b4fd34e71f94b2847253ef2b20cd3d8aa2acaa24
jcasper
  Mon May 19 10:31:30 2025 -0700
Fix a few issues with MaveDB json parse (score bounds, item count display for
cells with multiple values.  Also committing trackDb and doc for a native version, refs #31812

diff --git src/hg/makeDb/doc/hg38/hg38.txt src/hg/makeDb/doc/hg38/hg38.txt
index fcbc04a4d06..d57aacaaa4b 100644
--- src/hg/makeDb/doc/hg38/hg38.txt
+++ src/hg/makeDb/doc/hg38/hg38.txt
@@ -7395,16 +7395,54 @@
 ## $ ll /hive/data/outside/cosmic/ucsc_export*.bed.gz
 ## rw-rw-r- 1 max protein 198M Jan 14 16:15
 ## /hive/data/outside/cosmic/ucsc_export.v101.hg19.bed.gz
 ## rw-rw-r- 1 max protein 198M Jan 14 13:35
 ## /hive/data/outside/cosmic/ucsc_export.v101.hg38.bed.gz
 
 mkdir -p /hive/data/outside/cosmic/{hg19,hg38}/v101
 
 cd /hive/data/outside/cosmic/hg38/v101
 zcat /hive/data/outside/cosmic/ucsc_export.v101.hg38.bed.gz  | awk -F'\t' -v OFS="\t" '{ print $1, $2, $3, $7, 0, $6, $4, $5, $8 }' | sort -k1,1 -k2,2n > cosmic.bed
 bedToBigBed -type=bed6+3 -as=/hive/data/outside/cosmic/hg38/v98/cosmic.as cosmic.bed /hive/data/genomes/hg38/chrom.sizes cosmic.bb -tab
 cd /gbdb/hg38/cosmic/
 ln -s /hive/data/outside/cosmic/hg38/v98/cosmic.bb cosmicv98.bb
 ln -sf /hive/data/outside/cosmic/hg38/v101/cosmic.bb
 #Updated human/hg38/trackDb.ra and human/hg38/cosmicMuts.html
+
+#########################################################################
+# MaveDB (04-14-2025) Jonathan
+
+# MaveDB data for this track was taken from mappings they created and linked to
+# from https://github.com/VariantEffect/dcd_mapping2.  More specifically, from
+# https://mavedb-mapping.s3.us-east-2.amazonaws.com/mappings.tar.gz.
+
+mkdir -p /hive/data/outside/mavedb/dcd_mappings
+cd /hive/data/outside/mavedb/dcd_mappings
+wget https://mavedb-mapping.s3.us-east-2.amazonaws.com/mappings.tar.gz
+tar xzvf mappings.tar.gz
+
+mkdir -p /hive/data/genomes/hg38/bed/mavedb/2025_04_12
+cd /hive/data/genomes/hg38/bed/mavedb/2025_04_12
+
+# We skip 00000053-a-1.json because it's a very large dataset that also only
+# contains haplotype data, which we don't have a display for.
+time for fil in `grep -l hgvs.p /hive/data/outside/mavedb/dcd_mappings/mappings/*.json`;
+    do if [[ "$fil" == *"00000053-a-1.json" ]]; then continue; fi
+    echo $fil
+    perl ~/kent/src/oneShot/parseMave/parseMave.pl < $fil >> combined.bed;
+    done
+
+bedSort combined.bed combined.bed
+cp $HOME/kent/src/hg/lib/heatmap.as .
+# edit heatmap.as to add these fields to the end
+#    lstring maveLink; "Link to MaveDB"
+#    lstring abstractText; "Abstract"
+#    lstring methodText; "Methods"
+
+bedToBigBed -type=bed12+ -tab -as=heatmap.as combined.bed /hive/data/genomes/hg38/chrom.sizes all_mave.bb
+
+mkdir -p /gbdb/hg38/maveDB
+cd /gbdb/hg38/maveDB
+ln -s /hive/data/genomes/hg38/bed/mavedb/2025_04_12/all_mave.bb
+
+
 #########################################################################