1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
#!/usr/bin/perl
# Creates a fasta file with unique peptides from two peptide fasta input files
# Deletes redundant entries. Multiplicity information is taken from the first
# of two fasta input files.
my $usage = "joinPeptides.pl in1.fa in2.fa > out.fa\n\nRead script head comments for futher documentation!\n\n";
if(@ARGV!=2){print STDERR $usage; exit -1;}
my $in1 = $ARGV[0];
my $in2 = $ARGV[1];
my %peptides = ();
my $header;
my $maxLen = 100;
open(IN, "<", $in1) or die("Could not open file $in1!\n");
while ( <IN> ) {
chomp;
if($_=~m/^>/){
$header = $_;
}else{
if(length($_) > $maxLen){
print STDERR "The peptide $_ is longer $maxLen. Aborting.\n";
exit -1;
}
while($_=~m/-/){ # delete weird dashes in sequences
$_ = s/-//;
}
if(not(exists($locHash{$_}))){
$peptides{$_} = "$header";
}
}
}
close IN or die("Could not close file $in1!\n");
open(IN2, "<", $in2) or die("Could not open file $in2!\n");
while( <IN2>){
chomp;
if($_=~m/^>/){
$header = $_;
}else{
if(length($_) > $maxLen){
print STDERR "The peptide $_ is longer $maxLen. Aborting.\n";
exit -1;
}
while($_=~m/-/){ # delete weird dashes in sequences
$_ = s/-//;
}
if(not(exists($locHash{$_}))){
$peptides{$_} = "$header";
}
}
}
close IN2 or die("Could not close file $in2!\n");
# print unique fasta file
while ( ($k,$v) = each %peptides ) {
print "$v\n";
print "$k\n";
}
|
