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/lrSvHgsvc3.as src/hg/makeDb/scripts/lrSv/lrSvHgsvc3.as new file mode 100644 index 00000000000..00190f98798 --- /dev/null +++ src/hg/makeDb/scripts/lrSv/lrSvHgsvc3.as @@ -0,0 +1,26 @@ +table lrSvHgsvc3 +"HGSVC3 long-read structural variants (65 samples)" + ( + 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, or INV" + int svLen; "SV Length|Absolute length of the SV in base pairs" + uint alleleCount; "Allele Count|Number of haplotypes carrying the variant across 65 diploid samples" + uint sampleCount; "Sample Count|Number of distinct samples carrying the variant (ignoring haplotype suffix)" + string homRef; "Reference Homology|Homology (bp) at breakpoints in the reference (5',3'), insdel only" + string homTig; "Contig Homology|Homology (bp) at breakpoints in the assembly contig (5',3'), insdel only" + string regionRefInner; "Inversion Inner Region|Inner coordinate range of the inversion, INV only" + string te; "Transposable Element|TE class of the inserted/deleted sequence, insdel only" + string refTrf; "In Tandem Repeat|Variant falls in a reference Tandem Repeat Finder region (True/False)" + float refSd; "Segmental Duplication Overlap|Fraction of the variant overlapping reference segmental duplications (0-1)" + lstring mergeSamples; "Carrier Haplotypes|Comma-separated list of haplotype IDs carrying this variant" + string win500; "Flanking +/- 500 bp|Genomic window around the variant" + string win2k; "Flanking +/- 2000 bp|Genomic window around the variant" + )