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
|
#!/usr/bin/perl -w
##
# colorize_fasta.pl
#
# Convert nucleotide FASTA input to colorspace FASTA output.
# Colorspace versions of nucleotide sequnences are 1 character shorter.
# Names are unchanged. No primer base is given.
#
##
# Given a string in nucleotide space, convert to colorspace.
#
sub colorize($$) {
my ($s, $nucs) = @_;
defined($s) || die;
my %cmap = (
"AA" => "0", "CC" => "0", "GG" => "0", "TT" => "0",
"AC" => "1", "CA" => "1", "GT" => "1", "TG" => "1",
"AG" => "2", "GA" => "2", "CT" => "2", "TC" => "2",
"AT" => "3", "TA" => "3", "CG" => "3", "GC" => "3",
"NA" => ".", "NC" => ".", "NG" => ".", "NT" => ".",
"AN" => ".", "CN" => ".", "GN" => ".", "TN" => ".",
"NN" => "."
);
my %nmap = ("0" => "A", "1" => "C", "2" => "G", "3" => "T", "." => "N");
my $ret = "";
for(my $i = 0; $i < length($s)-1; $i++) {
my $di = uc substr($s, $i, 2);
$di =~ tr/-NnMmRrWwSsYyKkVvHhDdBbXx/N/;
defined($cmap{$di}) || die "Bad dinuc: $di\n";
$ret .= ($nucs ? $nmap{$cmap{$di}} : $cmap{$di});
}
return $ret;
}
while(<>) {
next if /^;/;
next if /^#/;
if(/^>/) {
print $_;
} else {
chomp;
print colorize($_, 0)."\n";
}
}
|
