66c51e29423da24a7144c7ba99a4cc2ebc96b32c
max
  Mon Sep 28 13:54:36 2026 -0700
varFreqs: combined tracks rebuilt with SFARI SPARK 45k WGS (without its NonHumanIns insertions); add its filter blocks, affected label now ~150,000 individuals, refs #38424

diff --git src/hg/makeDb/doc/hg38/varFreqs.txt src/hg/makeDb/doc/hg38/varFreqs.txt
index 47689ac58ed..7c7601c5dc2 100644
--- src/hg/makeDb/doc/hg38/varFreqs.txt
+++ src/hg/makeDb/doc/hg38/varFreqs.txt
@@ -1366,15 +1366,32 @@
     "$B view -r {} -e 'FILTER~\"NonHumanIns\"' -Ob -o merge.work/{}.bcf sparkWgs45kAsd.vcf.gz"
 $B concat -Oz --threads 8 -o sparkWgs45kAsd.noNonHumanIns.vcf.gz merge.work/chr{1..22}.bcf merge.work/chr{X,Y}.bcf
 tabix -p vcf sparkWgs45kAsd.noNonHumanIns.vcf.gz     # 493,014,684 records
 # databases.tsv: added SPARK45k, the 12k pilot SFARI_WGS is now displayed as
 # "SFARI SPARK iWGS v1.1 Pilot"; populations.tsv: SPARK45k AUT/NON_AUT arms.
 # The build writes varFreqsNew*.bb, which are moved over the live files at the
 # end, so hgwdev's /gbdb never points at a half-written bigBed.
 cd /hive/data/genomes/hg38/bed/varFreqs/all
 rm -f merged.vcf.gz merged.vcf.gz.tbi merged.annotated.vcf.gz \
       merged.annotated.vcf.gz.tbi normalized_files.txt
 bash ~/kent/src/hg/makeDb/scripts/varFreqs/mergeAndAnnotate.sh
 python3 ~/kent/src/hg/makeDb/scripts/varFreqs/vcfToBigBed.py \
     --annotated-vcf merged.annotated.vcf.gz --output-prefix varFreqsNew \
     --split-affected --threads 8 --work-dir /hive/data/genomes/hg38/bed/varFreqs/all \
     > rebuild45k.log 2>&1
+# Merged variants: 1,505,737,716 (was 1,374,129,993). varFreqsAffected
+# 425,183,826 items / 38.6 GB (was 133,290,997; the 20,858 SPARK 45k ASD genomes
+# add many rare WGS variants), varFreqsBackground 1,381,032,442 items / 71.0 GB
+# (was 1,278,354,588); 191 fields (SPARK45k adds AC/AF and AUT/NON_AUT AC/AF).
+# APOE rs429358: affectedAC/AN 38,922 / 254,866 = 32,782 + 6,140 and
+# 213,150 + 41,716 (SPARK45k AUT), SPARK45k ASD AF 0.147186 as in the subtrack.
+mv varFreqsAffected.bb varFreqsAffected.bb.preSpark45k.bak
+mv varFreqsNewAffected.bb varFreqsAffected.bb
+mv varFreqsBackground.bb varFreqsBackground.bb.preSpark45k.bak
+mv varFreqsNewBackground.bb varFreqsBackground.bb
+mv -f varFreqsNewAffected.as varFreqsAffected.as
+mv -f varFreqsNewBackground.as varFreqsBackground.as
+mv varFreqs.trackDb.ra varFreqs.trackDb.ra.preSpark45k
+mv varFreqsNew.trackDb.ra varFreqs.trackDb.ra
+# varFreqs.ra: SPARK45k in the affectedCohorts/backgroundSources menus and the
+# commented per-cohort filter blocks, taken from varFreqs.trackDb.ra; the
+# affected longLabel now says ~150,000 individuals.