4f8f8773bec66a9e993e9897e0b032c6e97dead8 max Fri May 15 10:12:29 2026 -0700 mei: add HMEID, SweGen, and euL1db subtracks Three new MEI catalogues under the existing mei superTrack: meiHmeid (hg38) 36,699 MELT MEIs from HMEID v1.1 (NyuWa+1KGP, 5,675 individuals, Niu et al. 2022, PMID 35212372). Site-level VCF; per-cohort and per-1KGP super- population AC/AN/AF; SVTYPE Alu/L1/SVA/HERVK. meiSwegen (hg38 lifted) 18,090 MELT MEIs from the SweGen 1,000-sample Swedish cohort (Ameur 2017, PMID 28832569; Gardner 2017, PMID 28855259). Built on hg19, liftOver to hg38 (10 unmapped). tableBrowser off per SweGen distribution terms. meiEul1db (hg19+hg38) 8,988 curated L1-HS insertion polymorphisms (MRIPs) from euL1db v1.00 (Mir 2015, PMID 25352549), aggregating 142,495 sample-level SRIPs across 32 published studies. Coloured by lineage (germline/somatic/mixed). Built on hg19, liftOver to hg38 (3 unmapped). Helman2014 used numeric chrom names (23=X, 24=Y) which are renamed during the build. meiEul1dbRef (hg19+hg38) 1,540 reference-genome L1-HS copies catalogued by euL1db (companion to meiEul1db). Single shared mei.ra (in human/) uses $D substitution so each stanza serves both assemblies where applicable. refs #37524 diff --git src/hg/makeDb/scripts/mei/meiHmeid.as src/hg/makeDb/scripts/mei/meiHmeid.as new file mode 100644 index 00000000000..7e145bf5d0c --- /dev/null +++ src/hg/makeDb/scripts/mei/meiHmeid.as @@ -0,0 +1,41 @@ +table meiHmeid +"Mobile Element Insertions in 5,675 genomes (HMEID v1.1 / NyuWa + 1KGP, GRCh38)" +( +string chrom; "Reference chromosome or scaffold" +uint chromStart; "0-based start position (anchor base)" +uint chromEnd; "Half-open end position (anchor base + 1)" +string name; "Item label (INS, MEI class, carrier allele count)" +uint score; "Score (alt-allele frequency * 1000)" +char[1] strand; "Strand (always .)" +uint thickStart; "Start of thick drawing region" +uint thickEnd; "End of thick drawing region" +uint itemRgb; "RGB color, by mobile-element class" +string teClass; "TE class|Family of mobile element (Alu, L1, SVA, HERVK)" +int svLen; "Insertion length (bp), -1 if unknown" +string tsd; "Target site duplication|TSD sequence reported by MELT, '.' if unknown" +int assess; "MELT ASSESS score|0=no overlapping reads, 1=imprecise, 2=discordant pairs only, 3=left-side TSD only, 4=right-side TSD only, 5=TSD decided with split reads (highest quality)" +int altAlleleCount; "Carrier haplotypes (all)|Haplotypes carrying the insertion across all 5,675 samples" +int alleleNumber; "Genotyped haplotypes (all)|Total haplotypes successfully genotyped" +float altAlleleFreq; "Allele frequency (all)|Alt-allele frequency across all 5,675 samples" +int nyuwaAC; "NyuWa AC|Alt-allele count in NyuWa (Chinese) cohort" +int nyuwaAN; "NyuWa AN|Genotyped haplotypes in NyuWa cohort" +float nyuwaAF; "NyuWa AF|Alt-allele frequency in NyuWa (Chinese) cohort" +int kgpAC; "1KGP AC|Alt-allele count in 1000 Genomes cohort" +int kgpAN; "1KGP AN|Genotyped haplotypes in 1000 Genomes cohort" +float kgpAF; "1KGP AF|Alt-allele frequency in 1000 Genomes cohort" +int afrAC; "AFR AC|Alt-allele count in 1KGP African super-population" +int afrAN; "AFR AN|Genotyped haplotypes in AFR" +float afrAF; "AFR AF|Alt-allele frequency in AFR" +int amrAC; "AMR AC|Alt-allele count in 1KGP Admixed American super-population" +int amrAN; "AMR AN|Genotyped haplotypes in AMR" +float amrAF; "AMR AF|Alt-allele frequency in AMR" +int easAC; "EAS AC|Alt-allele count in East Asian super-population (1KGP only)" +int easAN; "EAS AN|Genotyped haplotypes in EAS (1KGP only)" +float easAF; "EAS AF|Alt-allele frequency in EAS (1KGP only)" +int eurAC; "EUR AC|Alt-allele count in 1KGP European super-population" +int eurAN; "EUR AN|Genotyped haplotypes in EUR" +float eurAF; "EUR AF|Alt-allele frequency in EUR" +int sasAC; "SAS AC|Alt-allele count in 1KGP South Asian super-population" +int sasAN; "SAS AN|Genotyped haplotypes in SAS" +float sasAF; "SAS AF|Alt-allele frequency in SAS" +)