3 # Copyright (C) 2007-2009 Martin A. Hansen.
5 # This program is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU General Public License
7 # as published by the Free Software Foundation; either version 2
8 # of the License, or (at your option) any later version.
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
15 # You should have received a copy of the GNU General Public License
16 # along with this program; if not, write to the Free Software
17 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
19 # http://www.gnu.org/copyleft/gpl.html
22 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
24 # Count sequences from the stream and select only unique sequences.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
32 use Maasha::Biopieces;
36 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
39 my ( $options, $in, $out, %hash, $record, $seq, $rc_seq, $type );
41 $options = Maasha::Biopieces::parse_options(
43 { long => 'complement', short => 'c', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
47 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
48 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
50 while ( $record = Maasha::Biopieces::get_record( $in ) )
52 if ( $record->{ 'SEQ' } ) {
53 $hash{ uc $record->{ 'SEQ' } }++;
55 Maasha::Biopieces::put_record( $record, $out );
59 if ( $options->{ 'complement' } )
61 foreach $seq ( keys %hash )
63 $type = Maasha::Seq::seq_guess_type( $seq ) if not $type;
65 if ( $type eq 'DNA' ) {
66 $rc_seq = Maasha::Seq::dna_revcomp( $seq );
67 } elsif ( $type eq 'RNA' ) {
68 $rc_seq = Maasha::Seq::rna_revcomp( $seq );
70 Maasha::Common::error( "Cannot reverse-complement protein sequence" );
73 if ( exists $hash{ $rc_seq } )
75 $hash{ $seq } += $hash{ $rc_seq };
77 delete $hash{ $rc_seq };
82 foreach $seq ( keys %hash )
86 SEQ_LEN => length $seq,
87 SEQ_COUNT => $hash{ $seq },
90 Maasha::Biopieces::put_record( $record, $out );
93 Maasha::Biopieces::close_stream( $in );
94 Maasha::Biopieces::close_stream( $out );
97 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
102 Maasha::Biopieces::status_set();
108 Maasha::Biopieces::status_log();
112 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<