78cdae7249c8609dcbc743e996ea7e5eec33d75a max Mon Aug 17 08:15:39 2026 -0700 lrSv: fix off-by-one anchor base in deletion coordinates across converters, refs #38099 VCF/pangenome deletions carry a non-deleted anchor (padding) base at POS. Several lrSv converters set chromStart = pos-1, which includes that anchor, so each deletion was 1 bp too wide on the left and svLen was 1 too big. Callsets handled this inconsistently, so the same deletion appeared at offset coordinates and failed to merge in lrSvAll. For deletions only (INS/INV/CPX unchanged), advance chromStart past the anchor so the interval covers exactly the deleted bases (svLen == |SVLEN|). Verified against the hg38 reference: the old left base is present in both REF and ALT (i.e. retained by the sample), so it should not be inside the deletion. Fixed 11 converters: lrSv1kLin1218VcfToBed, lrSv1kgOntVcfToBed, lrSvGustafsonVcfToBed, lrSvGa4kSvVcfToBed, lrSvDecodeVcfToBed, lrSvAou1kCsvToBed, lrSvColorsDbSvVcfToBed, lrSvCardBbToBed, lrSvAprVcfToBed, lrSvCpc1VcfToBed, lrSvVcfToBed (generic, used by han945). Left unchanged, verified already anchor-correct: hgsvc3 and hgsvc2 (0-based source), hprc2v21 (Ro converter prefix-trims), noyvert/tommoJp (POS is the first deleted base), chirmade101 (1-based-closed source). Rebuilt all affected bigBeds (hg38 + hs1 where present) and the lrSvAll merge: 3,111,026 -> 2,963,093 rows as ~148k duplicate deletions now merge. diff --git src/hg/makeDb/scripts/lrSv/lrSvAprVcfToBed.py src/hg/makeDb/scripts/lrSv/lrSvAprVcfToBed.py index 11742f0293c..34cdc5e9ac0 100755 --- src/hg/makeDb/scripts/lrSv/lrSvAprVcfToBed.py +++ src/hg/makeDb/scripts/lrSv/lrSvAprVcfToBed.py @@ -130,30 +130,35 @@ if i < len(ac_list): ac_sum += _int(ac_list[i]) num_pass += 1 if num_pass == 0: skipped_no_sv_alt += 1 continue sv_type = next(iter(types)) if len(types) == 1 else "MIXED" sv_type = normalizeSvType(sv_type) rgb = svColor(sv_type) pos0 = int(pos) - 1 start = pos0 end = start + max(ref_len, 1) + # For DEL, POS is the non-deleted anchor base; drop it from the left + # (end already = pos-1+ref_len). The shared prefix is >=1 base so this + # never over-shifts. Only DEL moves; INS/MIXED keep the anchor. + if sv_type == "DEL": + start += 1 af = (ac_sum / an) if an else 0.0 score = min(1000, max(0, int(round(af * 1000)))) svLen = end - start if sv_type == "INS": insLen = max_ins else: insLen = 0 featLen = insLen if sv_type in ("INS", "MEI") else svLen name = svName(sv_type, featLen, ac_sum) row = [ chrom, str(start), str(end), name,