|
3
|
1 #!/usr/bin/perl
|
|
|
2
|
|
|
3 use strict;
|
|
|
4
|
|
|
5 my $indir = $ARGV[0];
|
|
|
6 my $matrix = $ARGV[1];
|
|
|
7 my $out = $ARGV[2];
|
|
|
8 my $strain_names = $ARGV[3];
|
|
|
9
|
|
|
10 my %strains_of_gb;
|
|
|
11 open(F,$strain_names);
|
|
|
12 while(<F>){
|
|
|
13 my $line = $_;
|
|
|
14 $line =~s/\n//g;$line =~s/\r//g;
|
|
|
15 my ($gb,$strain) = split(/\t/,$line);
|
|
|
16 $strains_of_gb{$gb} = $strain;
|
|
|
17 }
|
|
|
18 close(F);
|
|
|
19
|
|
|
20
|
|
|
21 my %corr;
|
|
|
22 open(D,"ls $indir/*rmdup.gff |");
|
|
|
23 while(<D>){
|
|
|
24 my $file = $_;
|
|
|
25 open(F,"$file");
|
|
|
26 while(<F>){
|
|
|
27 my @infos = split(/\t/,$_);
|
|
|
28 if ($infos[2] eq 'CDS' && /ID=([^;]*);.*protein_id=([^;]*);/){
|
|
|
29 my $id = $1;
|
|
|
30 my $protid = $2;
|
|
|
31 $corr{$id} = $protid;
|
|
|
32 }
|
|
|
33 }
|
|
|
34 close(F);
|
|
|
35 }
|
|
|
36 close(D);
|
|
|
37
|
|
|
38 my $cl_num = 0;
|
|
|
39 my $nb_strains = 1;
|
|
|
40 open(O,">$out");
|
|
|
41 open(F,$matrix);
|
|
|
42 my $firstline = <F>;
|
|
|
43 $firstline =~s/\n//g;$firstline =~s/\r//g;
|
|
|
44 my @infos = split(/\t/,$firstline);
|
|
|
45 print O "ClutserID";
|
|
|
46 print U "ClutserID";
|
|
|
47 print M "Gene";
|
|
|
48 for (my $j=1; $j <= $#infos; $j++){
|
|
|
49 my $gbfile = $infos[$j];
|
|
|
50 $gbfile =~s/\"//g;
|
|
|
51 $gbfile =~s/\.gb\.filt//g;
|
|
|
52 $gbfile =~s/\.gb\.rmdup//g;
|
|
|
53
|
|
|
54 my $strain = $strains_of_gb{$gbfile};
|
|
|
55 print O "\t".$strain;
|
|
|
56 print U "\t".$strain;
|
|
|
57 print M "\t".$strain;
|
|
|
58 $nb_strains++;
|
|
|
59 }
|
|
|
60 print O "\n";
|
|
|
61 while(<F>){
|
|
|
62 print O $_;
|
|
|
63 }
|
|
|
64 close(F);
|
|
|
65 close(O);
|
