b3af5822d95c94932b6d7b7abd93d1078bf251ee braney Mon Oct 30 16:55:40 2023 -0700 changes in response to max review #32416 diff --git src/hg/makeDb/doc/hg38/hprcRearrange.txt src/hg/makeDb/doc/hg38/hprcRearrange.txt index 0b63ed4..587b852 100644 --- src/hg/makeDb/doc/hg38/hprcRearrange.txt +++ src/hg/makeDb/doc/hg38/hprcRearrange.txt @@ -1,56 +1,56 @@ # 2023-08-12 braney VERSION=V1 inversion=hprcArrInv$VERSION duplication=hprcArrDup$VERSION all=hprcArrAll$VERSION -mkdir -p /cluster/data/hg38/bed/hprcArrange$VERSION -cd /cluster/data/hg38/bed/hprcArrange$VERSION +mkdir -p /cluster/data/hg38/bed/hprc/rearrange +cd /cluster/data/hg38/bed/hprc/rearrange # grab the chains -ls /hive/data/genomes/hg38/bed/hprc/reChain/*.chain > chain.lst +ls ../chain/*.chain > chain.lst rm -rf inversions duplications mkdir inversions duplications # make the job that will figure out the inversions and duplications in each assembly while read chain do name=`basename $chain | sed 's?.*chainHprc??' | sed 's/\.chain//'` echo chainArrange $chain $name inversions/$name.txt duplications/$name.txt done < chain.lst > jobs para make jobs # create the inversion bigBed and bigWig -cat inversions/* |sort -k1,1 -k2,2n -k3,3n -k5,5n | bedCollect stdin $inversion.bed -bedToBigBed $inversion.bed /cluster/data/hg38/chrom.sizes $inversion.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+1 +cat inversions/* |sort -k1,1 -k2,2n -k3,3n -k5,5n | bedCollect stdin stdout | awk '{print $0,$5}' > $inversion.bed +bedToBigBed $inversion.bed /cluster/data/hg38/chrom.sizes $inversion.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+3 cat inversions/* | 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 ln -s `pwd`/$inversion.bb /gbdb/hg38/hprcArr$VERSION # create the duplications bigBed and bigWig -cat duplications/* |sort -k1,1 -k2,2n -k3,3n -k5,5n | bedCollect stdin $duplication.bed -bedToBigBed $duplication.bed /cluster/data/hg38/chrom.sizes $duplication.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+1 +cat duplications/* |sort -k1,1 -k2,2n -k3,3n -k5,5n | bedCollect stdin stdout | awk '{print $0,$5}' > $duplication.bed +bedToBigBed $duplication.bed /cluster/data/hg38/chrom.sizes $duplication.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+3 cat duplications/* | sort -k1,1 | bedItemOverlapCount hg38 stdin > $duplication.bedGraph bedGraphToBigWig $duplication.bedGraph /cluster/data/hg38/chrom.sizes $duplication.bw mkdir -p /gbdb/hg38/hprcArr$VERSION rm -f /gbdb/hg38/hprcArr$VERSION/$duplication.* ln -s `pwd`/$duplication.bw /gbdb/hg38/hprcArr$VERSION ln -s `pwd`/$duplication.bb /gbdb/hg38/hprcArr$VERSION # create the sum of duplications and inversions bigBed and bigWig -cat inversions/* duplications/* |sort -k1,1 -k2,2n | bedCollect stdin $all.bed +cat inversions/* duplications/* |sort -k1,1 -k2,2n | bedCollect stdin stdout | awk '{print $0,$5}' > $all.bed bedToBigBed $all.bed /cluster/data/hg38/chrom.sizes $all.bb -as=$HOME/kent/src/hg/lib/chainArrange.as -type=bed9+1 cat inversions/* duplications/* | sort -k1,1 | bedItemOverlapCount hg38 stdin > $all.bedGraph bedGraphToBigWig $all.bedGraph /cluster/data/hg38/chrom.sizes $all.bw mkdir -p /gbdb/hg38/hprcArr$VERSION rm -f /gbdb/hg38/hprcArr$VERSION/$all.* ln -s `pwd`/$all.bw /gbdb/hg38/hprcArr$VERSION ln -s `pwd`/$all.bb /gbdb/hg38/hprcArr$VERSION