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/lrSvChirmade101.as src/hg/makeDb/scripts/lrSv/lrSvChirmade101.as new file mode 100644 index 00000000000..fcfa10edcde --- /dev/null +++ src/hg/makeDb/scripts/lrSv/lrSvChirmade101.as @@ -0,0 +1,46 @@ +table lrSvChirmade101 +"Chirmade 2026 (GWAS SVatalog) long-read structural variants" + ( + string chrom; "Chromosome" + uint chromStart; "Start position" + uint chromEnd; "End position" + string name; "Variant ID" + 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, ins, dup, inv, or complex" + int svLen; "SV Length|Absolute length of the SV in base pairs" + uint gcPct; "GC Content|Percent GC in the SV region" + string cytoband; "Cytoband" + uint geneCount; "Gene Count|Number of genes overlapping the SV" + lstring geneNames; "Overlapping Genes|Comma-separated gene symbols" + string geneAtStart; "Gene at Start|Gene at the left breakpoint" + string geneAtEnd; "Gene at End|Gene at the right breakpoint" + lstring exonName; "Overlapping Exons" + lstring cdsName; "Overlapping CDS" + string darkOverlap; "Dark Genes Overlap|Percent overlap with 'dark' (low-mappability) genes" + lstring clinGenHi; "ClinGen Haploinsufficient|Haploinsufficiency score/evidence per gene" + lstring clinGenTs; "ClinGen Triplosensitive|Triplosensitivity score/evidence per gene" + lstring gnomadLoefUpper; "gnomAD LOEUF|Observed/expected LoF upper bound per gene" + lstring gnomadMisUpper; "gnomAD Mis O/E|Observed/expected missense upper bound per gene" + lstring gnomadPli; "gnomAD pLI|Per-gene pLI" + lstring gnomadPrec; "gnomAD pRec|Per-gene pRec" + string repeatPct; "Repeat Overlap|Percent overlap with repetitive regions" + string dirtyPct; "Dirty Region Overlap|Percent overlap with 'dirty' / low-quality regions" + lstring chrRegion; "Chromosome Region" + lstring cgd; "CGD|Clinical Genomic Database gene annotation" + lstring omimPheno; "OMIM Phenotype" + lstring omimInh; "OMIM Inheritance" + lstring clinGenRegion; "ClinGen Region" + lstring decipherRegion; "Decipher Region" + lstring clinvarVarId; "ClinVar Variant ID" + string gnomadAfMax; "gnomAD AF Max (90% RO)|Max allele frequency across gnomAD populations for overlapping SV" + string gnomadPopAfMax; "gnomAD Population AF Max" + string gnomadHomRefFreq; "gnomAD Hom/Ref Freq" + string gnomadHetFreq; "gnomAD Het Freq" + string gnomadHomAltFreq; "gnomAD Hom/Alt Freq" + string dgvPct; "DGV Overlap|Percent overlap with Database of Genomic Variants" + string dgv50ro; "DGV 50% RO|Matched DGV variant at >=50% reciprocal overlap" + )