e7b98d8286de2133b30617a7eb9c78cd355fd21e braney Thu Aug 13 14:32:17 2026 -0700 geneReviews otto: survive a knownGene rebuild, and keep the bigBed in step with the tables, refs #38098 hg19 and hg18 take their gene coordinates from knownGene. The hg19 knownGene rebuild on 2026-07-15 moved the ends of most genes by a few bases, and the validation step compared chrom, chromStart, chromEnd and name exactly. That made 1325 of 1939 rows look new, far past the 10 percent ceiling, so the job has failed every week since July 21 and the tables have been stuck at their June 30 version. validateGeneReviews.sh now compares the overall span of each gene on each chromosome and counts a gene as unchanged when the old and new spans overlap. geneReviewsDetail still compares whole rows exactly. A zero-overlap result now fails with a message rather than an awk divide-by-zero. checkGeneReviews.sh validates all three assemblies before deciding, so one bad assembly no longer hides the state of the others. hg18 had not been checked since July. buildGeneReviews.sh pointed /gbdb at the new bigBed before validation ran, so a failed run left the browser image and the geneReviews tables six weeks apart. The relink moves to checkGeneReviews.sh, after validation passes and the tables are installed. diff --git src/hg/utils/otto/geneReviews/buildGeneReviews.sh src/hg/utils/otto/geneReviews/buildGeneReviews.sh index a4924193365..01df03328c1 100755 --- src/hg/utils/otto/geneReviews/buildGeneReviews.sh +++ src/hg/utils/otto/geneReviews/buildGeneReviews.sh @@ -51,35 +51,36 @@ db=$1 perl ../geneRevsAddDiseases.pl $geneDiseaseFile geneReviews.$db.tab > geneReviewsExt.$db.tab bedSort geneReviewsExt.$db.tab stdout | uniq > geneReviewsExt.$db.bed gbdb="/gbdb/$db/geneReviews" mkdir -p $gbdb # validate oldLc=`bigBedToBed $gbdb/geneReviews.bb stdout | wc -l` newLc=`wc -l < geneReviewsExt.$db.bed` echo rowcount: old $oldLc new: $newLc if [ $oldLc -ne 0 ]; then echo $oldLc $newLc | \ awk '{if (($2-$1)/$1 > 0.1) {printf "validate $db GENE REVIEWS failed: old count: %d, new count: %d\n", $1,$2; exit 1;}}' fi -#install +# Build the bigBed, but leave /gbdb pointing at the previous build for now. +# checkGeneReviews.sh moves the link after validation passes, so the browser +# image and the geneReviews/geneReviewsDetail tables always come from the same +# build. bedToBigBed -tab -type=bed9+2 -as=../geneReviews.as geneReviewsExt.$db.bed \ /hive/data/genomes/$db/chrom.sizes geneReviews.$db.bb -rm -f $gbdb/geneReviews.bb -ln -s `pwd`/geneReviews.$db.bb $gbdb/geneReviews.bb # Create and load geneReviewsDetail table hgsql $1 -N -e \ "SELECT s.geneSymbol, s.grShort, t.NBKid, t.grTitle \ FROM geneReviewsGrshortNBKidNew s, geneReviewsGrshortTitleNBKidNew t \ WHERE s.grShort = t.grShort ORDER BY s.geneSymbol;" > geneReviewsDetail.tab hgsql $1 -e 'drop table if exists geneReviewsDetailNew' hgsql $1 -e 'create table geneReviewsDetailNew select * from geneReviewsDetail limit 0' hgsql $1 -e \ 'load data local infile "geneReviewsDetail.tab" into table geneReviewsDetailNew' } ####### main ##########