加染色体号的三部曲

hg19参考基因组这注释文件加上gtf
sed -E ‘s/^>([0-9]+|X|MT) dna:chromosome chromosome:GRCh37:(\1):1:([0-9]+)😦[0-9]+) REF/>chr\1 dna:chromosome chromosome:GRCh37:chr\1:\2:\3:\4 REF/’ hg19N.fa >hg19.fa

sed -i ‘s/>Y dna:chromosome chromosome:GRCh37:Y:2649521:59034049:1 REF/>chrY dna:chromosome chromosome:GRCh37:chrY:2649521:59034049:1 REF/’ hg19.fa

sed -E ‘s/^([0-9]+|X|Y|MT)/chr&/’ hg19N.gtf>hg19.gtf

grep -P ‘s/^>([0-9]+|X|MT)’ hg19N.gtf |tail

grep -P ‘^([0-9]+|X|Y|MT)+’ hg19N.gtf |tail

Linux shell字符串截取与拼接https://blog.csdn.net/u013485792/article/details/70241377?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522159801522019724846401658%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fall.%2522%257D&request_id=159801522019724846401658&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2_allfirst_rank_ecpm_v3~pc_rank_v3-2-70241377.pc_ecpm_v3_pc_rank_v3&utm_term=linux%E6%88%AA%E5%8F%96%E8%B7%AF%E5%BE%84%E6%9C%80%E5%90%8E%E7%9A%84%E4%B8%80%E4%B8%AA%E5%AD%97%E6%AE%B5+substr&spm=1018.2118.3001.4187
加染色体号的三部曲：：
加一列
for i in {1…18}
do
awk 'BEGIN{ FS=“\t”;OFS=“\t” } {if($3==“1”){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad > ./ontad/chr$i-1
awk 'BEGIN{ FS=“\t”;OFS=“\t” } {if($3!=“1” && $3!=“0” ){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad >./ontad/chr$i-2
done

for i in X Y
do
awk '{if($3==“1”){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad > ./ontad/chr$i-1
awk '{if($3!=“1” && $3!=“0” ){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad >./ontad/chr$i-2
done

加数字
for i in {1…18}
do
cat chr$i-1|seds/chr/chr$i/>chr$i-1catchr$i-2|sed s/chr/chr$i/>chr$i-2
done
for i in X Y
do
cat chr$i-1|seds/chr/chr$i/>chr$i-1catchr$i-2|sed s/chr/chr$i/>chr$i-2
done

综合起来
for i in {1…18}
do
awk 'BEGIN{ FS=“\t”;OFS=“\t” } {if($3==“1”){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad |cat| sed s/chr/chr$i/g>./ontad/chr$i-1
awk 'BEGIN{ FS=“\t”;OFS=“\t” } {if($3!=“1” && $3!=“0” ){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad |cat|sed s/chr/chr$i/g>./ontad/chr$i-2
done

for i in X Y
do
awk '{if($3==“1”){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad|cat| sed s/chr/chr$i/g>./ontad/chr$i-1
awk '{if($3!=“1” && $3!=“0” ){print “chr”,KaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲}' OnTAD_NC_p…i.tad |cat|sed s/chr/chr$i/g>./ontad/chr$i-2
done
。。。。。。。。。。。。。。。。。。。。。。。。

###ls * 是死循环，一定要注意在文件夹内不要生成什么文件，或者用ls **？？？的具体代替。
for i in ls ontad/*
do
i=${i##*/}
echo $imkdir-p./ou/$i
mkdir -p ./ontadsort
sort-bed ontad/$i>ontadsort/$i.sort

for j in ls K562_TF_chip-seq_no_rep/*
do
j=${j##*/}
echo $j
mkdir -p ./K562_TF_chip-seq_no_repsort
awk 'BEGIN{FS=" “;OFS=”\t"}{$1=$1;printKaTeX parse error: Expected 'EOF', got '}' at position 2: 0}̲' K562_TF_chip…j > K562_TF_chip-seq_no_repsort/$j.tmpsort-bedK562_T{F}_{c}hip-se{q}_n{o}_{r}epsort/$j.tmp>K562_TF_chip-seq_no_repsort/$j.sortbedops-e1ontadsort/$i.sort K562_TF_chip-seq_no_repsort/$j.sort>./ou/$i/KaTeX parse error: Expected group after '_' at position 4: {i}_̲{j}
done
done