e941783cbc9cd3ec6af5f75b6969554fba9282e1
hiram
  Thu Apr 29 23:05:28 2021 -0700
adding frames procedure refs #11636

diff --git src/hg/makeDb/doc/hg38/cactus241way.txt src/hg/makeDb/doc/hg38/cactus241way.txt
index 48805f9..95d3fcc 100644
--- src/hg/makeDb/doc/hg38/cactus241way.txt
+++ src/hg/makeDb/doc/hg38/cactus241way.txt
@@ -933,16 +933,81 @@
 ############################################################################
 # pushQ readmine (TBD - 2017-11-07 - Hiram)
 
   cd /usr/local/apache/htdocs-hgdownload/goldenPath/hg38
   find -L `pwd`/cactus241way `pwd`/phastCons241way `pwd`/phyloP241way \
 	/gbdb/hg38/cactus241way -type f \
     > /hive/data/genomes/hg38/bed/cactus241way/downloads/redmine.20216.fileList
   wc -l /hive/data/genomes/hg38/bed/cactus241way/downloads/redmine.20216.fileList
 # 1450 /hive/data/genomes/hg38/bed/cactus241way/downloads/redmine.20216.fileList
 
   cd /hive/data/genomes/hg38/bed/cactus241way/downloads
   hgsql -e 'show tables;' hg38 | grep 241way \
 	| sed -e 's/^/hg38./;' > redmine.20216.table.list
 
 ############################################################################
+## adding frames ( DONE - 2021-04-29 - Hiram )
+
+  mkdir /hive/data/genomes/hg38/bed/cactus241way/frames
+  cd /hive/data/genomes/hg38/bed/cactus241way/frames
+  mkdir genes
+
+  hgsql -N -e "select name,chrom,strand,txStart,txEnd,cdsStart,cdsEnd,exonCount,exonStarts,exonEnds from knownGene" hg38 \
+        | genePredSingleCover stdin stdout | gzip -2c \
+          > genes/hg38.gp.gz
+
+  genePredCheck -db=hg38 genes/hg38.gp.gz
+
+  #  checked: 19328 failed: 0
+
+  ls ../ucscNames | sed -e 's/.maf//;' > chr.list
+  ls genes | sed -e 's/.gp.gz//;' > gene.list
+
+  printf '#!/bin/bash
+
+set -beEu -o pipefail
+
+export C=$1
+export G=$2
+
+cat ../ucscNames/${C}.maf | genePredToMafFrames hg38 stdin stdout \
+  "${G}" genes/${G}.gp.gz | gzip > parts/${C}.${G}.mafFrames.gz
+
+' > runOne
+
+  chmod +x rnOne
+
+  printf '#LOOP
+./runOne $(root1) $(root2) parts/$(root1).$(root2).mafFrames.gz
+#ENDLOOP
+' > template
+
+  gensub2 chr.list gene.list template perl.jobList
+
+  time ($HOME/kent/src/hg/utils/automation/perlPara.pl 4 perl.jobList) \
+    >> do.log 2>&1 &
+
+  tail do.log
+
+# Completed: 454 of 454 jobs
+# CPU time in finished jobs:      91822s    1530.37m    25.51h    1.06d  0.003y
+# Average job time:                 202s       3.37m     0.06h    0.00d
+# Longest finished job:            7570s     126.17m     2.10h    0.09d
+
+  # real    417m27.701s
+
+  time find ./parts -type f | while read F
+do
+    echo "${F}" 1>&2
+    zcat ${F}
+done | sort -k1,1 -k2,2n | gzip -c > cactus241wayFrames.bed.gz
+
+  # real    0m3.178s
+
+  hgLoadMafFrames hg38 cactus241wayFrames cactus241wayFrames.bed.gz
+
+  featureBits -countGaps hg38 cactus241wayFrames
+
+  # 33621579 bases of 3272116950 (1.028%) in intersection
+
+############################################################################