f350ebff8f2cc1e0772032e59e926b5e45b374cd
lrnassar
  Tue May 5 16:18:28 2026 -0700
Adding ClinPred missense pathogenicity score track on hg19 and hg38. refs #37510

ClinPred (Alirezaie et al, AJHG 2018) joins the predictionScoresSuper supertrack
as a composite of four bigWigs, one per alternate base, with a per-position color
overlay (red for score >= 0.5 likely pathogenic, blue for < 0.5 likely benign).
Adds clinPredToWig.py to convert the upstream score table to wig, a clinPred
branch in makeWigColorByRevelCadd.py for the color overlay step, and reciprocal
relatedTracks entries to REVEL, CADD, PrimateAI-3D, and AlphaMissense. Also adds
Display Conventions and Credits entries in predictionScoresSuper.html for
ClinPred, PrimateAI-3D, and PromoterAI.

diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt
index 063dad39988..0c38157241a 100644
--- src/hg/makeDb/doc/hg19.txt
+++ src/hg/makeDb/doc/hg19.txt
@@ -36012,15 +36012,47 @@
 # gnomad MPC 2025-10-17 max
 cd /hive/data/genomes/hg19/bed/gnomad/mpc
 wget https://storage.googleapis.com/gcp-public-data--gnomad/release/2.1.1/regional_missense_constraint/gnomAD_v2.1.1_transcripts_with_rmc.tsv
 cat gnomAD_v2.1.1_transcripts_with_rmc.tsv | python ~/kent/src/hg/makeDb/gnomad/gnomadMpcToBed.py | sort -k1,2n > mpc.bed
 bedToBigBed mpc.bed ../../../chrom.sizes mpc.bb -as=~/kent/src/hg/makeDb/gnomad/mpc.as -type=bed9+ -tab
 #############################################################################
 # variant frequencies, 2025-11-07, Max
 cd /hive/data/genomes/hg19/bed/varFreqs/mexbb/
 # got files as-is from Carmina
 cd /hive/data/genomes/hg19/bed/varFreqs/sgdp/
 https://sharehost.hms.harvard.edu/genetics/reich_lab/sgdp/vcf_variants/vcfs.variants.public_samples.279samples.tar
 tar xvfz *.tar
 ls *.vcf.gz > vcf.list
 bcftools merge -l vcf.list -O z -o SGDP.nh2.vcf.gz --threads 20
 tabix -p vcf SGDP.nh2.vcf.gz
+
+#############################################################################
+# ClinPred missense pathogenicity scores, RM #37510, 2026-05-05, Lou
+
+mkdir -p /hive/data/genomes/hg19/bed/clinPred
+cd /hive/data/genomes/hg19/bed/clinPred
+
+# Downloaded from https://sites.google.com/site/clinpred/ on May 5, 2026.
+# The ClinPred site links to a Google Drive file; bypass the virus-scan
+# interstitial with confirm=t to fetch directly:
+curl -L -o ClinPred.txt \
+    "https://drive.usercontent.google.com/download?id=1Rh696VtfU4BBI33EltsW5BltOCDqc8Q4&export=download&confirm=t"
+
+# Input is tab-separated: Chr Start Ref Alt ClinPred_Score (1-based positions,
+# no chr prefix, three rows per scored exome position).
+time python3 ~/kent/src/hg/makeDb/clinPred/clinPredToWig.py \
+    /hive/data/genomes/hg19/chrom.sizes ClinPred.txt
+
+wigToBigWig a.wig /hive/data/genomes/hg19/chrom.sizes a.bw &
+wigToBigWig c.wig /hive/data/genomes/hg19/chrom.sizes c.bw &
+wigToBigWig g.wig /hive/data/genomes/hg19/chrom.sizes g.bw &
+wigToBigWig t.wig /hive/data/genomes/hg19/chrom.sizes t.bw &
+wait
+rm -f *.wig
+
+# Color overlays generated with:
+~/kent/src/hg/makeDb/scripts/wigColorByColors/makeWigColorByRevelCadd.py
+
+# Install to /gbdb:
+mkdir -p /gbdb/hg19/clinPred
+ln -s /hive/data/genomes/hg19/bed/clinPred/{a,c,g,t}.bw /gbdb/hg19/clinPred/
+ln -s /hive/data/genomes/hg19/bed/clinPred/{a,c,g,t}.color.bb /gbdb/hg19/clinPred/