog_-3.1.2-.json.md5 + 5.0.0: + file: variant_catalog_grch37.json + file_check: variant_catalog_grch37.json.md5 + outfile: grch37_expansionhunter_variant_catalog_-5.0.0-.json + outfile_check: grch37_expansionhunter_variant_catalog_-5.0.0-.json.md5 outfile_check_method: md5sum - url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v3.1.2/ + url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v5.0.0/ + grch38: 4.0.2: file: variant_catalog_hg38.json file_check: variant_catalog_hg38.json.md5 @@ -488,6 +466,13 @@ reference_feature: outfile_check: grch38_expansionhunter_variant_catalog_-4.0.2-.json.md5 outfile_check_method: md5sum url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v4.0.2/ + 5.0.0: + file: variant_catalog_hg38.json + file_check: variant_catalog_hg38.json.md5 + outfile: grch38_expansionhunter_variant_catalog_-5.0.0-.json + outfile_check: grch38_expansionhunter_variant_catalog_-5.0.0-.json.md5 + outfile_check_method: md5sum + url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/disease_loci/ExpansionHunter-v5.0.0/ gatk_mitochondrial_ref: grch38: v0_m_amb: diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index f25b6ddb6..74ddfd61e 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -125,7 +125,7 @@ container: mip: executable: mip: - uri: docker.io/clinicalgenomics/mip:v11.1.1 + uri: docker.io/clinicalgenomics/mip:develop multiqc: executable: multiqc: From 9006464b740c3fe922644f75150784a76a2b98c5 Mon Sep 17 00:00:00 2001 From: jemten Date: Thu, 22 Dec 2022 11:00:22 +0100 Subject: [PATCH 05/29] added test data file --- .../grch37_expansionhunter_variant_catalog_-5.0.0-.json | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 t/data/references/grch37_expansionhunter_variant_catalog_-5.0.0-.json diff --git a/t/data/references/grch37_expansionhunter_variant_catalog_-5.0.0-.json b/t/data/references/grch37_expansionhunter_variant_catalog_-5.0.0-.json new file mode 100644 index 000000000..e69de29bb From e62b681e11b0a1f8e5a81e2488dded400ad70412 Mon Sep 17 00:00:00 2001 From: jemten Date: Thu, 5 Jan 2023 11:47:55 +0100 Subject: [PATCH 06/29] bump memory for salmon quant --- CHANGELOG.md | 4 ++++ definitions/rd_rna_parameters.yaml | 2 +- lib/MIP/Constants.pm | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 305ec7aa5..53debb434 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,10 @@ All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/). +## Develop + +- Increased memory allocation for salmon + ## [11.1.1] - Updates chromgraph to version 1.3.1 diff --git a/definitions/rd_rna_parameters.yaml b/definitions/rd_rna_parameters.yaml index 685b904ec..31c7ec923 100755 --- a/definitions/rd_rna_parameters.yaml +++ b/definitions/rd_rna_parameters.yaml @@ -194,7 +194,7 @@ recipe_memory: picardtools_mergesamfiles: 5 preseq_ar: 8 rseqc: 40 - salmon_quant: 2 + salmon_quant: 4 star_aln: 5 star_fusion: 25 stringtie_ar: 2 diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm index 71547bd02..8f8c7e6ad 100644 --- a/lib/MIP/Constants.pm +++ b/lib/MIP/Constants.pm @@ -82,7 +82,7 @@ Readonly our %ANALYSIS => ( ); ## Set MIP version -Readonly our $MIP_VERSION => q{11.1.1}; +Readonly our $MIP_VERSION => q{11.1.2}; ## Cli Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160; From b6f71fd3c77372bde5dbdf29f415ddb36fec6734 Mon Sep 17 00:00:00 2001 From: jemten Date: Mon, 9 Jan 2023 14:26:33 +0100 Subject: [PATCH 07/29] increase mem for picardtools mergesamfiles --- CHANGELOG.md | 2 +- definitions/rd_rna_parameters.yaml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index e6434c497..ea175b54a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,7 +5,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). ## Develop -- Increased memory allocation for salmon +- Increased memory allocation for salmon and picardtools_mergersamfiles (RNA) - Updates expansionhunter variant catalog - Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update diff --git a/definitions/rd_rna_parameters.yaml b/definitions/rd_rna_parameters.yaml index 31c7ec923..52d43d54c 100755 --- a/definitions/rd_rna_parameters.yaml +++ b/definitions/rd_rna_parameters.yaml @@ -191,7 +191,7 @@ recipe_memory: merge_fusion_reports: 8 multiqc_ar: 10 picardtools_collectrnaseqmetrics: 10 - picardtools_mergesamfiles: 5 + picardtools_mergesamfiles: 8 preseq_ar: 8 rseqc: 40 salmon_quant: 4 From 2d1cc43deab74ea87d6d9c9b1026cfbc64729ef2 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 10 Jan 2023 08:24:22 +0100 Subject: [PATCH 08/29] updates megafusion --- CHANGELOG.md | 4 +++- containers/megafusion/Dockerfile | 4 ++-- templates/mip_install_config.yaml | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index ea175b54a..12302120f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,10 +8,12 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Increased memory allocation for salmon and picardtools_mergersamfiles (RNA) - Updates expansionhunter variant catalog - Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update +- New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf. ### Tools -Tiddit 3.3.2 -> 3.4.0 +- Tiddit 3.3.2 -> 3.4.0 +- MegaFusion 66a3a80 -> d3feacf ## [11.1.1] diff --git a/containers/megafusion/Dockerfile b/containers/megafusion/Dockerfile index 60fd98924..dbb778bc8 100644 --- a/containers/megafusion/Dockerfile +++ b/containers/megafusion/Dockerfile @@ -7,7 +7,7 @@ FROM clinicalgenomics/mip_base:2.1 LABEL base_image="clinicalgenomics/mip_base:2.1" LABEL version="4" LABEL software="MegaFusion" -LABEL software.version="66a3a80" +LABEL software.version="d3feacf" LABEL extra.binaries="MegaFusion.py" LABEL maintainer="Clinical-Genomics/MIP" @@ -25,5 +25,5 @@ RUN git clone https://github.com/J35P312/MegaFusion.git /opt/conda/share/MegaFus WORKDIR /opt/conda/share/MegaFusion ## Make sure we're on the right commit -RUN git reset --hard 66a3a80 +RUN git reset --hard d3feacf diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index 00928fb08..45e6ee8c0 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -121,7 +121,7 @@ container: megafusion: executable: MegaFusion.py: "python /opt/conda/share/MegaFusion/MegaFusion.py" - uri: docker.io/clinicalgenomics/megafusion:66a3a80 + uri: docker.io/clinicalgenomics/megafusion:d3feacf mip: executable: mip: From 8ac8b7dca48a84e696bf37bafa8c3e2851932554 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 10 Jan 2023 15:26:43 +0100 Subject: [PATCH 09/29] remove rseqc read duplication analysis --- CHANGELOG.md | 1 + lib/MIP/Recipes/Analysis/Rseqc.pm | 10 ---------- 2 files changed, 1 insertion(+), 10 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 12302120f..7f76ef9cd 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Updates expansionhunter variant catalog - Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update - New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf. +- Remove the RSeQC read duplication analysis as it fails often. ### Tools diff --git a/lib/MIP/Recipes/Analysis/Rseqc.pm b/lib/MIP/Recipes/Analysis/Rseqc.pm index 931a6159e..6dd342ce6 100644 --- a/lib/MIP/Recipes/Analysis/Rseqc.pm +++ b/lib/MIP/Recipes/Analysis/Rseqc.pm @@ -292,16 +292,6 @@ sub analysis_rseqc { ); say {$filehandle} $NEWLINE; - say {$filehandle} q{## Rseqc read_duplication}; - rseqc_read_duplication( - { - filehandle => $filehandle, - infile_path => $infile_path, - outfiles_path_prefix => $outfile_path_prefix . $UNDERSCORE . q{read_duplication}, - } - ); - say {$filehandle} $NEWLINE; - close $filehandle; if ( $recipe{mode} == 1 ) { From d5787187fbf72a55a1035b4307ed7c6fe397ff07 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 10 Jan 2023 16:22:10 +0100 Subject: [PATCH 10/29] creating release branch --- CHANGELOG.md | 4 ++-- documentation/Setup.md | 2 +- lib/MIP/Constants.pm | 2 +- templates/mip_install_config.yaml | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 7f76ef9cd..95e57e8a8 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,13 +3,13 @@ All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/). -## Develop +## [11.2.0] - Increased memory allocation for salmon and picardtools_mergersamfiles (RNA) - Updates expansionhunter variant catalog - Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update - New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf. -- Remove the RSeQC read duplication analysis as it fails often. +- Remove the RSeQC read duplication analysis as it often fails. ### Tools diff --git a/documentation/Setup.md b/documentation/Setup.md index cc7fbc51a..ea4a2ef0a 100644 --- a/documentation/Setup.md +++ b/documentation/Setup.md @@ -77,7 +77,7 @@ You can speed up, for instance, the Readonly module by also installing the compa - [StringTie] (version: 2.1.3b) - [Svdb] (version: 2.4.0) - [Telomerecat] (version: 3.4.0) -- [Tiddit] (version: 2.12.1) +- [Tiddit] (version: 3.4.0) - [Upd] (version: 0.1.1) - [Varg] (version: 1.2.0) - [Vcf2cytosure] (version: 0.5.1) diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm index 8f8c7e6ad..a03ea8d72 100644 --- a/lib/MIP/Constants.pm +++ b/lib/MIP/Constants.pm @@ -82,7 +82,7 @@ Readonly our %ANALYSIS => ( ); ## Set MIP version -Readonly our $MIP_VERSION => q{11.1.2}; +Readonly our $MIP_VERSION => q{11.2.0}; ## Cli Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160; diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index 45e6ee8c0..cf132914d 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -125,7 +125,7 @@ container: mip: executable: mip: - uri: docker.io/clinicalgenomics/mip:develop + uri: docker.io/clinicalgenomics/mip:v11.2.0 multiqc: executable: multiqc: From a0f96e5d9569ad11eb3dea1dc95652fa4ff32a3b Mon Sep 17 00:00:00 2001 From: jemten Date: Wed, 11 Jan 2023 11:15:08 +0100 Subject: [PATCH 11/29] longer runtime for gatk_asereadcounter --- CHANGELOG.md | 1 + definitions/rd_rna_parameters.yaml | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 95e57e8a8..152194797 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,6 +10,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update - New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf. - Remove the RSeQC read duplication analysis as it often fails. +- Increased run time allocation for gatk_asereadcounter. ### Tools diff --git a/definitions/rd_rna_parameters.yaml b/definitions/rd_rna_parameters.yaml index 52d43d54c..324f76a18 100755 --- a/definitions/rd_rna_parameters.yaml +++ b/definitions/rd_rna_parameters.yaml @@ -146,7 +146,7 @@ recipe_time: dna_vcf_reformat: 1 fastqc_ar: 1 fusion_report: 8 - gatk_asereadcounter: 3 + gatk_asereadcounter: 8 gatk_baserecalibration: 5 gatk_haplotypecaller: 12 gatk_splitncigarreads: 16 From 3b4ace884d11c7298be0971fb93e10a00686a146 Mon Sep 17 00:00:00 2001 From: jemten Date: Mon, 23 Jan 2023 17:34:01 +0100 Subject: [PATCH 12/29] keep only trimmed rna reads longer than 40 bp --- CHANGELOG.md | 1 + definitions/rd_rna_parameters.yaml | 7 +++++++ lib/MIP/Cli/Mip/Analyse/Rd_rna.pm | 8 ++++++++ lib/MIP/Program/Trim_galore.pm | 11 +++++++++++ lib/MIP/Recipes/Analysis/Trim_galore.pm | 1 + t/trim_galore.t | 12 +++++++----- 6 files changed, 35 insertions(+), 5 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 152194797..6f2341108 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,6 +11,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). - New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf. - Remove the RSeQC read duplication analysis as it often fails. - Increased run time allocation for gatk_asereadcounter. +- Increased the default required length for a trimmed rna read to be retained from 20 bp to 40 bp. Configurable via CLI or config. ### Tools diff --git a/definitions/rd_rna_parameters.yaml b/definitions/rd_rna_parameters.yaml index 324f76a18..508b6578c 100755 --- a/definitions/rd_rna_parameters.yaml +++ b/definitions/rd_rna_parameters.yaml @@ -301,6 +301,13 @@ trim_galore_ar: program_executables: - trim_galore type: recipe +trim_min_length: + associated_recipe: + - trim_galore_ar + data_type: SCALAR + default: 40 + mandatory: no + type: recipe_argument ## Salmon salmon_quant: analysis_mode: sample diff --git a/lib/MIP/Cli/Mip/Analyse/Rd_rna.pm b/lib/MIP/Cli/Mip/Analyse/Rd_rna.pm index 4a807e871..10aa523bf 100644 --- a/lib/MIP/Cli/Mip/Analyse/Rd_rna.pm +++ b/lib/MIP/Cli/Mip/Analyse/Rd_rna.pm @@ -976,6 +976,14 @@ q{Regular expression file containing the regular expression to be used for each ) ); + option( + q{trim_min_length} => ( + documentation => q{Discard trimmed reads shorter than this}, + is => q{rw}, + isa => Int, + ) + ); + option( q{vcfparser_ar} => ( cmd_tags => [q{Analysis recipe switch}], diff --git a/lib/MIP/Program/Trim_galore.pm b/lib/MIP/Program/Trim_galore.pm index 876630ef4..0476664a4 100644 --- a/lib/MIP/Program/Trim_galore.pm +++ b/lib/MIP/Program/Trim_galore.pm @@ -37,6 +37,7 @@ sub trim_galore { ## : $filehandle => Filehandle to write to ## : $gzip_output => Gzip output fastq file ## : $infile_paths_ref => Infile paths {REF} +## : $length => Minimum length of trimmed read to retain ## : $outdir_path => Outdirectory path ## : $paired_reads => Do paired end trimming ## : $stderrfile_path => Stderrfile path @@ -50,6 +51,7 @@ sub trim_galore { my $cores; my $filehandle; my $infile_paths_ref; + my $length; my $outdir_path; my $paired_reads; my $stderrfile_path; @@ -88,6 +90,11 @@ sub trim_galore { store => \$infile_paths_ref, strict_type => 1, }, + length => { + allow => [ undef, qr/\A \d+ \z/xms ], + store => \$length, + strict_type => 1, + }, outdir_path => { store => \$outdir_path, strict_type => 1, @@ -137,6 +144,10 @@ sub trim_galore { push @commands, q{--paired}; } + if ($length) { + push @commands, q{--length} . $SPACE . $length; + } + push @commands, join $SPACE, @{$infile_paths_ref}; push @commands, diff --git a/lib/MIP/Recipes/Analysis/Trim_galore.pm b/lib/MIP/Recipes/Analysis/Trim_galore.pm index 9cfb2bbeb..decc92cb6 100644 --- a/lib/MIP/Recipes/Analysis/Trim_galore.pm +++ b/lib/MIP/Recipes/Analysis/Trim_galore.pm @@ -278,6 +278,7 @@ sub analysis_trim_galore { cores => $process_core_number, filehandle => $filehandle, infile_paths_ref => \@fastq_files, + length => $active_parameter_href->{trim_min_length}, outdir_path => $outsample_directory, paired_reads => $paired_reads, stderrfile_path => $stderrfile_path, diff --git a/t/trim_galore.t b/t/trim_galore.t index b2590ac79..e3adf2e64 100644 --- a/t/trim_galore.t +++ b/t/trim_galore.t @@ -23,16 +23,13 @@ use lib catdir( dirname($Bin), q{lib} ); use MIP::Constants qw{ $COMMA $SPACE }; use MIP::Test::Commands qw{ test_function }; - BEGIN { use MIP::Test::Fixtures qw{ test_import }; ### Check all internal dependency modules and imports ## Modules with import - my %perl_module = ( - q{MIP::Program::Trim_galore} => [qw{ trim_galore }], -); + my %perl_module = ( q{MIP::Program::Trim_galore} => [qw{ trim_galore }], ); test_import( { perl_module_href => \%perl_module, } ); } @@ -47,7 +44,8 @@ diag( q{Test trim_galore from Trim_galore.pm} . $SPACE . $EXECUTABLE_NAME ); -Readonly my $CORES => 12; +Readonly my $CORES => 12; +Readonly my $MIN_LENGTH => 30; ## Base arguments my @function_base_commands = qw{ trim_galore }; @@ -97,6 +95,10 @@ my %specific_argument = ( inputs_ref => [qw{ file_1.fastq file_2.fastq }], expected_output => q{file_1.fastq} . $SPACE . q{file_2.fastq}, }, + length => { + input => $MIN_LENGTH, + expected_output => q{--length} . $SPACE . $MIN_LENGTH, + }, outdir_path => { input => catdir(qw{ output dir }), expected_output => q{--output_dir} . $SPACE . catdir(qw{ output dir }), From 24ecad33135a4ee6ff92e11db608ac385b231ab7 Mon Sep 17 00:00:00 2001 From: jemten Date: Thu, 2 Feb 2023 09:56:21 +0100 Subject: [PATCH 13/29] update gnomad sv database --- CHANGELOG.md | 1 + lib/MIP/Recipes/Download/Gnomad.pm | 6 +++--- templates/mip_download_rd_dna_config_-1.0-.yaml | 14 +++++++------- 3 files changed, 11 insertions(+), 10 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6f2341108..894504326 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -12,6 +12,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Remove the RSeQC read duplication analysis as it often fails. - Increased run time allocation for gatk_asereadcounter. - Increased the default required length for a trimmed rna read to be retained from 20 bp to 40 bp. Configurable via CLI or config. +- Fixed a bug where gnomad SV version 2.0 instead of version 2.1 was used to annotate SVs ### Tools diff --git a/lib/MIP/Recipes/Download/Gnomad.pm b/lib/MIP/Recipes/Download/Gnomad.pm index 3adda2fcc..7c9f97feb 100644 --- a/lib/MIP/Recipes/Download/Gnomad.pm +++ b/lib/MIP/Recipes/Download/Gnomad.pm @@ -201,7 +201,7 @@ sub download_gnomad { }, method => \&_annotate, }, - q{r2.1.1_sv} => { + q{r2.1_sv} => { arg_href => { info_keys_ref => [qw{ INFO/AC INFO/AF INFO/POPMAX_AF }], }, @@ -723,7 +723,7 @@ sub _build_af_file { strict_type => 1, }, reference_version => { - allow => [qw{ r2.0.1 r2.1.1 r2.1.1_sv r3.1.1 r3.1.2 }], + allow => [qw{ r2.0.1 r2.1.1 r2.1_sv r3.1.1 r3.1.2 }], required => 1, store => \$reference_version, strict_type => 1, @@ -737,7 +737,7 @@ sub _build_af_file { use MIP::Program::Htslib qw{ htslib_bgzip htslib_tabix }; ## Don't build file for SV:s - return if ( $reference_version eq q{r2.1.1_sv} ); + return if ( $reference_version eq q{r2.1_sv} ); my $outfile_no_suffix = remove_file_path_suffix( { diff --git a/templates/mip_download_rd_dna_config_-1.0-.yaml b/templates/mip_download_rd_dna_config_-1.0-.yaml index 585795270..c8a478952 100644 --- a/templates/mip_download_rd_dna_config_-1.0-.yaml +++ b/templates/mip_download_rd_dna_config_-1.0-.yaml @@ -91,7 +91,7 @@ reference: gnomad: - r2.0.1 - r2.1.1 - - r2.1.1_sv + - r2.1_sv gnomad_chrsplit: - r3.1.1 - r3.1.2 @@ -789,12 +789,12 @@ reference_feature: outfile: grch37_gnomad.genomes_-r2.1.1-.vcf.gz outfile_index: grch37_gnomad.genomes_-r2.1.1-.vcf.gz.tbi url_prefix: https://storage.googleapis.com/gnomad-public/release/2.1.1/vcf/genomes/ - r2.1.1_sv: - file: gnomad_v2_sv.sites.vcf.gz - file_index: gnomad_v2_sv.sites.vcf.gz.tbi - outfile: grch37_gnomad.genomes_-r2.1.1_sv-.vcf.gz - outfile_index: grch37_gnomad.genomes_-r2.1.1_sv-.vcf.gz.tbi - url_prefix: https://storage.googleapis.com/gnomad-public/papers/2019-sv/ + r2.1_sv: + file: gnomad_v2.1_sv.sites.vcf.gz + file_index: gnomad_v2.1_sv.sites.vcf.gz.tbi + outfile: grch37_gnomad.genomes_-r2.1_sv-.vcf.gz + outfile_index: grch37_gnomad.genomes_-r2.1_sv-.vcf.gz.tbi + url_prefix: https://storage.googleapis.com/gcp-public-data--gnomad/papers/2019-sv/gnomad_v2.1_sv.sites.vcf.gz grch38: r2.1.1: file: gnomad.genomes.r2.1.1.sites.liftover_grch38.vcf.bgz From d80aca3fc0f394fb294eca7266549c59b00c1f01 Mon Sep 17 00:00:00 2001 From: jemten Date: Thu, 2 Feb 2023 10:39:21 +0100 Subject: [PATCH 14/29] fixing url --- templates/mip_download_rd_dna_config_-1.0-.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/templates/mip_download_rd_dna_config_-1.0-.yaml b/templates/mip_download_rd_dna_config_-1.0-.yaml index c8a478952..9f48aea1c 100644 --- a/templates/mip_download_rd_dna_config_-1.0-.yaml +++ b/templates/mip_download_rd_dna_config_-1.0-.yaml @@ -794,7 +794,7 @@ reference_feature: file_index: gnomad_v2.1_sv.sites.vcf.gz.tbi outfile: grch37_gnomad.genomes_-r2.1_sv-.vcf.gz outfile_index: grch37_gnomad.genomes_-r2.1_sv-.vcf.gz.tbi - url_prefix: https://storage.googleapis.com/gcp-public-data--gnomad/papers/2019-sv/gnomad_v2.1_sv.sites.vcf.gz + url_prefix: https://storage.googleapis.com/gcp-public-data--gnomad/papers/2019-sv/ grch38: r2.1.1: file: gnomad.genomes.r2.1.1.sites.liftover_grch38.vcf.bgz From 142f3abbf172fc1847928a632f9c94602428d68e Mon Sep 17 00:00:00 2001 From: jemten Date: Mon, 13 Feb 2023 17:34:37 +0100 Subject: [PATCH 15/29] fixing MT deletetion calculation, fixes #2016 --- CHANGELOG.md | 1 + lib/MIP/Recipes/Analysis/Mitodel.pm | 9 ++++++--- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 894504326..9917eabcd 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -13,6 +13,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Increased run time allocation for gatk_asereadcounter. - Increased the default required length for a trimmed rna read to be retained from 20 bp to 40 bp. Configurable via CLI or config. - Fixed a bug where gnomad SV version 2.0 instead of version 2.1 was used to annotate SVs +- Fixed a bug in the mitochondrial deletion recipe affecting samples with 0 intermediate discordant MT reads ### Tools diff --git a/lib/MIP/Recipes/Analysis/Mitodel.pm b/lib/MIP/Recipes/Analysis/Mitodel.pm index 0729f16f3..6f2563f40 100644 --- a/lib/MIP/Recipes/Analysis/Mitodel.pm +++ b/lib/MIP/Recipes/Analysis/Mitodel.pm @@ -230,14 +230,17 @@ sub analysis_mitodel { my $awk_statement = + # Set start value for intermediate discordant + q?BEGIN {sum=0} ? + # identification of read pairs that are separated by >1.2 kb but <15 kb - q?($2>=1200 && $2<=15000) {sum=sum+$3}? + . q?($2>=1200 && $2<=15000) {sum=sum+$3} ? # identification of normal read pairs which are <1.2 kb but >15 kb - . q?($2<1200 || $2>15000) {sum_norm=sum_norm+$3}? + . q?($2<1200 || $2>15000) {sum_norm=sum_norm+$3} ? # Add end rule - . q?END? + . q?END ? # ratio of discordant to normal read pairs . q?{print "intermediate discordant ", sum, "normal ", sum_norm, "ratio ppk", sum*1000/(sum_norm+sum)}?; From 6366de05fc1b372c136088e254d93921c55de399 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 21 Feb 2023 09:09:42 +0100 Subject: [PATCH 16/29] updates clinvar and loqus --- CHANGELOG.md | 7 +- ...ch37_clinvar_reformated_-20230218-.vcf.gz} | 0 ..._clinvar_reformated_-20230218-.vcf.gz.tbi} | 0 ..._loqusdb_sv_variants_export-20230214-.vcf} | 0 .../mip_download_rd_dna_config_-1.0-.yaml | 84 +++++++++---------- templates/mip_rd_dna_config.yaml | 4 +- 6 files changed, 50 insertions(+), 45 deletions(-) rename t/data/references/{grch37_clinvar_reformated_-20220829-.vcf.gz => grch37_clinvar_reformated_-20230218-.vcf.gz} (100%) rename t/data/references/{grch37_clinvar_reformated_-20220829-.vcf.gz.tbi => grch37_clinvar_reformated_-20230218-.vcf.gz.tbi} (100%) rename t/data/references/{grch37_loqusdb_sv_variants_export-20220905-.vcf => grch37_loqusdb_sv_variants_export-20230214-.vcf} (100%) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9917eabcd..8713b4e65 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -20,6 +20,11 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Tiddit 3.3.2 -> 3.4.0 - MegaFusion 66a3a80 -> d3feacf +### Databases + +clinvar: 20220829 -> 20230218 +loqusdb snapshot: 20230208 -> 20230214 + ## [11.1.1] - Updates chromgraph to version 1.3.1 @@ -69,7 +74,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). - dbnsfp: 4.1a -> 4.3a (grch38 only) - gnomad: r3.1.1 -> r3.1.2 (grch38 only) - giab: 3.3.2 -> 4.2.1 -- loqusdb dump: 20210921 -> 20220905 +- loqusdb dump: 20210921 -> c - nist: v3.3.2 -> v4.2.1 - vcf2cytosure blacklist: 200520 diff --git a/t/data/references/grch37_clinvar_reformated_-20220829-.vcf.gz b/t/data/references/grch37_clinvar_reformated_-20230218-.vcf.gz similarity index 100% rename from t/data/references/grch37_clinvar_reformated_-20220829-.vcf.gz rename to t/data/references/grch37_clinvar_reformated_-20230218-.vcf.gz diff --git a/t/data/references/grch37_clinvar_reformated_-20220829-.vcf.gz.tbi b/t/data/references/grch37_clinvar_reformated_-20230218-.vcf.gz.tbi similarity index 100% rename from t/data/references/grch37_clinvar_reformated_-20220829-.vcf.gz.tbi rename to t/data/references/grch37_clinvar_reformated_-20230218-.vcf.gz.tbi diff --git a/t/data/references/grch37_loqusdb_sv_variants_export-20220905-.vcf b/t/data/references/grch37_loqusdb_sv_variants_export-20230214-.vcf similarity index 100% rename from t/data/references/grch37_loqusdb_sv_variants_export-20220905-.vcf rename to t/data/references/grch37_loqusdb_sv_variants_export-20230214-.vcf diff --git a/templates/mip_download_rd_dna_config_-1.0-.yaml b/templates/mip_download_rd_dna_config_-1.0-.yaml index 9f48aea1c..5982bdc46 100644 --- a/templates/mip_download_rd_dna_config_-1.0-.yaml +++ b/templates/mip_download_rd_dna_config_-1.0-.yaml @@ -26,8 +26,8 @@ reference: chromograph_cytoband: - v1.0 clinvar: - - 20211010 - 20220829 + - 20230218 dbnsfp: - 3.5a - 4.1a @@ -111,8 +111,8 @@ reference: - gold_standard_indels rank_model: - v0.2 - - v1.33 - v1.34 + - v1.35 reduced_penetrance: - 2017 scout_exons: @@ -124,8 +124,8 @@ reference: - v1.4 svrank_model: - v0.1 - - v1.8 - v1.9 + - v1.10 vcf2cytosure_blacklist_regions: - 1.0 - 200520 @@ -323,15 +323,6 @@ reference_feature: url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/region/ clinvar: grch37: - 20211010: - file: clinvar_20211010.vcf.gz - file_check: clinvar_20211010.vcf.gz.md5 - file_index: clinvar_20211010.vcf.gz.tbi - outfile: grch37_clinvar_-20211010-.vcf.gz - outfile_check: grch37_clinvar_-20211010-.vcf.gz.md5 - outfile_index: grch37_clinvar_-20211010-.vcf.gz.tbi - outfile_check_method: md5sum - url_prefix: ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh37/weekly/ 20220829: file: clinvar_20220829.vcf.gz file_check: clinvar_20220829.vcf.gz.md5 @@ -341,16 +332,16 @@ reference_feature: outfile_index: grch37_clinvar_-20220829-.vcf.gz.tbi outfile_check_method: md5sum url_prefix: https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh37/weekly/ - grch38: - 20211010: - file: clinvar_20211010.vcf.gz - file_check: clinvar_20211010.vcf.gz.md5 - file_index: clinvar_20211010.vcf.gz.tbi - outfile: grch38_clinvar_-20211010-.vcf.gz - outfile_check: grch38_clinvar_-20211010-.vcf.gz.md5 - outfile_index: grch38_clinvar_-20211010-.vcf.gz.tbi + 20230218: + file: clinvar_20230218.vcf.gz + file_check: clinvar_20230218.vcf.gz.md5 + file_index: clinvar_20230218.vcf.gz.tbi + outfile: grch37_clinvar_-20230218-.vcf.gz + outfile_check: grch37_clinvar_-20230218-.vcf.gz.md5 + outfile_index: grch37_clinvar_-20230218-.vcf.gz.tbi outfile_check_method: md5sum - url_prefix: https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/weekly/ + url_prefix: ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh37/weekly/ + grch38: 20220829: file: clinvar_20220829.vcf.gz file_check: clinvar_20220829.vcf.gz.md5 @@ -360,6 +351,15 @@ reference_feature: outfile_index: grch38_clinvar_-20220829-.vcf.gz.tbi outfile_check_method: md5sum url_prefix: https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/weekly/ + 20230218: + file: clinvar_20230218.vcf.gz + file_check: clinvar_20230218.vcf.gz.md5 + file_index: clinvar_20230218.vcf.gz.tbi + outfile: grch38_clinvar_-20230218-.vcf.gz + outfile_check: grch38_clinvar_-20230218-.vcf.gz.md5 + outfile_index: grch38_clinvar_-20230218-.vcf.gz.tbi + outfile_check_method: md5sum + url_prefix: https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/weekly/ dbnsfp: grch37: 3.5a: @@ -900,13 +900,6 @@ reference_feature: url_prefix: https://storage.googleapis.com/genomics-public-data/resources/broad/hg38/v0/ rank_model: grch37: - v1.33: - file: rank_model_-v1.33-.ini - file_check: rank_model_-v1.33-.ini.md5 - outfile: rank_model_-v1.33-.ini - outfile_check: rank_model_-v1.33-.ini.md5 - outfile_check_method: md5sum - url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/rank_model/ v1.34: file: rank_model_-v1.34-.ini file_check: rank_model_-v1.34-.ini.md5 @@ -914,6 +907,13 @@ reference_feature: outfile_check: rank_model_-v1.34-.ini.md5 outfile_check_method: md5sum url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/rank_model/ + v1.35: + file: rank_model_-v1.35-.ini + file_check: rank_model_-v1.35-.ini.md5 + outfile: rank_model_-v1.35-.ini + outfile_check: rank_model_-v1.35-.ini.md5 + outfile_check_method: md5sum + url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/rank_model/ grch38: v0.2: file: grch38_rank_model_-v0.2-.ini @@ -971,13 +971,6 @@ reference_feature: url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/annotation/ svrank_model: grch37: - v1.8: - file: svrank_model_-v1.8-.ini - file_check: svrank_model_-v1.8-.ini.md5 - outfile: svrank_model_-v1.8-.ini - outfile_check: svrank_model_-v1.8-.ini.md5 - outfile_check_method: md5sum - url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/rank_model/ v1.9: file: svrank_model_-v1.9-.ini file_check: svrank_model_-v1.9-.ini.md5 @@ -985,6 +978,13 @@ reference_feature: outfile_check: svrank_model_-v1.9-.ini.md5 outfile_check_method: md5sum url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/rank_model/ + v1.10: + file: svrank_model_-v1.10-.ini + file_check: svrank_model_-v1.10-.ini.md5 + outfile: svrank_model_-v1.10-.ini + outfile_check: svrank_model_-v1.10-.ini.md5 + outfile_check_method: md5sum + url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/rank_model/ grch38: v0.1: file: grch38_sv_rank_model_-v0.1-.ini @@ -1010,13 +1010,6 @@ reference_feature: url_prefix: https://www.encodeproject.org/files/ENCFF356LFX/@@download/ vcfanno_config: grch37: - v1.17: - file: grch37_vcfanno_config_-v1.17-.toml - file_check: grch37_vcfanno_config_-v1.17-.toml.md5 - outfile: grch37_vcfanno_config_-v1.17-.toml - outfile_check: grch37_vcfanno_config_-v1.17-.toml.md5 - outfile_check_method: md5sum - url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/annotation/ v1.18: file: grch37_vcfanno_config_-v1.18-.toml file_check: grch37_vcfanno_config_-v1.18-.toml.md5 @@ -1024,6 +1017,13 @@ reference_feature: outfile_check: grch37_vcfanno_config_-v1.18-.toml.md5 outfile_check_method: md5sum url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/annotation/ + v1.19: + file: grch37_vcfanno_config_-v1.19-.toml + file_check: grch37_vcfanno_config_-v1.19-.toml.md5 + outfile: grch37_vcfanno_config_-v1.19-.toml + outfile_check: grch37_vcfanno_config_-v1.19-.toml.md5 + outfile_check_method: md5sum + url_prefix: https://raw.githubusercontent.com/Clinical-Genomics/reference-files/master/rare-disease/annotation/ grch38: v0.2: file: grch38_vcfanno_config_-v0.2-.toml diff --git a/templates/mip_rd_dna_config.yaml b/templates/mip_rd_dna_config.yaml index 988a8d8ae..71ab1bb07 100755 --- a/templates/mip_rd_dna_config.yaml +++ b/templates/mip_rd_dna_config.yaml @@ -32,7 +32,7 @@ sv_svdb_query_db_files: # FORMAT: filename|OUT_FREQUENCY_INFO_KEY|OUT_ALLELE_COUNT_INFO_KEY|IN_FREQUENCY_INFO_KEY|IN_ALLELE_COUNT_INFO_KEY|USE_IN_FREQUENCY_FILTER grch37_clinvar_sv_pathogenic_-20221004-.bedpe: clinvar_pathogenic|Occ|Frq grch37_gnomad_reformated_-r2.1.1_sv-.vcf.gz: gnomad_sv|AF|AC|AF|AC|1 - grch37_loqusdb_sv_variants_export-20220905-.vcf: clinical_genomics_loqus|Frq|Obs|Frq|Obs|1 + grch37_loqusdb_sv_variants_export-20230214-.vcf: clinical_genomics_loqus|Frq|Obs|Frq|Obs|1 grch37_mip_sv_svdb_export_-2018-10-09-.vcf: clinical_genomics_mip|AF|OCC|FRQ|OCC|1 grch37_svdb_query_decipher_-v1.0.0-.vcf: decipher|AF|OCC|FRQ|OCC grch37_svdb_query_clingen_cgh_benign_-v1.0.0-.vcf: clingen_cgh_benign @@ -76,7 +76,7 @@ vep_custom_annotation: force_report_coordinates: 0 key: CLINVAR file_type: vcf - path: cluster_constant_path!/references/grch37_clinvar_reformated_-20220829-.vcf.gz + path: cluster_constant_path!/references/grch37_clinvar_reformated_-20230218-.vcf.gz vcf_fields: CLNSIG,CLNVID,CLNREVSTAT vep_directory_cache: cluster_constant_path!/references/ensembl-tools-data-104/cache/ vep_plugins_dir_path: cluster_constant_path!/references/ensembl-tools-data-104/cache/Plugins From bdd61c5cd27fcc3d01c70c1a9a919dbcac83761a Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 21 Feb 2023 09:45:35 +0100 Subject: [PATCH 17/29] fixing test files --- templates/mip_dragen_rd_dna_config.yaml | 2 +- templates/mip_rd_dna_panel_config.yaml | 2 +- templates/mip_rd_dna_vcf_rerun_config.yaml | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/templates/mip_dragen_rd_dna_config.yaml b/templates/mip_dragen_rd_dna_config.yaml index 32338a0b7..812a051a7 100644 --- a/templates/mip_dragen_rd_dna_config.yaml +++ b/templates/mip_dragen_rd_dna_config.yaml @@ -68,7 +68,7 @@ vep_custom_annotation: force_report_coordinates: 0 key: CLINVAR file_type: vcf - path: cluster_constant_path!/references/grch37_clinvar_reformated_-20220829-.vcf.gz + path: cluster_constant_path!/references/grch37_clinvar_reformated_-20230218-.vcf.gz vcf_fields: CLNSIG,CLNVID,CLNREVSTAT vep_directory_cache: cluster_constant_path!/references/ensembl-tools-data-104/cache/ vep_plugins_dir_path: cluster_constant_path!/references/ensembl-tools-data-104/cache/Plugins diff --git a/templates/mip_rd_dna_panel_config.yaml b/templates/mip_rd_dna_panel_config.yaml index 4c8e9bc72..7535930ae 100755 --- a/templates/mip_rd_dna_panel_config.yaml +++ b/templates/mip_rd_dna_panel_config.yaml @@ -49,7 +49,7 @@ vep_custom_annotation: force_report_coordinates: 0 key: CLINVAR file_type: vcf - path: cluster_constant_path!/references/grch37_clinvar_reformated_-20220829-.vcf.gz + path: cluster_constant_path!/references/grch37_clinvar_reformated_-20230218-.vcf.gz vcf_fields: CLNSIG,CLNVID,CLNREVSTAT vep_directory_cache: cluster_constant_path!/references/ensembl-tools-data-104/cache/ vep_plugins_dir_path: cluster_constant_path!/references/ensembl-tools-data-104/cache/Plugins diff --git a/templates/mip_rd_dna_vcf_rerun_config.yaml b/templates/mip_rd_dna_vcf_rerun_config.yaml index 600579059..2cdeb228b 100644 --- a/templates/mip_rd_dna_vcf_rerun_config.yaml +++ b/templates/mip_rd_dna_vcf_rerun_config.yaml @@ -28,7 +28,7 @@ sv_rank_model_file: svrank_model_-v1.9-.ini # FORMAT: filename|OUT_FREQUENCY_INFO_KEY|OUT_ALLELE_COUNT_INFO_KEY|IN_FREQUENCY_INFO_KEY|IN_ALLELE_COUNT_INFO_KEY|USE_IN_FREQUENCY_FILTER sv_svdb_query_db_files: grch37_gnomad_reformated_-r2.1.1_sv-.vcf.gz: gnomad_sv|AF|AC|AF|AC|1 - grch37_loqusdb_sv_variants_export-20220905-.vcf: clinical_genomics_loqus|Frq|Obs|Frq|Obs + grch37_loqusdb_sv_variants_export-20230214-.vcf: clinical_genomics_loqus|Frq|Obs|Frq|Obs grch37_mip_sv_svdb_export_-2018-10-09-.vcf: clinical_genomics_mip|AF|OCC|FRQ|OCC|1 grch37_svdb_query_decipher_-v1.0.0-.vcf: decipher|AF|OCC|FRQ|OCC grch37_svdb_query_clingen_cgh_benign_-v1.0.0-.vcf: clingen_cgh_benign @@ -70,7 +70,7 @@ vep_custom_annotation: force_report_coordinates: 0 key: CLINVAR file_type: vcf - path: cluster_constant_path!/references/grch37_clinvar_reformated_-20220829-.vcf.gz + path: cluster_constant_path!/references/grch37_clinvar_reformated_-20230218-.vcf.gz vcf_fields: CLNSIG,CLNVID,CLNREVSTAT vep_directory_cache: cluster_constant_path!/references/ensembl-tools-data-104/cache/ vep_plugins_dir_path: cluster_constant_path!/references/ensembl-tools-data-104/cache/Plugins From a5c5b3cc8dffa586c05b7e73b1f41c6677d41cfe Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 21 Feb 2023 16:24:11 +0100 Subject: [PATCH 18/29] updating hmtnote dump --- CHANGELOG.md | 1 + containers/hmtnote/Dockerfile | 6 +++--- templates/mip_install_config.yaml | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 8713b4e65..9388458fd 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -24,6 +24,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). clinvar: 20220829 -> 20230218 loqusdb snapshot: 20230208 -> 20230214 +hmtvar: oct2022 ## [11.1.1] diff --git a/containers/hmtnote/Dockerfile b/containers/hmtnote/Dockerfile index ebade96d7..1ac78820c 100644 --- a/containers/hmtnote/Dockerfile +++ b/containers/hmtnote/Dockerfile @@ -5,15 +5,15 @@ FROM clinicalgenomics/mip_base:2.1 ################## METADATA ###################### LABEL base-image="clinicalgenomics/mip_base:2.1" -LABEL version="1" +LABEL version="2" LABEL software="HmtNote" LABEL software.version="0.7.2" -LABEL extra.binaries="HmtNote" +LABEL extra.binaries="HmtNote, hmtvar_oct2022" LABEL maintainer="Clinical-Genomics/MIP" ## Conda env installation + clean up RUN conda install pip python=3.7 && \ - /opt/conda/bin/conda clean -tipsy + /opt/conda/bin/conda clean -ya # Install HmtNote RUN pip install --no-cache-dir hmtnote==0.7.2 && \ diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index cf132914d..86abf7cbe 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -105,7 +105,7 @@ container: hmtnote: executable: hmtnote: - uri: docker.io/clinicalgenomics/hmtnote:0.7.2 + uri: docker.io/clinicalgenomics/hmtnote:0.7.2-oct2022 htslib: executable: bcftools: From 22b7abd787dd3f7e79a1a25fae1800cc31b40121 Mon Sep 17 00:00:00 2001 From: Emil Bertilsson Date: Thu, 2 Mar 2023 13:38:35 +0100 Subject: [PATCH 19/29] Adds index path to Gens deliverables --- lib/MIP/Recipes/Analysis/Gens_generatedata.pm | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/MIP/Recipes/Analysis/Gens_generatedata.pm b/lib/MIP/Recipes/Analysis/Gens_generatedata.pm index 892718190..628578b63 100644 --- a/lib/MIP/Recipes/Analysis/Gens_generatedata.pm +++ b/lib/MIP/Recipes/Analysis/Gens_generatedata.pm @@ -253,6 +253,7 @@ sub analysis_gens_generatedata { format => q{bed}, id => $sample_id, path => $outfile_path{$file_tag}, + path_index => $outfile_path{$file_tag} . q{.tbi}, recipe_name => $recipe_name, sample_info_href => $sample_info_href, tag => $file_tag, From e001559619262c8eb593f73258b31824b21c4fab Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 21 Mar 2023 12:01:47 +0100 Subject: [PATCH 20/29] updating programs --- CHANGELOG.md | 13 +++++++++++-- containers/fastqc/Dockerfile | 10 ++++------ containers/gffcompare/Dockerfile | 19 ------------------- containers/htslib/Dockerfile | 6 +++--- lib/MIP/Recipes/Analysis/Star_aln.pm | 18 ++---------------- templates/mip_install_config.yaml | 26 +++++++++++++------------- 6 files changed, 33 insertions(+), 59 deletions(-) delete mode 100644 containers/gffcompare/Dockerfile diff --git a/CHANGELOG.md b/CHANGELOG.md index 21f1a63be..41ffa7205 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -13,12 +13,21 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Increased run time allocation for gatk_asereadcounter. - Increased the default required length for a trimmed rna read to be retained from 20 bp to 40 bp. Configurable via CLI or config. - Fixed a bug where gnomad SV version 2.0 instead of version 2.1 was used to annotate SVs +- One-pass instead of two-pass mapping with STAR-Fusion, as recommended for STAR-Fusion 1.12 ### Tools -- Tiddit 3.3.2 -> 3.4.0 +- Arriba 2.3.0 -> 2.4.0 +- DeepVariant 1.4.0 -> 1.5.0 +- FastQC: 0.11.9 -> 0.12.1 +- GATK: 4.2.6.1 -> 4.4.0.0 +- Gffcompare 0.11.2 -> 0.12.6 +- Htslib 1.15.1 -> 1.16 - MegaFusion 66a3a80 -> d3feacf - +- Picard 2.27.2 -> 2.27.5 +- STAR-Fusion 1.11.0 -> 1.12.0 +- SVDB: 2.7.0 -> 2.8.1 +- Tiddit 3.3.2 -> 3.4.0 ### Databases clinvar: 20220829 -> 20230218 diff --git a/containers/fastqc/Dockerfile b/containers/fastqc/Dockerfile index 04a801a2f..8c146a3a2 100644 --- a/containers/fastqc/Dockerfile +++ b/containers/fastqc/Dockerfile @@ -5,15 +5,13 @@ FROM clinicalgenomics/mip_base:2.1 ################## METADATA ###################### LABEL base_image="clinicalgenomics/mip_base:2.1" -LABEL version="2" +LABEL version="3" LABEL software="fastqc" -LABEL software.version="0.11.9" +LABEL software.version="0.12.1" LABEL extra.binaries="fastqc" LABEL maintainer="Clinical-Genomics/MIP" -RUN conda install fastqc=0.11.9=0 - -## Clean up after conda -RUN /opt/conda/bin/conda clean -tipsy +RUN conda install fastqc=0.12.1 && \ + /opt/conda/bin/conda clean -ya WORKDIR /data/ diff --git a/containers/gffcompare/Dockerfile b/containers/gffcompare/Dockerfile deleted file mode 100644 index 617cfdc74..000000000 --- a/containers/gffcompare/Dockerfile +++ /dev/null @@ -1,19 +0,0 @@ -################## BASE IMAGE ###################### - -FROM clinicalgenomics/mip_base:2.1 - -################## METADATA ###################### - -LABEL base_image="clinicalgenomics/mip_base:2.1" -LABEL version="1" -LABEL software="gffcompare" -LABEL software.version="0.11.2" -LABEL extra.binaries="gffcompare" -LABEL maintainer="Clinical-Genomics/MIP" - -RUN conda install --yes gffcompare=0.11.2 - -## Clean up after conda -RUN /opt/conda/bin/conda clean -ay - -WORKDIR /data/ diff --git a/containers/htslib/Dockerfile b/containers/htslib/Dockerfile index 870a76eae..e46b9254f 100644 --- a/containers/htslib/Dockerfile +++ b/containers/htslib/Dockerfile @@ -5,13 +5,13 @@ FROM clinicalgenomics/mip_base:2.1 ################## METADATA ###################### LABEL base-image="clinicalgenomics/mip_base:2.1" -LABEL version="7" +LABEL version="8" LABEL software="htslib" -LABEL software.version="1.15.1" +LABEL software.version="1.16" LABEL extra.binaries="bcftools, bgzip, samtools, tabix" LABEL maintainer="Clinical-Genomics/MIP" -RUN conda install bcftools=1.15.1 htslib=1.15.1 samtools=1.15.1 && \ +RUN conda install bcftools=1.16 htslib=1.16 samtools=1.16.1 && \ /opt/conda/bin/conda clean -ya WORKDIR /data/ diff --git a/lib/MIP/Recipes/Analysis/Star_aln.pm b/lib/MIP/Recipes/Analysis/Star_aln.pm index 41655cb10..e693ed838 100644 --- a/lib/MIP/Recipes/Analysis/Star_aln.pm +++ b/lib/MIP/Recipes/Analysis/Star_aln.pm @@ -1037,8 +1037,9 @@ sub analysis_star_fusion_aln { outfile_name_prefix => $outfile_path_prefix . $DOT, pe_overlap_mmp => $PE_OVERLAP_MMP, pe_overlap_nbases_min => $PE_OVERLAP_NBASES_MIN, + quant_mode => q{GeneCounts}, thread_number => $recipe{core_number}, - two_pass_mode => q{Basic}, + two_pass_mode => q{None}, }, ); say {$filehandle} $NEWLINE; @@ -1053,21 +1054,6 @@ sub analysis_star_fusion_aln { ); say {$filehandle} $NEWLINE; - ## Remove intermediary files - FILE_TAG: - foreach my $file_tag (qw{ _STARgenome _STARpass1 }) { - - gnu_rm( - { - filehandle => $filehandle, - force => 1, - infile_path => $outfile_path_prefix . $DOT . $file_tag, - recursive => 1, - } - ); - print {$filehandle} $NEWLINE; - } - ## Close filehandle close $filehandle or $log->logcroak(q{Could not close filehandle}); diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index 86abf7cbe..7d1c624b3 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -2,9 +2,9 @@ container: arriba: executable: - arriba: /arriba_v2.3.0/arriba - draw_fusions.R: /arriba_v2.3.0/draw_fusions.R - uri: docker.io/uhrigs/arriba:2.3.0 + arriba: /arriba_v2.4.0/arriba + draw_fusions.R: /arriba_v2.4.0/draw_fusions.R + uri: docker.io/uhrigs/arriba:2.4.0 bedtools: executable: bedtools: @@ -60,12 +60,12 @@ container: call_variants: /opt/deepvariant/bin/call_variants postprocess_variants: /opt/deepvariant/bin/postprocess_variants gpu_support: 0 - uri: docker.io/google/deepvariant:1.4.0 + uri: docker.io/google/deepvariant:1.5.0 deeptrio: executable: run_deeptrio: /opt/deepvariant/bin/deeptrio/run_deeptrio gpu_support: 0 - uri: docker.io/google/deepvariant:deeptrio-1.4.0 + uri: docker.io/google/deepvariant:deeptrio-1.5.0 delly: executable: delly: @@ -77,7 +77,7 @@ container: fastqc: executable: fastqc: - uri: docker.io/clinicalgenomics/fastqc:0.11.9 + uri: docker.io/clinicalgenomics/fastqc:0.12.1 gatk: executable: gatk3: "no_executable_in_image" @@ -85,7 +85,7 @@ container: gatk4: executable: gatk: - uri: docker.io/broadinstitute/gatk:4.2.6.1 + uri: docker.io/broadinstitute/gatk:4.4.0.0 genmod: executable: genmod: @@ -97,7 +97,7 @@ container: gffcompare: executable: gffcompare: - uri: docker.io/clinicalgenomics/gffcompare:0.11.2 + uri: quay.io/biocontainers/gffcompare:0.12.6--h9f5acd7_0 glnexus: executable: glnexus_cli: @@ -112,7 +112,7 @@ container: bgzip: samtools: tabix: - uri: docker.io/clinicalgenomics/htslib:1.15.1 + uri: docker.io/clinicalgenomics/htslib:1.16 manta: executable: configManta.py: @@ -129,7 +129,7 @@ container: multiqc: executable: multiqc: - uri: docker.io/ewels/multiqc:v1.12 + uri: docker.io/ewels/multiqc:v1.14 perl: executable: perl: @@ -145,7 +145,7 @@ container: picard: executable: picard: "no_executable_in_image" - uri: docker.io/broadinstitute/picard:2.27.2 + uri: docker.io/broadinstitute/picard:2.27.5 plink: executable: plink2: @@ -201,7 +201,7 @@ container: remove_long_intron_readthru_transcripts.pl: /usr/local/src/STAR-Fusion/ctat-genome-lib-builder/util/remove_long_intron_readthru_transcripts.pl restrict_genome_to_chr_entries.pl: /usr/local/src/STAR-Fusion/ctat-genome-lib-builder/util/restrict_genome_to_chr_entries.pl STAR-Fusion: /usr/local/src/STAR-Fusion/STAR-Fusion - uri: docker.io/trinityctat/starfusion:1.11.0 + uri: docker.io/trinityctat/starfusion:1.12.0 stranger: executable: stranger: @@ -213,7 +213,7 @@ container: svdb: executable: svdb: - uri: quay.io/biocontainers/svdb:2.7.0--py39h5371cbf_0 + uri: quay.io/biocontainers/svdb:2.8.1--py310h79ef01b_0 telomerecat: executable: telomerecat: From 9bc1080101677bd6fb89059819299c1efddbb8af Mon Sep 17 00:00:00 2001 From: jemten Date: Mon, 8 May 2023 16:40:20 +0200 Subject: [PATCH 21/29] updates svdb and tiddit to latest versions --- CHANGELOG.md | 5 +++-- templates/mip_install_config.yaml | 4 ++-- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index e64fb4623..b71653912 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). ## [Develop] +- Update Tiddit to improve SV positioning - Increased memory allocation for salmon and picardtools_mergersamfiles (RNA) - Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update - New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf. @@ -25,8 +26,8 @@ This project adheres to [Semantic Versioning](http://semver.org/). - MegaFusion 66a3a80 -> d3feacf - Picard 2.27.2 -> 2.27.5 - STAR-Fusion 1.11.0 -> 1.12.0 -- SVDB: 2.7.0 -> 2.8.1 -- Tiddit 3.3.2 -> 3.4.0 +- SVDB: 2.7.0 -> 2.8.2 +- Tiddit 3.3.2 -> 3.6.0 ### Databases diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index c88a245a7..956af52b0 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -217,7 +217,7 @@ container: svdb: executable: svdb: - uri: quay.io/biocontainers/svdb:2.8.1--py310h79ef01b_0 + uri: docker.io/clinicalgenomics/svdb:2.8.2 telomerecat: executable: telomerecat: @@ -225,7 +225,7 @@ container: tiddit: executable: tiddit: - uri: quay.io/biocontainers/tiddit:3.4.0--py310hc2b7f4b_0 + uri: quay.io/biocontainers/tiddit:3.6.0--py310hc2b7f4b_0 trim-galore: executable: trim_galore: From 663ee28fa02251853aa2d2bf2c3c11d4e2257c0f Mon Sep 17 00:00:00 2001 From: jemten Date: Mon, 8 May 2023 17:19:05 +0200 Subject: [PATCH 22/29] modifying sv overlap requirements --- CHANGELOG.md | 3 ++- definitions/rd_dna_parameters.yaml | 8 +++++++- documentation/Setup.md | 4 ++-- lib/MIP/Cli/Mip/Analyse/Rd_dna.pm | 10 +++++++++- lib/MIP/Recipes/Analysis/Sv_combinevariantcallsets.pm | 11 +++-------- 5 files changed, 23 insertions(+), 13 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index b71653912..677e163ab 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,9 +5,10 @@ This project adheres to [Semantic Versioning](http://semver.org/). ## [Develop] +- Set overlap requirement for merging two SVs to 0.6 +- Set overlap requirement for SV annotation to 0.6, up from 0.5 - Update Tiddit to improve SV positioning - Increased memory allocation for salmon and picardtools_mergersamfiles (RNA) -- Changes sv annotation overlap back to 0.8 (from 0.5) with the new tiddit update - New version of MegaFusion. A bug in the previous version prevented SVDB from writing the format and sample field in the vcf. - Remove the RSeQC read duplication analysis as it often fails. - Increased run time allocation for gatk_asereadcounter. diff --git a/definitions/rd_dna_parameters.yaml b/definitions/rd_dna_parameters.yaml index 6284ac13b..9308edbb5 100755 --- a/definitions/rd_dna_parameters.yaml +++ b/definitions/rd_dna_parameters.yaml @@ -959,6 +959,12 @@ sv_svdb_merge_prioritize: data_type: SCALAR default: tiddit,cnvnator,manta type: recipe_argument +sv_svdb_merge_overlap: + associated_recipe: + - sv_combinevariantcallsets + data_type: SCALAR + default: 0.8 + type: recipe_argument sv_decompose: associated_recipe: - sv_combinevariantcallsets @@ -1015,7 +1021,7 @@ sv_svdb_query_overlap: associated_recipe: - sv_annotate data_type: SCALAR - default: 0.8 + default: 0.6 type: recipe_argument sv_vcfanno_config: associated_recipe: diff --git a/documentation/Setup.md b/documentation/Setup.md index a1a43c20c..edb0e7ac9 100644 --- a/documentation/Setup.md +++ b/documentation/Setup.md @@ -76,9 +76,9 @@ You can speed up, for instance, the Readonly module by also installing the compa - [STAR] (version: 2.7.8a) - [Stranger] (version: 0.8.0) - [StringTie] (version: 2.1.3b) -- [Svdb] (version: 2.4.0) +- [Svdb] (version: 2.8.2) - [Telomerecat] (version: 3.4.0) -- [Tiddit] (version: 3.4.0) +- [Tiddit] (version: 3.6.0) - [Upd] (version: 0.1.1) - [Varg] (version: 1.2.0) - [Vcf2cytosure] (version: 0.5.1) diff --git a/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm b/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm index 88d3cfafd..ae5f3fe42 100644 --- a/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm +++ b/lib/MIP/Cli/Mip/Analyse/Rd_dna.pm @@ -827,6 +827,14 @@ q{Default: grch37_dbsnp_-138-.vcf, grch37_1000g_indels_-phase1-.vcf, grch37_mill ) ); + option( + q{sv_svdb_merge_overlap} => ( + documentation => q{Required overlap to merge two structural variants}, + is => q{rw}, + isa => Num, + ) + ); + option( q{sv_svdb_merge_prioritize} => ( documentation => q{Prioritization order of structural variant callers}, @@ -897,7 +905,7 @@ q{Default: grch37_dbsnp_-138-.vcf, grch37_1000g_indels_-phase1-.vcf, grch37_mill q{sv_svdb_query_overlap} => ( documentation => q{Database file(s) for annotation}, is => q{rw}, - isa => Str, + isa => Num, ) ); diff --git a/lib/MIP/Recipes/Analysis/Sv_combinevariantcallsets.pm b/lib/MIP/Recipes/Analysis/Sv_combinevariantcallsets.pm index 4fd17f8ee..7d6d88a43 100644 --- a/lib/MIP/Recipes/Analysis/Sv_combinevariantcallsets.pm +++ b/lib/MIP/Recipes/Analysis/Sv_combinevariantcallsets.pm @@ -280,8 +280,9 @@ sub analysis_sv_combinevariantcallsets { { filehandle => $filehandle, infile_paths_ref => \@svdb_infile_paths, - priority => $active_parameter_href->{sv_svdb_merge_prioritize}, + overlap => $active_parameter_href->{sv_svdb_merge_overlap}, pass_only => 1, + priority => $active_parameter_href->{sv_svdb_merge_prioritize}, same_order => 1, stdoutfile_path => $outfile_path, } @@ -425,13 +426,7 @@ sub _add_to_parallel_chain { check( $tmpl, $arg_href, 1 ) or croak q{Could not parse arguments!}; ## If element is not part of array - if ( - not any { - $_ eq $structural_variant_caller_chain - } - @{$parallel_chains_ref} - ) - { + if ( not any { $_ eq $structural_variant_caller_chain } @{$parallel_chains_ref} ) { push @{$parallel_chains_ref}, $structural_variant_caller_chain; } return; From a7bb25c197707c723d6dd44aed1bb55870244157 Mon Sep 17 00:00:00 2001 From: jemten Date: Mon, 8 May 2023 17:29:04 +0200 Subject: [PATCH 23/29] updating mip version tag to reflect develop --- lib/MIP/Constants.pm | 2 +- templates/mip_install_config.yaml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm index 8b425d3d9..d6434afa0 100644 --- a/lib/MIP/Constants.pm +++ b/lib/MIP/Constants.pm @@ -82,7 +82,7 @@ Readonly our %ANALYSIS => ( ); ## Set MIP version -Readonly our $MIP_VERSION => q{11.2.1}; +Readonly our $MIP_VERSION => q{12.0.0-develop}; ## Cli Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160; diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index 956af52b0..12607db94 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -125,7 +125,7 @@ container: mip: executable: mip: - uri: docker.io/clinicalgenomics/mip:v11.2.1 + uri: docker.io/clinicalgenomics/mip:develop multiqc: executable: multiqc: From 5329ed0c01bda8eb43ceb73afaff8ea732f4ba5f Mon Sep 17 00:00:00 2001 From: jemten Date: Fri, 12 May 2023 09:02:22 +0200 Subject: [PATCH 24/29] fixing changelog --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index c6c44ddaa..efe4af122 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,7 +5,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). ## [Develop] -- Set overlap requirement for merging two SVs to 0.6 +- Set overlap requirement for merging two SVs to 0.8, down from the 0.95 default - Set overlap requirement for SV annotation to 0.6, up from 0.5 - Update Tiddit to improve SV positioning - Increased memory allocation for salmon and picardtools_mergersamfiles (RNA) From c1ef637af567c37f322a96f492dc4cc3790c8a88 Mon Sep 17 00:00:00 2001 From: jemten Date: Fri, 12 May 2023 10:19:22 +0200 Subject: [PATCH 25/29] increasing max retroseq run time to 15 h --- CHANGELOG.md | 1 + definitions/rd_dna_parameters.yaml | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index efe4af122..79b12a9de 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -15,6 +15,7 @@ This project adheres to [Semantic Versioning](http://semver.org/). - Increased the default required length for a trimmed rna read to be retained from 20 bp to 40 bp. Configurable via CLI or config. - Fixed a bug where gnomad SV version 2.0 instead of version 2.1 was used to annotate SVs - One-pass instead of two-pass mapping with STAR-Fusion, as recommended for STAR-Fusion 1.12 +- Bump max run time for retroseq to 15 hours. ### Tools diff --git a/definitions/rd_dna_parameters.yaml b/definitions/rd_dna_parameters.yaml index 9308edbb5..8dcd61723 100755 --- a/definitions/rd_dna_parameters.yaml +++ b/definitions/rd_dna_parameters.yaml @@ -377,7 +377,7 @@ recipe_time: prepareforvariantannotationblock: 5 qccollect_ar: 1 rankvariant: 10 - retroseq: 5 + retroseq: 15 rhocall_ar: 5 rhocall_viz: 1 rtg_vcfeval: 1 From 6bc34e09a3c8e4afb1e77e2749ad4a1e3229430b Mon Sep 17 00:00:00 2001 From: jemten Date: Fri, 12 May 2023 15:02:34 +0200 Subject: [PATCH 26/29] uppdates clinvar references --- CHANGELOG.md | 4 +-- .../mip_download_rd_dna_config_-1.0-.yaml | 30 +++++++++---------- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 79b12a9de..8a7b5c892 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -33,8 +33,8 @@ This project adheres to [Semantic Versioning](http://semver.org/). ### Databases -clinvar: 20220829 -> 20230218 -loqusdb snapshot: 20230208 -> 20230214 +clinvar: 20220829 -> 20230508 +loqusdb snapshot: 20230208 -> 20230512 hmtvar: oct2022 ## [11.2.2] diff --git a/templates/mip_download_rd_dna_config_-1.0-.yaml b/templates/mip_download_rd_dna_config_-1.0-.yaml index 5982bdc46..9adeef3d6 100644 --- a/templates/mip_download_rd_dna_config_-1.0-.yaml +++ b/templates/mip_download_rd_dna_config_-1.0-.yaml @@ -27,7 +27,7 @@ reference: - v1.0 clinvar: - 20220829 - - 20230218 + - 20230508 dbnsfp: - 3.5a - 4.1a @@ -332,13 +332,13 @@ reference_feature: outfile_index: grch37_clinvar_-20220829-.vcf.gz.tbi outfile_check_method: md5sum url_prefix: https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh37/weekly/ - 20230218: - file: clinvar_20230218.vcf.gz - file_check: clinvar_20230218.vcf.gz.md5 - file_index: clinvar_20230218.vcf.gz.tbi - outfile: grch37_clinvar_-20230218-.vcf.gz - outfile_check: grch37_clinvar_-20230218-.vcf.gz.md5 - outfile_index: grch37_clinvar_-20230218-.vcf.gz.tbi + 20230508: + file: clinvar_20230508.vcf.gz + file_check: clinvar_20230508.vcf.gz.md5 + file_index: clinvar_20230508.vcf.gz.tbi + outfile: grch37_clinvar_-20230508-.vcf.gz + outfile_check: grch37_clinvar_-20230508-.vcf.gz.md5 + outfile_index: grch37_clinvar_-20230508-.vcf.gz.tbi outfile_check_method: md5sum url_prefix: ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh37/weekly/ grch38: @@ -351,13 +351,13 @@ reference_feature: outfile_index: grch38_clinvar_-20220829-.vcf.gz.tbi outfile_check_method: md5sum url_prefix: https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/weekly/ - 20230218: - file: clinvar_20230218.vcf.gz - file_check: clinvar_20230218.vcf.gz.md5 - file_index: clinvar_20230218.vcf.gz.tbi - outfile: grch38_clinvar_-20230218-.vcf.gz - outfile_check: grch38_clinvar_-20230218-.vcf.gz.md5 - outfile_index: grch38_clinvar_-20230218-.vcf.gz.tbi + 20230508: + file: clinvar_20230508.vcf.gz + file_check: clinvar_20230508.vcf.gz.md5 + file_index: clinvar_20230508.vcf.gz.tbi + outfile: grch38_clinvar_-20230508-.vcf.gz + outfile_check: grch38_clinvar_-20230508-.vcf.gz.md5 + outfile_index: grch38_clinvar_-20230508-.vcf.gz.tbi outfile_check_method: md5sum url_prefix: https://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/weekly/ dbnsfp: From c77c281a3eed9ce03e88f62ef49e34d58157341b Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 16 May 2023 15:58:51 +0200 Subject: [PATCH 27/29] updating version --- CHANGELOG.md | 2 +- lib/MIP/Constants.pm | 2 +- templates/mip_install_config.yaml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 8a7b5c892..6ec1d88ef 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/). -## [Develop] +## [12.0.0] - Set overlap requirement for merging two SVs to 0.8, down from the 0.95 default - Set overlap requirement for SV annotation to 0.6, up from 0.5 diff --git a/lib/MIP/Constants.pm b/lib/MIP/Constants.pm index d6434afa0..9052437c5 100644 --- a/lib/MIP/Constants.pm +++ b/lib/MIP/Constants.pm @@ -82,7 +82,7 @@ Readonly our %ANALYSIS => ( ); ## Set MIP version -Readonly our $MIP_VERSION => q{12.0.0-develop}; +Readonly our $MIP_VERSION => q{12.0.0}; ## Cli Readonly our $MOOSEX_APP_SCEEN_WIDTH => 160; diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index 23ccd8918..3881b1187 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -125,7 +125,7 @@ container: mip: executable: mip: - uri: docker.io/clinicalgenomics/mip:develop + uri: docker.io/clinicalgenomics/mip:12.0.0 multiqc: executable: multiqc: From 6bc663a934d862a963a67a83a3866bac5f865419 Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 16 May 2023 16:01:46 +0200 Subject: [PATCH 28/29] adding missing v in version --- templates/mip_install_config.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/templates/mip_install_config.yaml b/templates/mip_install_config.yaml index 3881b1187..26515fba8 100644 --- a/templates/mip_install_config.yaml +++ b/templates/mip_install_config.yaml @@ -125,7 +125,7 @@ container: mip: executable: mip: - uri: docker.io/clinicalgenomics/mip:12.0.0 + uri: docker.io/clinicalgenomics/mip:v12.0.0 multiqc: executable: multiqc: From 2b958acc6fa1b638942ab05f30b917618e55db3a Mon Sep 17 00:00:00 2001 From: jemten Date: Tue, 27 Jun 2023 13:31:37 +0200 Subject: [PATCH 29/29] add vcfanno config to download list --- templates/mip_download_rd_dna_config_-1.0-.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/templates/mip_download_rd_dna_config_-1.0-.yaml b/templates/mip_download_rd_dna_config_-1.0-.yaml index 9adeef3d6..394a70101 100644 --- a/templates/mip_download_rd_dna_config_-1.0-.yaml +++ b/templates/mip_download_rd_dna_config_-1.0-.yaml @@ -131,8 +131,8 @@ reference: - 200520 vcfanno_config: - v0.2 - - v1.17 - v1.18 + - v1.19 vcfanno_functions: - v1.0 reference_feature: