use strict; use warnings; use List::Util 'shuffle'; # Idea from http://www.perlmonks.org/?node_id=199901 my $input = shift @ARGV; open(IN, '<', $input) or die "Can't read multifasta input genomic DNA file $input : $!\n"; my $destination = $input."_1MBWindow_ListUtilshuffle.fasta"; open(OUT, '>', $destination) or die "Can't write to file $destination: $!\n"; my $window = 1000000; # hard coded for shuffle window to be 1MB i.e 10^6 my ($seq_id, $seq); # process every alternate line with ID (and its corresponding sequence in next line) while (defined($seq_id = ) { if (!defined($seq = ) { last; } chomp $seg_id; chomp $seg; my $final_seq = ''; for (my $i = 1; $i <= length $seq; $i += $window ) { my $s = substr ($seq, $i - 1, $window); my @temp_seq_array = split //, $s; @temp_seq_array = shuffle @temp_seq_array; # using the List::Util module AND Shuffles EACH window!!! my $rand_shuffled_seq = join ('', @temp_seq_array,); $final_seq .= $rand_shuffled_seq; # concatenates the shuffled DNA seq to the 3' end of the previous 1MB fragment } print OUT $seq_id, "\n",$final_seq,"\n"; } close IN; close OUT;