http://qs1969.pair.com?node_id=377106


in reply to how to merge the files of DNA sequences?

Please read this documentation to help you learn: perlfunc, perlretut, perlreftut, perlre.
#!/usr/bin/perl use strict; use warnings; my %sequences; # read the input files, passing in a filename and # a reference to the sequences hash read_file("file1", \%sequences); read_file("file2", \%sequences); # write the output file, passing in a filename and # a reference to the sequences hash write_file("file3", \%sequences); sub read_file { my $filename = shift; my $seqref = shift; open SEQFILE, "<$filename" or die "can't open $filename: $!"; # use greater-than for record separator # see perldoc perlvar local $/ = ">"; while(my $line = <SEQFILE>) { # the data will match a word, followed by a # newline, followed by another word # see perldoc perlretut and perlre if ($line =~ m/(\w+)\n(\w+)/s) { # the first word captured is the name my $name = $1; # the second word captured is the sequence my $sequence = $2; # add the sequence on to what ever is # already there $seqref->{$name} .= $sequence; } } close SEQFILE; } sub write_file { my $filename = shift; my $seqref = shift; open OUTPUT, ">$filename" or die "can't open $filename: $!"; # write the sequences hash to the output file for my $key (sort keys %{$seqref}) { print OUTPUT ">$key\n$seqref->{$key}\n" or die "can't write: $!"; } close OUTPUT or die "can't close $filename: $!"; } __END__