7594507ca126d5242346787e42e13c52ea7709b1 max Fri Apr 17 08:40:31 2026 -0700 Add lrSv supertrack: long-read structural variants from 9 studies (hg38). #Preview2 week - bugs introduced now will need a build patch to fix Sub-tracks (all bigBed 9+): han945Sv - 945 Han Chinese, ONT (Gong 2025, PMID 39929826) lrSv1kgOnt - 1019 1000 Genomes, ONT, SVAN-annotated (Schloissnig 2025, PMID 40702182; lifted from hs1) tommoJpSv - 333 Japanese (111 trios), ONT (Otsuki 2022, PMID 36127505) aou1kSv - 1027 All of Us, PacBio HiFi (Garimella 2025, PMID 41256123) ga4kSv - 502 GA4K pediatric rare disease, PacBio HiFi (Cohen 2022, PMID 35305867) decodeSv - 3622 Icelanders, ONT (Beyter 2021, PMID 33972781) hgsvc3Sv - 65 HGSVC3 diverse haplotype-resolved assemblies, HiFi+ONT (Logsdon 2025, PMID 40702183; merges insdel+inv tables) kwanhoSv - 100 post-mortem brains (PD/ILBD/HC), PacBio HiFi (Kim 2026, PMID 41929179) chirmade101Sv - 101 long-read WGS GWAS SVatalog cohort (Chirmade 2026, PMID 41203876) Includes per-track conversion scripts and autoSql under scripts/lrSv/, the supertrack summary table in lrSv.html, and a consolidated makeDoc at doc/hg38/lrSv.txt. refs #36258 Co-Authored-By: Claude Opus 4.7 (1M context) diff --git src/hg/makeDb/scripts/lrSv/lrSvAou1k.as src/hg/makeDb/scripts/lrSv/lrSvAou1k.as new file mode 100644 index 00000000000..beb1cf957ee --- /dev/null +++ src/hg/makeDb/scripts/lrSv/lrSvAou1k.as @@ -0,0 +1,33 @@ +table lrSvAou1k +"All of Us long-read structural variants" + ( + string chrom; "Chromosome" + uint chromStart; "Start position" + uint chromEnd; "End position" + string name; "Variant Name" + uint score; "Score" + char[1] strand; "Strand" + uint thickStart; "Thick start (same as chromStart)" + uint thickEnd; "Thick end (same as chromEnd)" + uint reserved; "Item color" + string svType; "SV Type|DEL or INS" + int svLen; "SV Length|Length of the structural variant in base pairs" + float afAfr; "AF African|Allele frequency in African/African American samples" + float afAmr; "AF Admixed American|Allele frequency in Admixed American samples" + float afEas; "AF East Asian|Allele frequency in East Asian samples" + float afEur; "AF European|Allele frequency in European samples" + float afSas; "AF South Asian|Allele frequency in South Asian samples" + string fst; "Fst (AFR vs Non-AFR)|Fixation index between African and non-African populations" + lstring omimGenes; "OMIM Genes|OMIM genes intersected with pLI and LOEUF scores" + lstring diseaseGenes; "Disease Genes|Disease genes intersected with pLI and LOEUF scores" + lstring cancerGenes; "Cancer Genes|Cancer genes intersected with pLI and LOEUF scores" + lstring acmgGenes; "ACMG Genes|ACMG genes intersected with pLI and LOEUF scores" + string regElement; "Regulatory Element|Type of regulatory element intersected (e.g. enhancer, promoter)" + string segDup; "SegDup|Segmental duplication association (INS: within 1kb, DEL: intersect)" + string tandemRepeat; "Tandem Repeat|Tandem repeat intersected" + string otherLrDatasets; "Other LR Datasets|Detected in other long-read datasets (HPRC, HGSVC, 1KG-ONT)" + string detectedInSr; "Detected in SR|Detected in matched AoU short-read data" + lstring eqtls; "eQTLs|eQTL associations: gene(qvalue)" + lstring gwas; "GWAS Associations|GWAS associations: trait(gene, rsID, pvalue, LD_r2)" + lstring traitAssoc; "SV-Trait Associations|SV-trait associations in AoU Phase I (Carrier%, Non-carrier%, OR, 95% CI, pvalue)" + )