7594507ca126d5242346787e42e13c52ea7709b1
max
  Fri Apr 17 08:40:31 2026 -0700
Add lrSv supertrack: long-read structural variants from 9 studies (hg38).

#Preview2 week - bugs introduced now will need a build patch to fix
Sub-tracks (all bigBed 9+):
han945Sv     - 945 Han Chinese, ONT (Gong 2025, PMID 39929826)
lrSv1kgOnt   - 1019 1000 Genomes, ONT, SVAN-annotated (Schloissnig 2025,
PMID 40702182; lifted from hs1)
tommoJpSv    - 333 Japanese (111 trios), ONT (Otsuki 2022, PMID 36127505)
aou1kSv      - 1027 All of Us, PacBio HiFi (Garimella 2025, PMID 41256123)
ga4kSv       - 502 GA4K pediatric rare disease, PacBio HiFi
(Cohen 2022, PMID 35305867)
decodeSv     - 3622 Icelanders, ONT (Beyter 2021, PMID 33972781)
hgsvc3Sv     - 65 HGSVC3 diverse haplotype-resolved assemblies, HiFi+ONT
(Logsdon 2025, PMID 40702183; merges insdel+inv tables)
kwanhoSv     - 100 post-mortem brains (PD/ILBD/HC), PacBio HiFi
(Kim 2026, PMID 41929179)
chirmade101Sv - 101 long-read WGS GWAS SVatalog cohort
(Chirmade 2026, PMID 41203876)

Includes per-track conversion scripts and autoSql under
scripts/lrSv/, the supertrack summary table in lrSv.html, and a
consolidated makeDoc at doc/hg38/lrSv.txt.

refs #36258

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

diff --git src/hg/makeDb/scripts/lrSv/lrSvGa4kSvVcfToBed.py src/hg/makeDb/scripts/lrSv/lrSvGa4kSvVcfToBed.py
new file mode 100644
index 00000000000..082f128d7f5
--- /dev/null
+++ src/hg/makeDb/scripts/lrSv/lrSvGa4kSvVcfToBed.py
@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+"""Convert a GA4K Jasmine-merged SV VCF (site-only) to BED9+ for bigBed.
+
+Usage:
+    lrSvGa4kSvVcfToBed.py input.vcf.gz output.bed
+"""
+
+import gzip
+import sys
+
+SV_COLORS = {
+    "DEL": "200,0,0",      # red
+    "INS": "0,0,200",      # blue
+    "DUP": "0,160,0",      # green
+    "INV": "230,140,0",    # orange
+}
+
+
+def parseInfo(infoStr):
+    d = {}
+    for item in infoStr.split(";"):
+        if "=" in item:
+            k, v = item.split("=", 1)
+            d[k] = v
+        else:
+            d[item] = True
+    return d
+
+
+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])
+            name = fields[2]
+            info = parseInfo(fields[7])
+
+            svType = info.get("SVTYPE", ".")
+            end = int(info.get("END", pos))
+            svLen = int(float(info.get("SVLEN", "0")))
+            af = float(info.get("SVF", "0"))
+            svc = int(info.get("SVC", "0"))
+            svn = int(info.get("SVN", "0"))
+
+            chromStart = pos - 1
+            chromEnd = end
+            if chromEnd <= chromStart:
+                chromEnd = chromStart + 1
+
+            absSvLen = abs(svLen)
+            color = SV_COLORS.get(svType, "100,100,100")
+
+            row = [
+                chrom,
+                str(chromStart),
+                str(chromEnd),
+                name,
+                "0",
+                ".",
+                str(chromStart),
+                str(chromEnd),
+                color,
+                svType,
+                str(absSvLen),
+                f"{af:.6f}",
+                str(svc),
+                str(svn),
+            ]
+            fOut.write("\t".join(row) + "\n")
+
+
+if __name__ == "__main__":
+    main()