|
10
|
1 #!/usr/bin/perl -w
|
|
|
2 ###
|
|
|
3 ###Yufei LUO
|
|
|
4 ###
|
|
|
5
|
|
|
6 use strict;
|
|
|
7
|
|
|
8 my $in_file = $ARGV[0];
|
|
|
9 my $out_file = $ARGV[1];
|
|
|
10 my $sort_type = $ARGV[2]; # n(umeric) or a(lphanumeric)
|
|
|
11 my ($line,$ID,$nbOverlaps,%hash);
|
|
|
12
|
|
|
13 open(IN, $in_file);
|
|
|
14 while ($line = <IN>){
|
|
|
15 chomp($line);
|
|
|
16 $line=~s/\t/|/g;
|
|
|
17 my @part=split(/\|/,$line);
|
|
|
18 my @split=split(";",$part[$#part]);
|
|
|
19 $split[0] =~ m/^(\w+).+$/;
|
|
|
20
|
|
|
21 foreach my $i (@split){
|
|
|
22 if ($i=~m/nbOverlaps=(.+)/){
|
|
|
23 $nbOverlaps=$1;
|
|
|
24 }
|
|
|
25 if ($i=~m/gene_id=(.+)/){
|
|
|
26 $ID=$1;
|
|
|
27 $hash{$ID}=$nbOverlaps;
|
|
|
28 }
|
|
|
29 }
|
|
|
30 }
|
|
|
31 close(IN);
|
|
|
32
|
|
|
33 open(OUT, ">$out_file");
|
|
|
34 foreach my $key ( sort keys %hash) {
|
|
|
35 print OUT "$key\t$hash{$key}\n";
|
|
|
36 }
|
|
|
37 close(OUT);
|
