Regexp : 230 wallclock secs (229.86 usr + 0.06 sys = 229.92 CPU) Index : 22 wallclock secs (21.47 usr + 0.01 sys = 21.48 CPU) Merged : 663 wallclock secs (663.73 usr + 0.17 sys = 663.90 CPU) #### use strict; use Bio::SeqIO; use Benchmark; use Regexp::Assemble; use Carp; my $seqio = Bio::SeqIO->new( -file => "chrY.fa.masked", -format => "fasta" ); my $seq = $seqio->next_seq(); my $sequence = $seq->seq(); my @strings = ( 'CACGTG', 'GTGCAC' ); my $t0 = new Benchmark; for (1..100) { foreach my $string (@strings) { my $len = length($string); while ($sequence =~ /$string/g) { my $val = pos($sequence) - $len; } } } my $t1 = new Benchmark; my $t2 = new Benchmark; for (1..100) { foreach my $string (@strings) { my $pos = 0; my $len = length($string); while ( ($pos = index($sequence, $string, $pos)) >= 0 ) { my $val = substr($sequence, $pos, $len); $pos += $len; } } } my $t3 = new Benchmark; my $t4 = new Benchmark; for (1..100) { my $ra = Regexp::Assemble->new(); $ra->add(@strings); while ( $sequence =~ /$ra/g) { my $val = pos($sequence) - 6; } } my $t5 = new Benchmark; my $td1 = timediff($t1, $t0); my $td2 = timediff($t3, $t2); my $td3 = timediff($t5, $t4); print 'Regexp : ', timestr($td1), "\n"; print 'Index : ', timestr($td2), "\n"; print 'Merged : ', timestr($td3), "\n";