9e87a928af4260e37c2054af239b6b411058fd7e kate Thu Jun 4 11:24:29 2020 -0700 Adding make docs for ENCODE CCRE tracks. refs #24668 diff --git src/hg/makeDb/doc/mm10.txt src/hg/makeDb/doc/mm10.txt index 2476208..819c8e3 100644 --- src/hg/makeDb/doc/mm10.txt +++ src/hg/makeDb/doc/mm10.txt @@ -17782,15 +17782,56 @@ # real 50m20.639s cat fb.canFam4.chainMm10Link.txt # 772902855 bases of 2481941580 (31.141%) in intersection cat fb.canFam4.chainSynMm10Link.txt # 737924732 bases of 2481941580 (29.732%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev canFam4 mm10 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 173m38.016s cat fb.canFam4.chainRBest.Mm10.txt # 740357755 bases of 2481941580 (29.830%) in intersection ############################################################################## +# ENCODE Registry of Candidate cis-Regulatory Elements +# +# 2020-05-12 kate +# +# From ENCODE 3 Data Analysis Center at U Mass Med Center (Zlab) +# Data contacts: Henry Pratt, Jill Moore, Zhiping Weng PI +# +# RM #24668 +# +# Download BED file (hosted on their integrative hub) + +cd /hive/data/outside/encode3/ccre +mkdir mouse +cd mouse +wget http://gcp.wenglab.org/hubs/integrative1/data/mm10/cta/mm10-ccres.bigbed + +### +# Add scores +wget -nd https://users.wenglab.org/moorej3/mouse-maxz-dnase.txt.gz +gunzip Mouse-maxZ-DNase.txt.gz + +sort Mouse-maxZ-DNase.txt > Mouse-maxZ-DNase.sorted.txt +# noting that order of accessions in score file doesn't match bed file ;-( +sort -k 4 mm10-ccREs.bed > mm10-ccREs.sorted.bed +paste mm10-ccREs.sorted.bed Mouse-maxZ-DNase.sorted.txt > ccres.prescored.bed +# sanity check ids match + +# score using zscore, min(zscore*100),1000), and reformat +awk '{OFS="\t"; print $1, $2, $3, $4, ($13>10)? 1000 : int($13 * 100), $6, $7, $8, $9, $10, $13}' \ + ccres.prescored.bed | bedSort stdin ccres.scored.bed +set f = encodeCcreCombined + +# Reformat to add fields for filtering and mouseover, etc. +perl ../makeCcreCombined.pl < ccres.scored.bed > $f.bed +bedToBigBed -tab -type=bed9+6 -as=../$f.as $f.bed /hive/data/genomes/mm10/chrom.sizes $f.bb +mkdir -p /gbdb/mm10/encode3/ccre +ln -s `pwd`/$f.bb /gbdb/mm10/encode3/ccre + + +############################################################################## +