3bf9e1a841206d3bf5902e06791ef5be2dbdbd39 max Fri Jul 17 09:09:47 2026 -0700 lrSv: add Noyvert multi-ancestry long-read SV subtrack (noyvertSv) #Preview2 week - bugs introduced now will need a build patch to fix 888 Oxford Nanopore 1000 Genomes genomes, Sniffles2 v2.0.7, 107,445 SVs with per-superpopulation allele frequencies, imputation-accuracy metrics and UK Biobank SV-WAS associations. Converter approximates AC/AN from AF and the genotype missing rate (source has no allele count), stores BND mate breakends, and follows the shared lrSv svType/svLen/insLen/AC field convention so the container-level filters apply. refs #36258 diff --git src/hg/makeDb/scripts/lrSv/lrSvNoyvert.as src/hg/makeDb/scripts/lrSv/lrSvNoyvert.as new file mode 100644 index 00000000000..f6d8752ec7e --- /dev/null +++ src/hg/makeDb/scripts/lrSv/lrSvNoyvert.as @@ -0,0 +1,35 @@ +table lrSvNoyvert +"Multi-ancestry long-read structural variants (888 samples, Noyvert et al. 2025)" + ( + 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, INS, INV, DUP or BND" + int svLen; "SV Length|Length of the variant on the reference in base pairs" + int insLen; "Insertion Length|Length of inserted sequence, 0 for non-insertions" + int AC; "Allele Count|Approximate alternate allele count (AF times allele number)" + int AN; "Allele Number|Approximate called alleles, 2 x 888 x (1 - missing rate)" + float AF; "Allele Frequency|Overall allele frequency across all samples" + float afAfr; "AF African|Allele frequency in African samples (n=241)" + float afAmr; "AF Admixed American|Allele frequency in Admixed American samples (n=144)" + float afEas; "AF East Asian|Allele frequency in East Asian samples (n=168)" + float afEur; "AF European|Allele frequency in European samples (n=164)" + float afSas; "AF South Asian|Allele frequency in South Asian samples (n=171)" + string secondBp; "Second Breakpoint|Mate breakend locus and orientation, BND records only" + float stdevLen; "Length StdDev|Sniffles2 standard deviation of SV length across samples" + float stdevPos; "Position StdDev|Sniffles2 standard deviation of the breakpoint position" + float missingRate; "Genotype Missing Rate|Fraction of samples with a missing genotype" + string hwe; "HWE p-values|Hardy-Weinberg exact test p-value per superpopulation" + float r2Loo; "Imputation r2 (LOO)|Leave-one-out internal imputation accuracy" + float concordanceLoo; "Minor Allele Concordance (LOO)|Leave-one-out minor-allele genotype concordance" + float afUkb; "AF in UK Biobank|Imputed allele frequency in the UK Biobank cohort" + float r2Ukb; "Imputation r2 (UKB)|Imputation accuracy in the UK Biobank cohort" + int nGwas; "GWAS Hit Count|Number of significant UK Biobank SV-WAS trait associations" + lstring ukbGwas; "UK Biobank GWAS|Significant SV-WAS associations (trait: info, log10 p-value)" + )