use strict; use warnings; my $seq = 'GAATGTTTTAGCAATCTCTTTCTGTC' . 'ATGAATCCATGGCAGTGACCATACTAAT' . 'GGTGACTGCCATTGATGGAGGGAGACACA'; my $word = 'CTGGATAAGAATGTTTTAGCAATCTCTT'; print slidingMatch($seq, $word); sub slidingMatch { my ($seq, $word) = @_; return "Complete match at $-[1]\n" if $seq =~ /($word)/; my @bestMatch; # Try matching start my $str = substr $seq, 0, 3; my $wordLen = length $word; while ($word =~ /$str/g) { my $tailLen = length ($word) - (my $start = $-[0]); my $subWord = substr ($word, $wordLen - $tailLen); next if $seq !~ m/^$subWord/; @bestMatch = ($start, $tailLen); last; } # Try matching end my $rword = reverse $word; my $rseq = reverse $seq; $str = substr $rseq, 0, 3; while ($rword =~ /$str/g) { my $tailLen = length ($rword) - (my $start = $-[0]); last if @bestMatch && $tailLen < $bestMatch[1]; my $subWord = substr ($rword, $wordLen - $tailLen); next if $rseq !~ m/^$subWord/; @bestMatch = (length ($seq) - $tailLen, $tailLen); last; } return "Partial match found at $bestMatch[0] for $bestMatch[1] characters\n" if @bestMatch; return "No match found for $word in $seq\n"; }