mkdir /hive/data/genomes/hg38/bed/unusualcons/

mkdir /hive/data/genomes/hg38/bed/unusualcons/hars/
mkdir hg19
cd hg19
wget https://docpollard.org/wordpress/wp-content/research/nchaes_merged_hg19.bed
cd ../
mkdir hg38
cd hg38
liftOver ../hg19/nchaes_merged_hg19.bed /hive/data/genomes/hg19/bed/liftOver/hg19ToHg38.over.chain.gz  ../hg38/nchaes_merged_hg38.bed unmapped.txt
bedSort nchaes_merged_hg38.bed  nchaes_merged_hg38.bed
bedToBigBed nchaes_merged_hg38.bed ../../../../chrom.sizes nchaes_merged_hg38.bb
# downloaded Excel table from pollard lab homepage and converted to text using Excel
cut -f1,2,3,4 -d'	' KeoughTableS1.txt | grep -v ^chrom | grep -v ^positive > KeoughTableS1.bed
bedSort KeoughTableS1.bed KeoughTableS1.bed
bedToBigBed KeoughTableS1.bed ../../../chrom.sizes KeoughTableS1.bb

mkdir /hive/data/genomes/hg38/bed/unusualcons/hcondels/
cd /hive/data/genomes/hg38/bed/unusualcons/hcondels/
# from science.abn2253_tables_s1_to_s4.xls created three text files
paste meta.txt mpradeseq.txt > both.txt
~/kent/src/utils/tabToBed/tabToBed both.txt hcondels.bed hcondels.as --bedFields=chrom=hg38_mpra_chr,start=hg38_mpra_start_pos,end=hg38_mpra_end_pos,name=hCONDEL_ID
bedToBigBed hcondels.bed /hive/data/genomes/hg38/chrom.sizes hcondels.bb -tab -type=bed12+ -as=hcondels.as

mkdir /hive/data/genomes/hg38/bed/unusualcons/longhcondels/
cd /hive/data/genomes/hg38/bed/unusualcons/longhcondels/
# converted manually excel Excel in supp2 in https://pmc.ncbi.nlm.nih.gov/articles/PMC3071156/#S2
# fix position mistakes
cat supp2.hg18.bed | tawk '{if ($3<$2) { t=$2; $2=$3; $3=t }; print } ' | less > supp2.hg18.fixed.bed
# lift to hg38
liftOver supp2.hg18.fixed.bed /hive/data/genomes/hg18/bed/liftOver/hg18ToHg38.over.chain.gz supp2.hg38.bed unmapped.txt
# convert
bedSort supp2.hg38.bed supp2.hg38.bed
bedToBigBed supp2.hg38.bed ../../../chrom.sizes hcondels583.bb

mkdir /hive/data/genomes/hg38/bed/unusualcons/ultras/
cd /hive/data/genomes/hg38/bed/unusualcons/ultras/
wget http://genome-test.gi.ucsc.edu/~hiram/hubs/GillBejerano/hg19/hg19.ultraConserved.bb
bigBedToBed hg19.ultraConserved.bb hg19.ultraConserved.bed
liftOver hg19.ultraConserved.bed /hive/data/genomes/hg19/bed/liftOver/hg19ToHg38.over.chain.gz hg38.ultraConserved.bed unmapped.txt
bedToBigBed hg38.ultraConserved.bed ../../../chrom.sizes hg38.ultraConserved.bb

mkdir /hive/data/genomes/hg38/bed/unusualcons/zooUces/
cd /hive/data/genomes/hg38/bed/unusualcons/zooUces/
wget https://cgl.gi.ucsc.edu/data/cactus/zoonomia-2021-track-hub/hg38/zooUCEs.bed.gz
wget https://cgl.gi.ucsc.edu/data/cactus/zoonomia-2021-track-hub/hg38/RoCCs.bigBed
wget https://cgl.gi.ucsc.edu/data/cactus/zoonomia-2021-track-hub/hg38/UNICORNs.bigBed

cd /hive/data/genomes/hg38/bed/unusualcons/haqers/
bedSort haqers.bed haqers.bed 
bedToBigBed haqers.bed ../../../chrom.sizes haqers.bb

# UCNEbase
mkdir /hive/data/genomes/hg38/bed/unusualcons/ucnebase/hg19
cd /hive/data/genomes/hg38/bed/unusualcons/ucnebase/hg19
wget https://epd.expasy.org/ucnebase/data/UCNEs_hg19.bed
# split file manually in vim
mkdir /hive/data/genomes/hg38/bed/unusualcons/ucnebase/hg38
cd /hive/data/genomes/hg38/bed/unusualcons/ucnebase/hg38
liftOver ../hg19/chicken.bed /hive/data/genomes/hg19/bed/liftOver/hg19ToHg38.over.chain.gz  chicken.hg38.bed unmapped.txt
liftOver ../hg19/clusters.bed /hive/data/genomes/hg19/bed/liftOver/hg19ToHg38.over.chain.gz  clusters.bed unmapped.txt
liftOver ../hg19/paralogs.bed /hive/data/genomes/hg19/bed/liftOver/hg19ToHg38.over.chain.gz  paralogs.bed unmapped.txt
for i in *.bed; do bedSort $i $i; bedToBigBed $i ../../../../chrom.sizes `basename $i .bed`.bb; done
