9eb4e0937782954c19d664e7d384d210bffb3b25
max
  Sat Jun 13 16:01:42 2026 -0700
lrSv: QA fixes from Lou's review - dedup, shared color palette, deCODE/AoU cleanup

- Drop kwanhoSv (KimPD) from the lrSvAll merge in databases.tsv; it stays on
dev/alpha until published, which also removes its >5 Mb breakend artifacts
from the merged track.
- Remove searchIndex from colorsDbSv, lrSv1kLin and lrSvAll (and the merge
generator): the bigBeds were built without a name index, so by-name search
never worked.
- Single shared per-SV-type color palette in lrSvCommon.py (svColor), used by
every converter and the merge. CPX is purple everywhere (was orange in
1kgOnt/apr/cpc1, colliding with INV's orange), colorsDb DEL is 200,0,0 like
the rest, and TRA/INSDEL get their own colors.
- deCODE: drop byte-identical duplicate rows and blank the fake AC=50
placeholder (AC is now a string field, omitted from the name and mouseOver).
- AoU: numeric-entity-encode non-ASCII gene/trait text and drop duplicate rows.
- gustafson, chirmade101, hprc2v21: drop byte-identical duplicate rows.
- lrSvMergeAll.py: skip byte-identical duplicate source rows instead of summing
their allele counts, which had inflated the per-database and total AC.

refs #36258

diff --git src/hg/makeDb/scripts/lrSv/lrSvVcfToBed.py src/hg/makeDb/scripts/lrSv/lrSvVcfToBed.py
index 754dec4aa9b..6c48315c4d2 100644
--- src/hg/makeDb/scripts/lrSv/lrSvVcfToBed.py
+++ src/hg/makeDb/scripts/lrSv/lrSvVcfToBed.py
@@ -1,144 +1,135 @@
 #!/usr/bin/env python3
 """Convert a SURVIVOR-merged SV VCF (site-only) to BED9+ for bigBed.
 
 Usage:
     lrSvVcfToBed.py input.vcf.gz output.bed
 """
 
 import gzip
 import os
 import sys
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-from lrSvCommon import svName, normalizeSvType, insLenFor
-
-# Colors by SV type (R,G,B)
-SV_COLORS = {
-    "DEL": "200,0,0",      # red
-    "INS": "0,0,200",      # blue
-    "DUP": "0,160,0",      # green
-    "INV": "230,140,0",    # orange
-    "TRA": "140,0,200",    # purple
-}
+from lrSvCommon import svName, normalizeSvType, insLenFor, svColor
 
 def parseInfo(infoStr):
     """Parse INFO field into a dict."""
     d = {}
     for item in infoStr.split(";"):
         if "=" in item:
             k, v = item.split("=", 1)
             d[k] = v
         else:
             d[item] = True
     return d
 
 def suppVecToList(suppVec):
     """Convert binary support vector to comma-separated 1-based sample indices."""
     indices = []
     for i, c in enumerate(suppVec):
         if c == "1":
             indices.append(str(i + 1))
     return ",".join(indices) if indices else ""
 
 def main():
     if len(sys.argv) != 3:
         print(__doc__, file=sys.stderr)
         sys.exit(1)
 
     inFile, outFile = sys.argv[1], sys.argv[2]
     opener = gzip.open if inFile.endswith(".gz") else open
 
     with opener(inFile, "rt") as fIn, open(outFile, "w") as fOut:
         for line in fIn:
             if line.startswith("#"):
                 continue
 
             fields = line.rstrip("\n").split("\t")
             chrom = fields[0]
             pos = int(fields[1])
             qual = fields[5]
             info = parseInfo(fields[7])
 
             svTypeRaw = info.get("SVTYPE", ".")
             svType = normalizeSvType(svTypeRaw)
             end = int(info.get("END", pos))
             svLenRaw = int(float(info.get("SVLEN", "0")))
             af = float(info.get("AF", "0"))
             supp = int(info.get("SUPP", "0"))
             ciPos = info.get("CIPOS", "0,0")
             ciEnd = info.get("CIEND", "0,0")
             chr2 = info.get("CHR2", ".")
             strands = info.get("STRANDS", "+-")
             suppVec = info.get("SUPP_VEC", "")
 
             # BED is 0-based half-open
             chromStart = pos - 1
 
             # For INS, END == POS so the item has zero width; expand by 1 bp
             chromEnd = end
             if chromEnd <= chromStart:
                 chromEnd = chromStart + 1
 
             # Score: map QUAL to 0-1000
             try:
                 score = min(int(round(float(qual) * 2)), 1000)
             except ValueError:
                 score = 0
 
             # Strand from first character of STRANDS field
             strand = strands[0] if strands and strands[0] in "+-" else "."
 
-            color = SV_COLORS.get(svType, "100,100,100")
+            color = svColor(svType)
 
             # sampleList from SUPP_VEC
             sampleList = suppVecToList(suppVec)
 
             # end2 for TRA; empty for non-TRA so skipEmptyFields hides them
             end2 = str(end) if svType == "TRA" else ""
             chr2Out = chr2 if svType == "TRA" else ""
 
             # For TRA, chromEnd is the position on chr1 side, not chr2
             if svType == "TRA":
                 chromEnd = chromStart + 1
 
             # svLen: length on reference
             svLen = chromEnd - chromStart
             # insLen: for INS use abs(SVLEN); else 0 (except TRA which is 0)
             if svType in ("INS", "MEI"):
                 insLen = abs(svLenRaw)
             else:
                 insLen = 0
 
             # AC: SURVIVOR input doesn't have AC, use supp*2 as approximation
             # (SUPP is number of samples carrying; use 2*SUPP as proxy for diploid AC)
             ac = supp * 2
 
             featLen = insLen if svType in ("INS", "MEI") else svLen
             name = svName(svType, featLen, ac)
 
             row = [
                 chrom,
                 str(chromStart),
                 str(chromEnd),
                 name,
                 str(score),
                 strand,
                 str(chromStart),   # thickStart
                 str(chromEnd),     # thickEnd
                 color,
                 svType,
                 str(svLen),
                 str(insLen),
                 str(ac),
                 f"{af:.6f}",
                 str(supp),
                 ciPos,
                 ciEnd,
                 chr2Out,
                 end2,
                 sampleList,
             ]
             fOut.write("\t".join(row) + "\n")
 
 if __name__ == "__main__":
     main()