44c00f07b0e94306e09f30c84ea6ab0f044e1a29
max
  Fri Aug 14 05:09:12 2026 -0700
adding lin et al long-read SV subtrack, refs #38099

diff --git src/hg/makeDb/doc/hg38/lrSv.txt src/hg/makeDb/doc/hg38/lrSv.txt
index 039a46ecbcf..baf01e9c450 100644
--- src/hg/makeDb/doc/hg38/lrSv.txt
+++ src/hg/makeDb/doc/hg38/lrSv.txt
@@ -517,34 +517,42 @@
 # NPE in sequence comparison. Once the inputs are pre-filtered to
 # SV-sized records the NPE no longer fires, so the current pipeline runs
 # Jasmine with its normal sequence-aware merging. The symbolic-pipeline
 # scripts and output/ tree are retained for comparison.
 
 ##########
 # 2026-06-01 Claude max
 #
 # lrSv1kLin: 1000 Genomes linear long-read SVs from 1,218 individuals.
 # Two native VCFs (GRCh38 and CHM13/T2T-CHM13v2) provided by user from
 # dropbox (rclone copy mhaeussldropbox:1KG_LR_SVs/).
 # SVs merged with Truvari v5.2.0; population-level allele frequencies
 # (EUR, AMR, EAS, AFR, SAS) annotated with bcftools fill-tags.
 # Only DEL and INS variant types are present.
 # GRCh38: 587,779 SVs (196,369 DEL, 391,410 INS)
-# CHM13:  614,522 SVs
-# NOTE: data was received from the Eichler lab via email and has not been
-# published. Do NOT release this track and do NOT add it to lrSvAll until
-# a preprint or paper is available. HTML page is a placeholder.
+# CHM13:  614,522 SVs (238,405 DEL, 376,117 INS)
+# Callset integrated with the BoostSV machine-learning tool (Lin et al.).
+# NOTE: data was received from the Eichler lab. Manuscript submitted 2026:
+# Lin et al., "A high-resolution human pangenome structural variant resource
+# for improved disease association" (Maximilian Haeussler is a co-author).
+# Track released (release alpha removed) once the manuscript was submitted.
+# Added to the lrSvAll merge (databases.tsv key Lin1218) per user request.
+# Caveat: Lin1218 is itself a merge of overlapping 1KG callsets (HPRC, HGSVC3,
+# IB-ONT/Vienna, UW-ONT/Gustafson), so those samples are represented both in
+# their own database columns and in the Lin1218 column of lrSvAll; the merge
+# keeps per-database AC columns (it does not sum a single AC), so this is
+# double-representation, not double-counting of a single number.
 
 mkdir -p /hive/data/genomes/hg38/bed/lrSv/1k-lin
 cd /hive/data/genomes/hg38/bed/lrSv/1k-lin
 
 # Input VCFs in /hive/data/genomes/hg38/bed/lrSv/1k-lin/input/:
 #   GRCh38_INSDEL_1218.vcf.gz  (hg38 native, 587,779 SVs)
 #   CHM13_INSDEL_1218.vcf.gz   (hs1/CHM13 native, 614,522 SVs)
 
 python3 ~/kent/src/hg/makeDb/scripts/lrSv/lrSv1kLin1218VcfToBed.py \
     input/GRCh38_INSDEL_1218.vcf.gz lin1218.hg38.bed
 bedSort lin1218.hg38.bed lin1218.hg38.sorted.bed
 bedToBigBed -type=bed9+ -as=$HOME/kent/src/hg/makeDb/scripts/lrSv/lrSv1kLin1218.as \
     -tab lin1218.hg38.sorted.bed /hive/data/genomes/hg38/chrom.sizes lin1218.hg38.bb
 
 python3 ~/kent/src/hg/makeDb/scripts/lrSv/lrSv1kLin1218VcfToBed.py \
@@ -783,15 +791,29 @@
 # (reordered, plus a comparison with the 1KG ONT Vienna dataset, Schloissnig
 # et al. 2025).
 
 # Added a clarifying sentence to noyvertSv.html: the Noyvert (Boehringer) panel
 # is an independent reprocessing of the same ONT reads as the 1KG ONT Vienna
 # track (Schloissnig et al. 2025), plus a rough call-level overlap on hg38.
 # Overlap analysis (scratch, overlapSelect + bedtools, Boehringer vs Vienna):
 #   DEL (Boehringer 38,459 / Vienna 58,637): reciprocal >=50% = 12,529 (33%);
 #       >=90% = 9,136 (24%); >=10% = 15,127 (39%). Cross-checked with
 #       bedtools intersect -f .5 -r (11,802). Reverse direction ~ same.
 #   INS (Boehringer 59,953 / Vienna 73,298): within +-100bp and insLen ratio
 #       >=0.5 = 13,535 (23%); plateaus at ~26% out to +-1000bp (so not a
 #       liftOver positional-shift artifact - Vienna hg38 is lifted from CHM13).
 #   INV/DUP/BND have no comparable Vienna type (Vienna calls only DEL/INS/CPX).
 # Only trackDb HTML changed; no data rebuild.
+
+# 2026-08-13 (Claude) lrSv1kLin released and added to the lrSvAll merge.
+# The Lin et al. manuscript was submitted ("A high-resolution human pangenome
+# structural variant resource for improved disease association"; Maximilian
+# Haeussler is a co-author), so `release alpha` was removed from the lrSv1kLin
+# stanza and the label became "1KG Lin 1218 SVs". Description/methods pages
+# rewritten from the manuscript (BoostSV integration, 293 HGSVC+HPRC assemblies
+# + 480 UW-ONT + 445 IB-ONT = 1,218; 587,779 SVs hg38 / 614,522 hs1).
+# Appended databases.tsv key Lin1218 and re-ran the merge:
+python3 ~/kent/src/hg/makeDb/scripts/lrSv/lrSvMergeAll.py
+# lrSvAll grew 2,582,278 -> 3,111,026 variants (17 source databases). Note the
+# Lin1218 callset already merges several 1KG datasets (HPRC, HGSVC3, IB-ONT,
+# UW-ONT), so those samples appear both in their own columns and in Lin1218AC;
+# the merge keeps per-database AC columns, so no single count is inflated.