3 # Copyright (C) 2007-2010 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 # Find stretches of N's in sequences from the stream.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 use Maasha::Biopieces;
34 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
37 my ( $options, $in, $out, $record, $gaps, $gap );
39 $options = Maasha::Biopieces::parse_options(
41 { long => 'min_len', short => 'm', type => 'uint', mandatory => 'no', default => 5, allowed => undef, disallowed => 0 },
45 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
46 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
48 while ( $record = Maasha::Biopieces::get_record( $in ) )
50 if ( exists $record->{ 'SEQ' } )
52 $gaps = find_gaps( $record->{ 'SEQ' }, $options->{ 'min_len' } );
54 foreach $gap ( @{ $gaps } )
56 $gap->{ 'S_ID' } = $record->{ 'S_ID' } || $record->{ 'SEQ_NAME' };
58 Maasha::Biopieces::put_record( $gap, $out );
62 Maasha::Biopieces::put_record( $record, $out );
65 Maasha::Biopieces::close_stream( $in );
66 Maasha::Biopieces::close_stream( $out );
69 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SUBROUTINES <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
74 # Martin A. Hansen, March 2010.
76 # Find stretches, larger than or equal to a given minimum
77 # of N's in a sequence, and returns a list of intervals
81 $min, # Minimum stretch length
86 my ( @gaps, $block, $beg, $end );
96 $beg = index $seq, $block, $beg;
102 while ( substr( $seq, $end, 1 ) eq 'N' ) {
114 return wantarray ? @gaps : \@gaps;
118 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
123 Maasha::Biopieces::status_set();
129 Maasha::Biopieces::status_log();
133 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<