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 # Split sequences in the stream into subsequences.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 use Maasha::Biopieces;
34 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
37 my ( $options, $in, $out, $record, $new_record, $i, $step, $subseq );
39 $options = Maasha::Biopieces::parse_options(
41 { long => 'word_size', short => 'w', type => 'uint', mandatory => 'no', default => 7, allowed => undef, disallowed => 0 },
42 { long => 'step_size', short => 's', type => 'uint', mandatory => 'no', default => 1, allowed => undef, disallowed => 0 },
46 if ( $options->{ "step_size" } > $options->{ "word_size" } ) {
47 Maasha::Common::error( qq(step_size > word_size: $options->{ "step_size" } > $options->{ "word_size" } ) );
50 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
51 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
53 $step = $options->{ "step_size" };
55 while ( $record = Maasha::Biopieces::get_record( $in ) )
57 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
59 for ( $i = 0; $i < length( $record->{ "SEQ" } ) - $options->{ "word_size" } + 1; $i += $step )
61 $subseq = substr $record->{ "SEQ" }, $i, $options->{ "word_size" };
63 $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]";
64 $new_record->{ "SEQ" } = $subseq;
65 $new_record->{ "SEQ_LEN" } = $options->{ "word_size" };
67 Maasha::Biopieces::put_record( $new_record, $out );
72 Maasha::Biopieces::put_record( $record, $out );
76 Maasha::Biopieces::close_stream( $in );
77 Maasha::Biopieces::close_stream( $out );
80 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
85 Maasha::Biopieces::status_set();
91 Maasha::Biopieces::status_log();
95 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<