Skip to content

Commit

Permalink
feat: import of gnomAD SV data into RocksDB (#66)
Browse files Browse the repository at this point in the history
  • Loading branch information
holtgrewe authored Nov 22, 2023
1 parent 0797f2d commit 3fd72dd
Show file tree
Hide file tree
Showing 107 changed files with 629 additions and 17 deletions.
6 changes: 6 additions & 0 deletions Snakefile
Original file line number Diff line number Diff line change
Expand Up @@ -161,6 +161,10 @@ rule all:
f"output/full/annonars/gnomad-genomes-grch38-{DV.gnomad_v3}+{PV.annonars}/rocksdb/IDENTITY",
f"output/full/annonars/helixmtdb-grch37-{DV.helixmtdb}+{PV.annonars}/rocksdb/IDENTITY",
f"output/full/annonars/helixmtdb-grch38-{DV.helixmtdb}+{PV.annonars}/rocksdb/IDENTITY",
f"output/full/annonars/gnomad-sv-exomes-grch37-{DV.exac_cnv}+{PV.annonars}/rocksdb/IDENTITY",
f"output/full/annonars/gnomad-sv-exomes-grch38-{DV.gnomad_cnv4}+{PV.annonars}/rocksdb/IDENTITY",
f"output/full/annonars/gnomad-sv-genomes-grch37-{DV.gnomad_sv}+{PV.annonars}/rocksdb/IDENTITY",
f"output/full/annonars/gnomad-sv-genomes-grch38-{DV.gnomad_sv4}+{PV.annonars}/rocksdb/IDENTITY",
# ----- conservation
f"output/full/annonars/cons-grch37-{DV.ucsc_cons_37}+{PV.annonars}/rocksdb/IDENTITY",
f"output/full/annonars/cons-grch38-{DV.ucsc_cons_38}+{PV.annonars}/rocksdb/IDENTITY",
Expand Down Expand Up @@ -364,6 +368,7 @@ include: "rules/work/annos/strucvars/exac.smk"
include: "rules/work/annos/strucvars/g1k.smk"
include: "rules/work/annos/strucvars/gnomad.smk"
include: "rules/work/annos/strucvars/clinvar.smk"
include: "rules/work/annos/strucvars/gnomad_sv4.smk"
# -- output directory ---------------------------------------------------------------------------
# ---- mehari
include: "rules/output/mehari/freqs.smk"
Expand All @@ -378,6 +383,7 @@ include: "rules/output/annonars/dbsnp.smk"
include: "rules/output/annonars/gnomad_exomes.smk"
include: "rules/output/annonars/gnomad_genomes.smk"
include: "rules/output/annonars/gnomad_mtdna.smk"
include: "rules/output/annonars/gnomad_sv.smk"
include: "rules/output/annonars/helix.smk"
include: "rules/output/annonars/genes.smk"
# ---- worker
Expand Down
45 changes: 44 additions & 1 deletion download_urls.yml
Original file line number Diff line number Diff line change
@@ -1,3 +1,47 @@
- url: https://storage.googleapis.com/gcp-public-data--gnomad/legacy/exac_browser/ExAC.r1.sites.vep.vcf.gz
excerpt_strategy:
strategy: gz-head
count: 225
- url: https://storage.googleapis.com/gcp-public-data--gnomad/papers/2019-sv/gnomad_v2.1_sv.sites.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/papers/2019-sv/gnomad_v2.1_sv.controls_only.sites.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/papers/2019-sv/gnomad_v2.1_sv.nonneuro.sites.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/exome_cnv/gnomad.v4.0.cnv.all.vcf.gz
excerpt_strategy:
strategy: gz-head
count: 160
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/exome_cnv/gnomad.v4.0.cnv.non_neuro.vcf.gz
excerpt_strategy:
strategy: gz-head
count: 160
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/exome_cnv/gnomad.v4.0.cnv.non_neuro_controls.vcf.gz
excerpt_strategy:
strategy: gz-head
count: 160
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr1.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr2.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr3.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr4.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr5.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr6.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr7.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr8.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr9.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr10.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr11.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr12.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr13.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr14.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr15.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr16.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr17.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr18.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr19.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr20.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr21.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chr22.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chrX.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/release/4.0/genome_sv/gnomad.v4.0.sv.chrY.vcf.gz

- url: https://www.deciphergenomics.org/files/downloads/HI_Predictions_Version3.bed.gz

- url: ftp://ftp.clinicalgenome.org/ClinGen_region_curation_list_GRCh37.tsv
Expand Down Expand Up @@ -204,7 +248,6 @@
- url: http://dgv.tcag.ca/dgv/docs/DGV.GS.hg38.gff3
- url: ftp://ftp.broadinstitute.org/pub/ExAC_release/release0.3.1/cnv/exac-final.autosome-1pct-sq60-qc-prot-coding.cnv.bed
- url: https://ftp-trace.ncbi.nih.gov/1000genomes/ftp/phase3/integrated_sv_map/ALL.wgs.integrated_sv_map_v2.20130502.svs.genotypes.vcf.gz
- url: https://storage.googleapis.com/gcp-public-data--gnomad/papers/2019-sv/gnomad_v2.1_sv.sites.vcf.gz

- url: https://gnomad-public-us-east-1.s3.amazonaws.com/release/2.1.1/vcf/genomes/gnomad.genomes.r2.1.1.sites.1.vcf.bgz
- url: https://gnomad-public-us-east-1.s3.amazonaws.com/release/2.1.1/vcf/genomes/gnomad.genomes.r2.1.1.sites.2.vcf.bgz
Expand Down
3 changes: 3 additions & 0 deletions excerpt-data/05e93e6f1f5d60e6/gnomad.v4.0.sv.chr4.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/05e93e6f1f5d60e6/gnomad.v4.0.sv.chr4.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/05e93e6f1f5d60e6/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/0be9b2561c9397f2/gnomad.v4.0.sv.chr15.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/0be9b2561c9397f2/gnomad.v4.0.sv.chr15.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/0be9b2561c9397f2/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/13d4b1406e769b80/gnomad.v4.0.sv.chr3.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/13d4b1406e769b80/gnomad.v4.0.sv.chr3.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/13d4b1406e769b80/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/182806147755e799/gnomad.v4.0.sv.chr5.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/182806147755e799/gnomad.v4.0.sv.chr5.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/182806147755e799/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/19a12d845df10514/gnomad.v4.0.sv.chr18.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/19a12d845df10514/gnomad.v4.0.sv.chr18.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/19a12d845df10514/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/2245e9d640b3f206/gnomad.v4.0.sv.chrX.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/2245e9d640b3f206/gnomad.v4.0.sv.chrX.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/2245e9d640b3f206/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/2a2a71f92360a9d6/ExAC.r1.sites.vep.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/2a2a71f92360a9d6/url.txt
Git LFS file not shown
Git LFS file not shown
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/32e2612bdb4f2586/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/3390d9ca9ce97bac/gnomad.v4.0.sv.chr2.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/3390d9ca9ce97bac/gnomad.v4.0.sv.chr2.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/3390d9ca9ce97bac/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/3b19a5df654e6b4f/gnomad.v4.0.sv.chrY.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/3b19a5df654e6b4f/gnomad.v4.0.sv.chrY.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/3b19a5df654e6b4f/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/418b9faa168c4d22/gnomad.v4.0.cnv.all.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/418b9faa168c4d22/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/41e368687b2c69e4/gnomad.v4.0.sv.chr7.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/41e368687b2c69e4/gnomad.v4.0.sv.chr7.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/41e368687b2c69e4/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/555fd2fa82d1b73d/gnomad.v4.0.sv.chr11.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/555fd2fa82d1b73d/gnomad.v4.0.sv.chr11.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/555fd2fa82d1b73d/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/6433022d4690f461/gnomad.v4.0.sv.chr21.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/6433022d4690f461/gnomad.v4.0.sv.chr21.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/6433022d4690f461/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/6f337fba39cc4c2e/gnomad.v4.0.sv.chr13.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/6f337fba39cc4c2e/gnomad.v4.0.sv.chr13.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/6f337fba39cc4c2e/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/9cc0f2ee73775510/gnomad.v4.0.sv.chr10.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/9cc0f2ee73775510/gnomad.v4.0.sv.chr10.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/9cc0f2ee73775510/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/a271968c7bf845c0/gnomad.v4.0.sv.chr16.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/a271968c7bf845c0/gnomad.v4.0.sv.chr16.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/a271968c7bf845c0/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/a83da02295a7ae02/gnomad.v4.0.sv.chr20.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/a83da02295a7ae02/gnomad.v4.0.sv.chr20.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/a83da02295a7ae02/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/aea53328ecd0b712/gnomad.v4.0.sv.chr6.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/aea53328ecd0b712/gnomad.v4.0.sv.chr6.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/aea53328ecd0b712/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/bc6f1860df305e83/gnomad.v4.0.sv.chr17.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/bc6f1860df305e83/gnomad.v4.0.sv.chr17.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/bc6f1860df305e83/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/c3ce41a42c6319e0/gnomad.v4.0.sv.chr22.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/c3ce41a42c6319e0/gnomad.v4.0.sv.chr22.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/c3ce41a42c6319e0/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ca218c36ad8374d2/gnomad.v4.0.sv.chr14.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ca218c36ad8374d2/gnomad.v4.0.sv.chr14.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ca218c36ad8374d2/url.txt
Git LFS file not shown
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/d7c8ea3ac2f20138/url.txt
Git LFS file not shown
Git LFS file not shown
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/df2e7d7301f6c4e1/url.txt
Git LFS file not shown
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/e5189d35693b0b8f/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ec5c8ad8a9c29dd0/gnomad.v4.0.sv.chr12.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ec5c8ad8a9c29dd0/gnomad.v4.0.sv.chr12.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ec5c8ad8a9c29dd0/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/eed573336b6205b5/gnomad.v4.0.sv.chr19.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/eed573336b6205b5/gnomad.v4.0.sv.chr19.vcf.gz.tbi
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/eed573336b6205b5/url.txt
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ef1e660e8e0359bc/gnomad.v4.0.sv.chr1.vcf.gz
Git LFS file not shown
3 changes: 3 additions & 0 deletions excerpt-data/ef1e660e8e0359bc/gnomad.v4.0.sv.chr1.vcf.gz.tbi
Git LFS file not shown
Loading

0 comments on commit 3fd72dd

Please sign in to comment.