wget http://hgdownload.soe.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeAwgDnaseMasterSites/wgEncodeAwgDnaseMasterSites.bed.gz

gunzip *.gz

wget http://hgdownload.soe.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeAwgDnaseMasterSites/wgEncodeAwgDnaseMasterSources.tab

awk -v OFS="\t" '{print $1,$2,$3,$1":"$2"-"$3"*"$8,$5,"+"}' wgEncodeAwgDnaseMasterSites.bed > encode_DNAse_5.bed

liftOver -multiple encode_DNAse_5.bed ../lift/hg19_to_hg38reps.over.chain encode_DNAse_5_hg38reps.bed encode_DNAse_5_hg38reps.unmapped

awk -v OFS="\t" '{split($4, a, "*"); {print $1,$2,$3,a[1],$5,"+",a[2]}}' encode_DNAse_5_hg38reps.bed > temp.bed

awk -v OFS="\t" '{split($7, a, ","); for(i in a) { if (a[i] ~/^[0-9]+$/ ){print $1,$2,$3,$4,$5,"+",a[i]}}}' temp.bed | sort -k 7b,7 > encode_DNAse_7_hg38reps.bed

sort -k1b,1 wgEncodeAwgDnaseMasterSources.tab > DNAse_key.tab

join -1 1 -2 7 DNAse_key.tab encode_DNAse_7_hg38reps.bed | awk -v OFS="\t" '{print $3,$4,$5,$6,$7,$8, $2}' > encode_DNAse_7_hg38reps_named.bed

mv encode_DNAse_7_hg38reps_named.bed ~/hive/jferna10/RepeatBrowserHub/hg38reps/wgEncodeAwgDnaseMasterSites

awk -v OFS="\t" '{print $1,$2,$3,$4,$5,$6 >> "encode_DNAse_6_" $7 ".bed"}' encode_DNAse_7_hg38reps_named.bed

mv encode_DNAse_7_hg38reps_named.bed encode_DNAse_7_hg38reps_named.bak

ls *.bed | cut -f 1 -d"."| while read i; do bedSort $i.bed $i.bed ; bedtools genomecov -bg -split -i $i.bed -g ../hg38reps.sizes > temp.bg; bedGraphToBigWig temp.bg ../hg38reps.sizes $i.bw; done