0f23d17640ca30e2c9ee456c7e15966cabd3bc57 max Mon Sep 7 23:32:24 2026 -0700 Position box: let a hyphen separate a range of codons, e.g. "BRCA1 100-200" A bare number after a gene symbol has always meant a codon, and "KAT6A 495-533" was already accepted -- it just landed on codon 495 and dropped the rest, the same silent truncation that the underscore form had. A hyphen now separates a range wherever the coordinates are protein: after a gene symbol with no prefix, and after an explicit p. with a symbol or a transcript accession. The hyphen stays out of c. and n. terms, where HGVS already uses it for an intron offset. KAT6A c.1483-1599 is still the single base 1599 nt before c.1483, not codons 1483 to 1599, and there are now regression tests pinning both readings so the two do not drift into each other. refs #38285 diff --git src/hg/lib/tests/expected/hgvs/validTerms.txt src/hg/lib/tests/expected/hgvs/validTerms.txt index a29a90f8c10..04aae108e3a 100644 --- src/hg/lib/tests/expected/hgvs/validTerms.txt +++ src/hg/lib/tests/expected/hgvs/validTerms.txt @@ -42,15 +42,26 @@ chr3 38555661 38555664 NM_198056.3:pArg1512Trp 0 - chr20 33443333 33443334 NM_003098.2:c.287G>C 0 - chr17 43093299 43093300 NM_007294.3:c.2231C>A 0 - chr17 43093299 43093300 NM_007294.3(BRCA1):c.2231C>A 0 - # Bare codon numbers and ranges of codon numbers, refs #38285 chr8 41955408 41955411 KAT6A p.495 0 - chr8 41949362 41955411 KAT6A p.495_533 0 - chr8 41949362 41955411 KAT6A p.Lys495_Ser533 0 - chr8 41955408 41955411 NM_006766.5 p.495 0 - chr8 41949362 41955411 NM_006766.5 p.495_533 0 - chr8 41955408 41955411 ENST00000265713.8 p.495 0 - chr8 41949362 41955411 ENST00000265713.8 p.495_533 0 - chr8 41949362 41955411 KAT6A c.1483_1599 0 - +chr8 41955408 41955411 KAT6A 495 0 - +chr8 41949362 41955411 KAT6A 495_533 0 - +# A hyphen is a range separator in protein coordinates only, refs #38285 +chr8 41949362 41955411 KAT6A 495-533 0 - +chr8 41949362 41955411 KAT6A p.495-533 0 - +chr8 41949362 41955411 NM_006766.5 p.495-533 0 - +chr8 41949362 41955411 ENST00000265713.8 p.495-533 0 - +# ...but in c. and n. terms a hyphen is still an intron offset, not a range: +# this one must stay a single base 1599 nt before c.1483, not codons 1483..1599 +chr8 41957009 41957010 KAT6A c.1483-1599 0 - +chr8 42049489 42049490 KAT6A n.100-200 0 -