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