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) <noreply@anthropic.com> diff --git src/hg/makeDb/scripts/lrSv/lrSvKwanho.as src/hg/makeDb/scripts/lrSv/lrSvKwanho.as new file mode 100644 index 00000000000..8a490015eb6 --- /dev/null +++ src/hg/makeDb/scripts/lrSv/lrSvKwanho.as @@ -0,0 +1,42 @@ +table lrSvKwanho +"Kim 2026 Parkinson's disease brain 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 or INV" + int svLen; "SV Length|Absolute length of the SV in base pairs" + string sizeBin; "Size Bin|Length category used in the paper (e.g. [50,100))" + uint qual; "Quality|Variant quality score from the joint callset" + uint supp; "Caller Support|Number of SV callers supporting this variant" + string suppVec; "Cohort Support Vector|Bitmask indicating which cohorts carry the variant (PD/ILBD/HC)" + float missingRate; "Missing-genotype Rate|Fraction of samples with missing genotype at this site" + float caseRate; "Case Carrier Rate|Fraction of PD+ILBD cases carrying the variant" + float controlRate; "Control Carrier Rate|Fraction of HC controls carrying the variant" + float differentialRate; "Case-Control Differential|caseRate - controlRate (negative: enriched in controls)" + float afPd; "Allele Frequency (PD)|Alternate allele frequency in Parkinson's disease samples" + float afHc; "Allele Frequency (HC)|Alternate allele frequency in healthy-control samples" + float afIlbd; "Allele Frequency (ILBD)|Alternate allele frequency in incidental Lewy body disease samples" + uint acPd; "Allele Count (PD)|Alternate allele count in PD samples" + uint acHc; "Allele Count (HC)|Alternate allele count in HC samples" + uint acIlbd; "Allele Count (ILBD)|Alternate allele count in ILBD samples" + uint anPd; "Allele Number (PD)|Total called alleles in PD samples" + uint anHc; "Allele Number (HC)|Total called alleles in HC samples" + uint anIlbd; "Allele Number (ILBD)|Total called alleles in ILBD samples" + uint nCarriersPd; "Carrier Count (PD)" + uint nCarriersHc; "Carrier Count (HC)" + uint nCarriersIlbd; "Carrier Count (ILBD)" + uint ldSnpsCount; "LD SNPs|Number of nearby SNPs in linkage disequilibrium with this SV" + uint totalSnpsNearby; "Nearby SNPs|Total number of SNPs in the surrounding window" + float avgMapQuality; "Avg Mapping Quality|Average read mapping quality at the SV" + float avgReadsPerSample; "Avg Reads / Sample|Average supporting reads per sample" + lstring pdCarriers; "PD Carriers|Sample IDs of PD carriers" + lstring hcCarriers; "HC Carriers|Sample IDs of HC carriers" + lstring ilbdCarriers; "ILBD Carriers|Sample IDs of ILBD carriers" + )