56332b7995bf6075d07d88b04e5675c247725892
braney
  Tue Oct 17 16:21:18 2023 -0700
flesh out the indel tracks

diff --git src/hg/makeDb/doc/hg38/hprcInDel.txt src/hg/makeDb/doc/hg38/hprcInDel.txt
index 3176b77..9df9e33 100644
--- src/hg/makeDb/doc/hg38/hprcInDel.txt
+++ src/hg/makeDb/doc/hg38/hprcInDel.txt
@@ -1,36 +1,57 @@
 VERSION=V1
 inserts=hprcInserts$VERSION
+insertsLarge=hprcInsertsLarge$VERSION
 deletions=hprcDeletions$VERSION
+deletionsLarge=hprcDeletionsLarge$VERSION
 double=hprcDouble$VERSION
+doubleLarge=hprcDoubleLarge$VERSION
 
 cd /cluster/data/hg38/bed/hprc/inDels
 
 rm -rf topLevel
 mkdir topLevel
 for i in ../chain/*.chain; do f=`basename $i .chain`;echo netChainSubset ../net/$f.net $i topLevel/$f.chain -type=top; done > subset.jobs
 para make subset.jobs
 
 rm -rf indels
 mkdir indels
 for chain in topLevel/*.chain; do 
 name=`basename $chain | sed 's?.*chainHprc??' | sed 's/\.chain//'`
 echo chainInDel $chain $name indels/$name.txt
 done > indel.jobs
 para make indel.jobs
 
-sort -k1 -k2,2n indels/* | awk '{if (($3 > $2) && ($5 == 0)) print}' | bedCollect stdin stdout | awk '{if ($5 > 1) print} ' > $inserts.bed
-
+sort -S 50G -k1,1 -k2,2n -k3,3n -k5,5n indels/* > sortIndels.bed
+awk '{if (($3 > $2) && ($5 == 0)) print}' sortIndels.bed > inserts.bed
+awk '{if (($3 - $2 < 20)) print}' inserts.bed | bedCollect -exact stdin $inserts.bed
 bedToBigBed  $inserts.bed /cluster/data/hg38/chrom.sizes $inserts.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+1
-
-#cat indels/* | sort -k1,1 | bedItemOverlapCount hg38 stdin > $inversion.bedGraph
-#bedGraphToBigWig $inversion.bedGraph /cluster/data/hg38/chrom.sizes $inversion.bw
-#mkdir -p /gbdb/hg38/hprcArr$VERSION
-#rm -f  /gbdb/hg38/hprcArr$VERSION/$inversion.*
-#ln -s `pwd`/$inversion.bw /gbdb/hg38/hprcArr$VERSION
+rm -f  /gbdb/hg38/hprcArr$VERSION/$inserts.bb
 ln -s `pwd`/$inserts.bb /gbdb/hg38/hprcArr$VERSION
 
-sort -k1 -k2,2n indels/* | awk '{if (($3 == $2) && ($5 != 0)) print}' | bedCollect stdin stdout | awk '{if ($5 > 1) print} ' > $deletions.bed
+awk '{if (($3 - $2 >= 20)) print}' inserts.bed | bedCollect -exact stdin $insertsLarge.bed
+bedToBigBed  $insertsLarge.bed /cluster/data/hg38/chrom.sizes $insertsLarge.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+1
+rm -f  /gbdb/hg38/hprcArr$VERSION/$insertsLarge.bb
+ln -s `pwd`/$insertsLarge.bb /gbdb/hg38/hprcArr$VERSION
 
-
-bedToBigBed  $deletions.bed /cluster/data/hg38/chrom.sizes $deletions.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+1
+awk '{if ($3 == $2) print}' sortIndels.bed > deletes.bed
+awk '{if ($5 < 20) print}' deletes.bed | bedCollect -exact stdin $deletions.bed
+bedToBigBed  $deletions.bed /cluster/data/hg38/chrom.sizes $deletions.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+2
+rm  -f /gbdb/hg38/hprcArr$VERSION/$deletions.bb
 ln -s `pwd`/$deletions.bb /gbdb/hg38/hprcArr$VERSION
+
+awk '{if ($5 >= 20) print}' deletes.bed | bedCollect -exact stdin $deletionsLarge.bed
+bedToBigBed  $deletionsLarge.bed /cluster/data/hg38/chrom.sizes $deletionsLarge.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+2
+rm  -f /gbdb/hg38/hprcArr$VERSION/$deletionsLarge.bb
+ln -s `pwd`/$deletionsLarge.bb /gbdb/hg38/hprcArr$VERSION
+
+awk '{if (($3 > $2) && ($5 != 0)) print}' sortIndels.bed > double.bed
+awk '{if (($3 - $2 < 20) && ($5 < 20)) print}' double.bed | bedCollect -exact stdin $double.bed
+bedToBigBed  $double.bed /cluster/data/hg38/chrom.sizes $double.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+2
+rm  -f /gbdb/hg38/hprcArr$VERSION/$double.bb
+ln -s `pwd`/$double.bb /gbdb/hg38/hprcArr$VERSION
+
+awk '{if (($3 - $2 >= 20) || ($5 >= 20)) print}' double.bed | bedCollect -exact stdin $doubleLarge.bed
+bedToBigBed  $doubleLarge.bed /cluster/data/hg38/chrom.sizes $doubleLarge.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+2
+rm  -f /gbdb/hg38/hprcArr$VERSION/$doubleLarge.bb
+ln -s `pwd`/$doubleLarge.bb /gbdb/hg38/hprcArr$VERSION
+