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 overlapping subsequences.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
30 use Maasha::Biopieces;
33 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
36 my ( $options, $in, $out, $record, $new_record, $i, $inc, $subseq, %lookup );
38 $options = Maasha::Biopieces::parse_options(
40 { long => 'word_size', short => 'w', type => 'uint', mandatory => 'no', default => 7, allowed => undef, disallowed => 0 },
41 { long => 'non_overlapping', short => 'n', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
42 { long => 'uniq', short => 'u', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
46 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
47 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
50 $inc = $options->{ "word_size" } if $options->{ "non_overlapping" };
52 while ( $record = Maasha::Biopieces::get_record( $in ) )
54 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
56 for ( $i = 0; $i < length( $record->{ "SEQ" } ) - $options->{ "word_size" } + 1; $i += $inc )
58 $subseq = substr $record->{ "SEQ" }, $i, $options->{ "word_size" };
60 if ( $options->{ "uniq" } and not $lookup{ $subseq } )
62 $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]";
63 $new_record->{ "SEQ" } = $subseq;
64 $new_record->{ "SEQ_LEN" } = $options->{ "word_size" };
66 Maasha::Biopieces::put_record( $new_record, $out );
68 $lookup{ $subseq } = 1;
72 $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]";
73 $new_record->{ "SEQ" } = $subseq;
74 $new_record->{ "SEQ_LEN" } = $options->{ "word_size" };
76 Maasha::Biopieces::put_record( $new_record, $out );
82 Maasha::Biopieces::put_record( $record, $out );
86 Maasha::Biopieces::close_stream( $in );
87 Maasha::Biopieces::close_stream( $out );
90 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
95 Maasha::Biopieces::status_set();
101 Maasha::Biopieces::status_log();
105 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<