From 98204dae7373191efd4259e91e4054b85a70ee61 Mon Sep 17 00:00:00 2001 From: Manuel Holtgrewe Date: Thu, 4 Jan 2024 15:40:34 +0100 Subject: [PATCH] wip --- download_urls.yml | 4 ++-- environment.yml | 2 +- .../GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz | 0 excerpt-data/4c4ffa6ddc180f40/url.txt | 3 +++ .../GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt | 0 excerpt-data/4efb53cbe56f8290/url.txt | 3 +++ excerpt-data/95e8d788836873e9/url.txt | 3 --- excerpt-data/d0a5951ccb4cd824/url.txt | 3 --- rules/output/annonars/genes.smk | 2 ++ rules/work/genes/gtex.smk | 4 ++-- 10 files changed, 13 insertions(+), 11 deletions(-) rename excerpt-data/{95e8d788836873e9 => 4c4ffa6ddc180f40}/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz (100%) create mode 100644 excerpt-data/4c4ffa6ddc180f40/url.txt rename excerpt-data/{d0a5951ccb4cd824 => 4efb53cbe56f8290}/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt (100%) create mode 100644 excerpt-data/4efb53cbe56f8290/url.txt delete mode 100644 excerpt-data/95e8d788836873e9/url.txt delete mode 100644 excerpt-data/d0a5951ccb4cd824/url.txt diff --git a/download_urls.yml b/download_urls.yml index e7a9609..a4f0af8 100644 --- a/download_urls.yml +++ b/download_urls.yml @@ -91,12 +91,12 @@ - url: ftp://ftp.clinicalgenome.org/ClinGen_gene_curation_list_GRCh37.tsv - url: ftp://ftp.clinicalgenome.org/ClinGen_gene_curation_list_GRCh38.tsv -- url: https://storage.cloud.google.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt +- url: https://storage.googleapis.com/adult-gtex/annotations/v8/metadata-files/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt excerpt_strategy: strategy: no-excerpt count: null -- url: https://storage.cloud.google.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz +- url: https://storage.googleapis.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz excerpt_strategy: strategy: manual count: null diff --git a/environment.yml b/environment.yml index caf11e8..1f42695 100644 --- a/environment.yml +++ b/environment.yml @@ -41,7 +41,7 @@ dependencies: # Parallel (de)compression. - pigz # Varfish related - - annonars =0.32.0 + - annonars =0.33.0 - viguno =0.2.0 - mehari =0.21.1 - varfish-server-worker =0.10.2 diff --git a/excerpt-data/95e8d788836873e9/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz b/excerpt-data/4c4ffa6ddc180f40/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz similarity index 100% rename from excerpt-data/95e8d788836873e9/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz rename to excerpt-data/4c4ffa6ddc180f40/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz diff --git a/excerpt-data/4c4ffa6ddc180f40/url.txt b/excerpt-data/4c4ffa6ddc180f40/url.txt new file mode 100644 index 0000000..f50b3d7 --- /dev/null +++ b/excerpt-data/4c4ffa6ddc180f40/url.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e96d926c2e9db720d9c852898dadae9e212ee31f5f201ef94a5201ba7f2e0ed +size 120 diff --git a/excerpt-data/d0a5951ccb4cd824/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt b/excerpt-data/4efb53cbe56f8290/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt similarity index 100% rename from excerpt-data/d0a5951ccb4cd824/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt rename to excerpt-data/4efb53cbe56f8290/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt diff --git a/excerpt-data/4efb53cbe56f8290/url.txt b/excerpt-data/4efb53cbe56f8290/url.txt new file mode 100644 index 0000000..adc73c6 --- /dev/null +++ b/excerpt-data/4efb53cbe56f8290/url.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff230dd9fe588feac8473e0c525a99b5a8f4629309b2899a6c5dd64b69f1102c +size 124 diff --git a/excerpt-data/95e8d788836873e9/url.txt b/excerpt-data/95e8d788836873e9/url.txt deleted file mode 100644 index 2bdc79c..0000000 --- a/excerpt-data/95e8d788836873e9/url.txt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3c0be28ae237143a1b1143b6e129be9e652346c01c4c7f9b924ba0857c247732 -size 122 diff --git a/excerpt-data/d0a5951ccb4cd824/url.txt b/excerpt-data/d0a5951ccb4cd824/url.txt deleted file mode 100644 index 90f8837..0000000 --- a/excerpt-data/d0a5951ccb4cd824/url.txt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4d9cc185d363d4d24c084b1e78bbc4c6e21cd06c1147a0b14e1405cf5ef3ffce -size 116 diff --git a/rules/output/annonars/genes.smk b/rules/output/annonars/genes.smk index b0833c3..b461a34 100644 --- a/rules/output/annonars/genes.smk +++ b/rules/output/annonars/genes.smk @@ -12,6 +12,7 @@ rule output_annonars_genes: # -- build annonars genes RocksDB file ncbi="work/genes/entrez/{date}/gene_info.jsonl", omim="work/genes/omim/{v_hpo}+{date}/omim_diseases.tsv", orpha="work/genes/orphapacket/{v_orpha}+{date}/orpha_diseases.tsv", + panelapp="work/download/genes/panelapp/{date}/panelapp.jsonl", rcnv="work/genes/rcnv/2022/rcnv_collins_2022.tsv", shet="work/genes/shet/2019/shet_weghorn_2019.tsv", gtex="work/genes/annonars/gtex_v8/genes_tpm.jsonl.gz", @@ -44,6 +45,7 @@ rule output_annonars_genes: # -- build annonars genes RocksDB file --path-in-hgnc {input.hgnc} \ --path-in-omim {input.omim} \ --path-in-orpha {input.orpha} \ + --path-in-panelapp {input.panelapp} \ --path-in-ncbi {input.ncbi} \ --path-in-rcnv {input.rcnv} \ --path-in-shet {input.shet} \ diff --git a/rules/work/genes/gtex.smk b/rules/work/genes/gtex.smk index c33792e..9457f1a 100644 --- a/rules/work/genes/gtex.smk +++ b/rules/work/genes/gtex.smk @@ -34,11 +34,11 @@ rule genes_gtex_v8_download: # -- download GTex v8 gene expression data r""" wget --no-check-certificate \ -O {output.attributes} \ - https://storage.cloud.google.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt + https://storage.googleapis.com/adult-gtex/annotations/v8/metadata-files/GTEx_Analysis_v8_Annotations_SampleAttributesDS.txt wget --no-check-certificate \ -O {output.genes_tpm} \ - https://storage.cloud.google.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz + https://storage.googleapis.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_tpm.gct.gz md5sum {output.attributes} > {output.attributes_md5} md5sum {output.genes_tpm} > {output.genes_tpm_md5}