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 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
30 use Maasha::Biopieces;
36 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
39 my ( $run_time_beg, $run_time_end, $options, $in, $out, $record, $data_in, $num, $entry, $i,
40 $seq_name, $seq_cs, $line, $seq_qual, @scores, @seqs );
42 $options = Maasha::Biopieces::parse_options(
44 { long => 'data_in', short => 'i', type => 'files!', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
45 { long => 'num', short => 'n', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => '0' },
46 { long => 'quality', short => 'q', type => 'uint', mandatory => 'no', default => 20, allowed => undef, disallowed => undef },
50 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
51 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
53 while ( $record = Maasha::Biopieces::get_record( $in ) ) {
54 Maasha::Biopieces::put_record( $record, $out );
57 if ( $options->{ 'data_in' } )
59 $data_in = Maasha::Filesys::files_read_open( $options->{ 'data_in' } );
63 while ( $line = <$data_in> )
67 ( $seq_name, $seq_cs, $seq_qual ) = split /\t/, $line;
69 @scores = split /,/, $seq_qual;
70 @seqs = split //, Maasha::Solid::color_space2seq( $seq_cs );
72 for ( $i = 0; $i < @seqs; $i++ ) {
73 $seqs[ $i ] = lc $seqs[ $i ] if $scores[ $i ] < $options->{ "quality" };
78 SEQ_NAME => $seq_name,
80 SEQ_QUAL => join( ";", @scores ),
81 SEQ_LEN => length $seq_cs,
82 SEQ => join( "", @seqs ),
83 SCORE_MEAN => sprintf( "%.2f", Maasha::Calc::mean( \@scores ) ),
86 Maasha::Biopieces::put_record( $record, $out );
88 last if $options->{ "num" } and $num == $options->{ "num" };
97 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
102 $run_time_beg = Maasha::Biopieces::run_time();
104 Maasha::Biopieces::log_biopiece();
109 Maasha::Biopieces::close_stream( $in );
110 Maasha::Biopieces::close_stream( $out );
112 $run_time_end = Maasha::Biopieces::run_time();
114 Maasha::Biopieces::run_time_print( $run_time_beg, $run_time_end, $options );
118 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<