Created
May 15, 2013 21:00
-
-
Save ivan-krukov/5587337 to your computer and use it in GitHub Desktop.
Solution to Rosalind CORR problem
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env perl | |
use v5.14; | |
use warnings; | |
sub hamming { | |
my @a = split "", shift; | |
my @b = split "", shift; | |
my $distance = 0; | |
for (my $n = 0; $n < scalar(@a); $n++) { | |
unless (($a[$n]) eq ($b[$n])) { | |
$distance++; | |
} | |
} | |
return $distance; | |
} | |
sub revcomp { | |
my $rc = reverse(shift); | |
$rc =~ tr/ACTG/TGAC/; | |
return $rc; | |
} | |
my %bins = (); | |
while (<>) { | |
unless (/>.*/) { | |
chomp; | |
my $seq = $_; | |
if (exists $bins{revcomp($seq)}) { | |
$bins{revcomp($seq)} ++; | |
} else { | |
$bins{$seq} ++; | |
} | |
} | |
} | |
my (@correct, @ambiguous) = (),(); | |
while (my ($key,$value)= each(%bins)) { | |
if ($value >= 2){ | |
push @correct, $key; | |
}else { | |
push @ambiguous, $key; | |
} | |
} | |
my %corrected_reads = (); | |
for my $error (@ambiguous) { | |
for my $seq (@correct) { | |
if (hamming($seq,$error) == 1) { | |
$corrected_reads{$error} = $seq; | |
say "$error->$seq"; | |
last; | |
} | |
if (hamming(revcomp($seq),$error) == 1) { | |
my $rc = revcomp($seq); | |
$corrected_reads{$error}=$rc; | |
say "$error->$rc"; | |
last; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment