40a49b0eb0c44d5a5fd20fb43468405b12d0390c gperez2 Tue Jun 29 16:21:53 2021 -0700 lastz chainNet per user request hg19 gorGor6, refs #27757 diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt index aa0c1bc..2ab3ad1 100644 --- src/hg/makeDb/doc/hg19.txt +++ src/hg/makeDb/doc/hg19.txt @@ -34530,15 +34530,94 @@ ############################################################################## # Add Revel track, Max, Thu Apr 15 03:33:49 PDT 2021 cd /hive/data/genomes/hg19/bed/revel aria2c https://rothsj06.u.hpc.mssm.edu/revel_grch38_all_chromosomes.csv.zip unzip revel_grch38_all_chromosomes.csv.zip # make sure that no weird chroms and no weird multi-nucleotide changes cat revel_grch38_all_chromosomes.csv | tr ',' '\t' | cut -f5 | grep -v alt | awk '{print length($1)}' | uniq > lens.tmp & cut -d, revel_grch38_all_chromosomes.csv -f1 | uniq | sort | uniq -c > chroms.tmp & pigz revel_grch38_all_chromosomes.csv time python revelToWig.py revel_grch38_all_chromosomes.csv.gz hg19 wigToBigWig t.wig ../../chrom.sizes t.bw & wigToBigWig c.wig ../../chrom.sizes c.bw & wigToBigWig a.wig ../../chrom.sizes a.bw & wigToBigWig g.wig ../../chrom.sizes g.bw & ############################################################################## +# LASTZ human/hg19 Gorilla/gorGor6 - (DONE - 2021-06-28 - Hiram) + mkdir /hive/data/genomes/hg19/bed/lastzGorGor6.2021-06-28/ + cd /hive/data/genomes/hg19/bed/lastzGorGor6.2021-06-28/ + + printf '# human vs gorilla +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz +BLASTZ_T=2 +BLASTZ_O=600 +BLASTZ_E=150 +BLASTZ_M=254 +BLASTZ_K=4500 +BLASTZ_Y=15000 +BLASTZ_Q=/hive/data/staging/data/blastz/human_chimp.v2.q +# A C G T +# A 90 -330 -236 -356 +# C -330 100 -318 -236 +# G -236 -318 100 -330 +# T -356 -236 -330 90 + +# TARGET: Human hg19 +SEQ1_DIR=/hive/data/genomes/hg19/hg19.2bit +SEQ1_LEN=/hive/data/genomes/hg19/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_IN_CONTIGS=0 + +# QUERY: gorilla gorGor6 +SEQ2_DIR=/hive/data/genomes/gorGor6/gorGor6.2bit +SEQ2_LEN=/hive/data/genomes/gorGor6/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=50 + +BASE=/hive/data/genomes/hg19/bed/lastzGorGor6.2021-06-28 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ + -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > do.log 2>&1 + # real 113m7.350s + + cat fb.hg19.chainGorGor6Link.txt + # 2874362387 bases of 2991710746 (96.078%) in intersection + + cat fb.hg19.chainSynGorGor6Link.txt + # 2854800888 bases of 2991710746 (95.424%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg19 gorGor6) > rbest.log 2>&1 & + # real 67m18.231s + + sed -e 's/^/ # /;' fb.hg19.chainRBest.GorGor6.txt + # 2691356356 bases of 2991710746 (89.960%) in intersection + + # running the swap + mkdir /hive/data/genomes/gorGor6/bed/blastz.hg19.swap + cd /hive/data/genomes/gorGor6/bed/blastz.hg19.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/hg19/bed/lastzGorGor6.2021-06-28/DEF \ + -swap -syntenicNet -workhorse=hgwdev \ + -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 & + # real 69m32.058s + + cat fb.gorGor6.chainHg19Link.txt + 2735990533 bases of 2999027915 (91.229%) in intersection + + cat fb.gorGor6.chainSynHg19Link.txt + 2726237067 bases of 2999027915 (90.904%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` gorGor6 hg19) > rbest.log 2>&1 & + # real 70m15.001s + + sed -e 's/^/ # /;' fb.gorGor6.chainRBest.Hg19.txt + # 2694784811 bases of 2999027915 (89.855%) in intersection + +##############################################################################