人类基因组的外显子区域到底有多长

ftp://ftp.ncbi.nlm.nih.gov/pub/CCDS/current_human/CCDS.current.txt

#!usr/bin/perl open(FILE,"CCDS.CURRENT.TXT");while(){

next if /^#/;

@F=split;

/\[(.*?)\]/;#匹配到[]的任意内容

@tmp=split/,/,$1;

foreach(@tmp){

$_=~s/-/\t/;

print "$F[2]\t$F[6]\t$F[0]\t$_\n";}

}

结果

#!usr/bin/perl open FH,"norm.txt";while(){

chomp;

@F=split;

foreach ($F[3]..$F[4]){

$hash{"$F[2]:$_"}=1;}}

close FH;

$tmp++ foreach keys %hash;

print "$tmp\n";