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 # Read SOLID entries from one or more files.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 use Maasha::Biopieces;
37 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
40 my ( $options, $in, $out, $record, $data_in, $num, $entry, $i,
41 $seq_name, $seq_cs, $line, $seq_qual, @scores, @seqs );
43 $options = Maasha::Biopieces::parse_options(
45 { long => 'data_in', short => 'i', type => 'files!', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
46 { long => 'num', short => 'n', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => '0' },
47 { long => 'quality', short => 'q', type => 'uint', mandatory => 'no', default => 20, allowed => undef, disallowed => undef },
51 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
52 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
54 while ( $record = Maasha::Biopieces::get_record( $in ) ) {
55 Maasha::Biopieces::put_record( $record, $out );
58 if ( $options->{ 'data_in' } )
60 $data_in = Maasha::Filesys::files_read_open( $options->{ 'data_in' } );
64 while ( $line = <$data_in> )
68 ( $seq_name, $seq_cs, $seq_qual ) = split /\t/, $line;
70 @scores = split /,/, $seq_qual;
71 @seqs = split //, Maasha::Solid::color_space2seq( $seq_cs );
73 for ( $i = 0; $i < @seqs; $i++ ) {
74 $seqs[ $i ] = lc $seqs[ $i ] if $scores[ $i ] < $options->{ "quality" };
79 SEQ_NAME => $seq_name,
81 SEQ_QUAL => join( ";", @scores ),
82 SEQ_LEN => length $seq_cs,
83 SEQ => join( "", @seqs ),
84 SCORE_MEAN => sprintf( "%.2f", Maasha::Calc::mean( \@scores ) ),
87 Maasha::Biopieces::put_record( $record, $out );
89 last if $options->{ "num" } and $num == $options->{ "num" };
97 Maasha::Biopieces::close_stream( $in );
98 Maasha::Biopieces::close_stream( $out );
101 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
106 Maasha::Biopieces::status_set();
112 Maasha::Biopieces::status_log();
116 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<