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 Solexa entries from one or more files.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
32 use Maasha::Biopieces;
38 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
41 my ( $options, $in, $out, $record, $data_in, $num, $entry, @seqs, @scores, $i );
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 => 'format', short => 'f', type => 'string', mandatory => 'no', default => 'octal', allowed => 'octal,decimal', disallowed => undef },
48 { long => 'quality', short => 'q', type => 'uint', mandatory => 'no', default => 20, allowed => undef, disallowed => undef },
49 { long => 'skip_quality', short => 's', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
53 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
54 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
56 while ( $record = Maasha::Biopieces::get_record( $in ) ) {
57 Maasha::Biopieces::put_record( $record, $out );
60 if ( $options->{ 'data_in' } )
62 $data_in = Maasha::Filesys::files_read_open( $options->{ 'data_in' } );
66 while ( $entry = Maasha::Fastq::get_entry( $data_in ) )
68 if ( $record = Maasha::Fastq::fastq2biopiece( $entry ) )
70 if ( not $options->{ 'skip_quality' } )
72 $record->{ 'SCORES' } =~ s/(\d+) ?/Maasha::Fastq::score2phred( $1 )/ge if $options->{ 'format' } eq 'decimal';
73 Maasha::Fastq::solexa2phred( $record->{ 'SCORES' } );
74 Maasha::Fastq::lowercase_low_scores( $record->{ 'SEQ' }, $record->{ 'SCORES' }, $options->{ 'quality' } );
76 $record->{ 'SCORES' } =~ s/(.)/ord( $1 ) - 33 . ";"/ge; # http://maq.sourceforge.net/fastq.shtml
77 $record->{ 'SCORE_MEAN' } = sprintf( "%.2f", Maasha::Calc::mean( [ split /;/, $record->{ 'SCORES' } ] ) );
80 Maasha::Biopieces::put_record( $record, $out );
83 last if $options->{ "num" } and $num == $options->{ "num" };
91 Maasha::Biopieces::close_stream( $in );
92 Maasha::Biopieces::close_stream( $out );
95 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
100 Maasha::Biopieces::status_set();
106 Maasha::Biopieces::status_log();
110 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<