bac95a147f49cd331052e597006e04b3deee40fc max Wed Apr 22 10:43:20 2026 -0700 lrSv/srSv: human-readable SV type filter labels, script cleanups Add human-readable labels to the supertrack-level svType filter on both the lrSv and srSv supertracks using the "CODE|CODE (Long name)" filterValues syntax: DEL -> "DEL (Deletion)", INS -> "INS (Insertion)", etc. Labels keep the short code up front so users can match what hgTracks shows next to each feature. Also sweep in the in-progress converter/as-file cleanups under scripts/lrSv/ and scripts/srSv/ (introduction of lrSvCommon.py helpers, consistent insLen / svLen / AC column naming, tightened field-description text) that had been piling up as an unstaged working tree. refs #36258 diff --git src/hg/makeDb/scripts/lrSv/lrSvKwanho.as src/hg/makeDb/scripts/lrSv/lrSvKwanho.as index 8a490015eb6..e14247413bb 100644 --- src/hg/makeDb/scripts/lrSv/lrSvKwanho.as +++ src/hg/makeDb/scripts/lrSv/lrSvKwanho.as @@ -1,42 +1,44 @@ 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" + int svLen; "SV Length|Length of the variant on the reference in base pairs" + int insLen; "Insertion Length|Length of inserted sequence, 0 for DEL/INV/CPX" + int AC; "Allele Count|Total AC across PD+HC+ILBD cohorts" 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" )