view release on metacpan or  search on metacpan

examples/bioperl.pl  view on Meta::CPAN

                  waitenter
                  # PARSING GENBANK RECORDS
                  # -----------------------
                  # to parse genbank files, use
                  # the read_seq() method, or
                  # simply use the '<' command.
                  #
                  # First of all we're going to
                  # take a look at the file
                  # 't/data/test.genbank'
                  # Let's examine the file itself
                  # using the unix command "cat"
                  # (you can use any unix command
                  #  using the ! at the beginning
                  #  of a line)
                  ^!cat t/data/test.genbank
                  waitenter
                  # Ok, you can see this is a
                  # typical file of genbank records.
                  # Let's get the first sequence
                  # from the file
                  ^<t/data/test.genbank
                  waitenter
                  # we have parsed the first
                  # record of the file, and placed
                  # the sequence object into
                  # the variable $seq
                  #
                  # if you are familiar with perl
                  # objects and the bioperl object
                  # model, you can interact with
                  # the object; for instance, to
                  # display the residues we use the
                  # seq() method like this:
                  ^print $seq->seq()
                  waitenter
                  #
                  # we can cycle through all the
                  # sequences in the file using
                  # the ',' command.
                  ^,
                  waitenter
                  # this fetched the second sequence
                  # and placed it in the $seq variable
                  #
                  # we can change the output format
                  # by setting the 'outformat' parameter
                  # like this:
                  ^+outformat fasta
                  ^,
                  waitenter
                  # now the sequences are output in
                  # fasta format
                  # to change to embl format:
                  ^+outformat embl
                  ^,
                  waitenter
                  # we can also fetch _all_ seqs from
                  # a file; for this example we will
                  # use t/data/swiss.dat, which is in
                  # swiss format. usually bioperl can guess
                  # the file format from the file extension
                  # but this isn't possible here, so we
                  # must help by setting the input format:
                  ^+format swiss
                  # now lets get all the sequences, like this:
                  ^<*t/data/swiss.dat
                  waitenter
                  # typing <* is equivalent to
                  # using the read_seqs() function,
                  # like this:
                  ^read_seqs('t/data/swiss.dat')
                  waitenter
                  # we now have all the sequences in
                  # the array @seqs
                  # we can write these all out as fasta
                  ^+outformat fasta
                  ^>*
                  # we can also write these out to a file:
                  ^>*myfile.tmp
                  ^!cat myfile.tmp
                  #
                  # RANDOM ACCESS OF FASTA FILES
                  # END
                  +echo 0
                  %$options = %keep
                 ]);

        @lines = 
          map {
              s/^ *//;
              $_;
          } @lines;
    }

    sub error {
        if ($error) {
            print "Error:\n$error";
        }
        else {
            print "No errors have been reported\n";
        }
    }

    sub fmt {
        $options->{format} = shift if @_;
        print "format=$options->{format}\n";
    }

    # should this move to Bio::Perl ?
    sub seqio {
        my $filename = shift;
        $options->{format} = shift if @_;

        if( !defined $filename ) {
            warn "read_sequence($filename) - usage incorrect";
        }

        if( defined $options->{format} ) {
            $seqio = Bio::SeqIO->new( '-file' => $filename, '-format' => $options->{format});
        } else {