8e2ce67692e814db90b2d2938915712ff9b0ee51
jeltje.van.baren
  Wed Apr 16 18:07:03 2025 -0700
Adding recount3 #34886

diff --git src/hg/makeDb/doc/hg38/recount3.txt src/hg/makeDb/doc/hg38/recount3.txt
new file mode 100644
index 00000000000..daad9e35c06
--- /dev/null
+++ src/hg/makeDb/doc/hg38/recount3.txt
@@ -0,0 +1,61 @@
+
+####################################
+# recount3 intron tracks ticket 34886
+# Jeltje January 2025
+# NOTE: The sra files are so large that the trackDb.ra file needs a maxWindowToDraw limit
+# or else the browser window won't load within the set time
+
+
+cat << _TOEND_ > recount3.as
+table recount3
+"Bed 9+6 file for NCBI orthologs"
+    (
+    string chrom;      "Reference sequence chromosome or scaffold"
+    uint   chromStart; "Start position in chromosome"
+    uint   chromEnd;   "End position in chromosome"
+    string name;       "Short Name of item"
+    uint   score;      "Score from 0-1000"
+    char[1] strand;    "+ or -"
+    uint thickStart;   "Start of where display should be thick"
+    uint thickEnd;     "End of where display should be thick"
+    uint reserved;     "Used as itemRgb as of 2004-11-22"
+    bigint readcount;  "Read count"
+    uint samplecount;  "Sample count"
+    string donor;      "Splice donor"
+    string acceptor;   "Splice acceptor"
+    string url;        "URL"
+    )
+_TOEND_
+
+
+process_dataset() {
+	local dset=$1
+	if [ ! -f "$dset.tsv" ]; then
+	    wget -O $dset.tsv.bgz https://snaptron.cs.jhu.edu/data/$dset/junctions.bgz
+	    bgzip -d $dset.tsv.bgz
+	fi
+	./junctionsToBed.py --junctions $dset.tsv --bed $dset.bed --decorator dec$dset.bed --compilation $dset
+	bedSort $dset.bed $dset.bed
+	bedSort dec$dset.bed dec$dset.bed
+}
+
+for dset in gtexv2 srav3h tcgav2 ccle; do
+	wget https://snaptron.cs.jhu.edu/data/$dset/junctions.bgz
+	zcat junctions.bgz > $dset.tsv 
+	process_dataset $dset &
+done
+wait
+
+toBB() {
+	local dset=$1
+	bedToBigBed -type=bed9+6 -tab -as=recount3.as $dset.bed /hive/data/genomes/hg38/chrom.sizes $dset.bb &
+	bedToBigBed -type=bed12+ -as=/cluster/home/jeltje/kent/src/hg/lib/decoration.as dec$dset.bed /hive/data/genomes/hg38/chrom.sizes dec$dset.bb &
+}
+
+for dset in gtexv2 srav3h tcgav2 ccle; do
+	toBB $dset &
+done
+wait
+
+
+rm *.bed *tsv junctions.bgz