f665d4cc3b02924a8507b2f910eaf85eab54d433
braney
  Sat Jul 18 14:12:24 2026 -0700
hprc2X: left-shifted HPRC r2 deletion analysis and external-catalog cross-reference scripts

Deletion-only re-derivation of the HPRC Release 2 rearrangement track used to
test left-shifting indel placement and to measure how the deletions correspond
to dbSNP, DGV, ClinVar, and the previous (rel1) release. Includes the unbounded
left-normalizer, the aggregation and subsampling drivers, the stability and
cross-release carryover analyses, and the dbSNP rs cross-reference prototype.
See README.txt for the manifest; full results and cached data live in
/hive/data/genomes/hg38/bed/hprc2X.

refs #37891

diff --git src/hg/makeDb/scripts/hprc2X/xrefDbSnp.sh src/hg/makeDb/scripts/hprc2X/xrefDbSnp.sh
new file mode 100644
index 00000000000..8a55fec5103
--- /dev/null
+++ src/hg/makeDb/scripts/hprc2X/xrefDbSnp.sh
@@ -0,0 +1,11 @@
+#!/bin/bash
+set -beEu -o pipefail
+D=/hive/data/genomes/hg38/bed/hprc2X; TB=/hive/data/genomes/hg38/hg38.2bit
+export PATH=$HOME/bin/x86_64:/cluster/bin/x86_64:$PATH
+# normalize hprc2Del events (annot col4 = arrDel name) -> canonical key + name
+python3 ~/kent/src/hg/makeDb/scripts/hprc2X/leftNormDel.py $TB $D/hprc2Del.pos 4 \
+  | awk 'BEGIN{OFS="\t"}{print $1":"$2":"$4, $5}' | sort > $D/hprc2Del.canon.named
+# join canonical key -> rs (left join: every hprc2Del event, rs or empty)
+join -t $'\t' -a1 -1 1 -2 1 -o '1.2,2.2,1.1' \
+   $D/hprc2Del.canon.named $D/dbSnp.canon.rs > $D/hprc2Del.xref.tsv
+echo "DONE"