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 # Use bowtie to map sequences in the stream against a specified genome.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 use Maasha::Biopieces;
37 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
40 my ( $options, $in, $out, $index, $tmp_dir, $tmp_in, $tmp_out, $fh_in, $fh_out, $record, $entry, $line, @fields );
42 $options = Maasha::Biopieces::parse_options(
44 { long => 'genome', short => 'g', type => 'genome', mandatory => 'yes', default => undef, allowed => undef, disallowed => undef },
48 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
49 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
51 $index = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/bowtie/$options->{ 'genome' }";
53 $tmp_dir = Maasha::Biopieces::get_tmpdir();
54 $tmp_in = "$tmp_dir/bowtie.seq";
55 $tmp_out = "$tmp_dir/bowtie.out";
57 $fh_out = Maasha::Filesys::file_write_open( $tmp_in );
59 while ( $record = Maasha::Biopieces::get_record( $in ) )
61 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) ) {
62 Maasha::Fasta::put_entry( $entry, $fh_out );
65 Maasha::Biopieces::put_record( $record, $out );
70 if ( $options->{ 'verbose' } ) {
71 Maasha::Common::run( "bowtie", "-f $index $tmp_in $tmp_out" );
73 Maasha::Common::run( "bowtie", "-f $index $tmp_in $tmp_out > /dev/null 2>&1" );
78 $fh_in = Maasha::Filesys::file_read_open( $tmp_out );
80 while ( $line = <$fh_in> )
84 @fields = split /\t/, $line;
86 $record = bowtie2biopiece( \@fields );
88 Maasha::Biopieces::put_record( $record, $out );
95 Maasha::Biopieces::close_stream( $in );
96 Maasha::Biopieces::close_stream( $out );
99 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SUBROUTINES <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
104 # Martin A. Hansen, July 2009
106 # Convert a bowtie entry to a Biopiece record.
108 my ( $entry, # bowtie entry
113 my ( $record, @scores );
115 $record->{ 'Q_ID' } = $entry->[ 0 ];
116 $record->{ 'STRAND' } = $entry->[ 1 ];
117 $record->{ 'S_ID' } = $entry->[ 2 ];
118 $record->{ 'S_BEG' } = $entry->[ 3 ];
119 $record->{ 'SEQ' } = $entry->[ 4 ];
120 $record->{ 'SCORES' } = $entry->[ 5 ];
121 $record->{ 'MISMATCH' } = $entry->[ 6 ];
123 $record->{ 'SEQ_LEN' } = length $entry->[ 4 ];
124 $record->{ 'S_END' } = $record->{ 'S_BEG' } + $record->{ 'SEQ_LEN' } - 1;
125 $record->{ 'SCORES' } =~ s/(.)/ord( $1 ) - 33 . ";"/ge; # http://maq.sourceforge.net/fastq.shtml
126 $record->{ 'SCORE' } = Maasha::Calc::mean( [ split /;/, $record->{ 'SCORES' } ] );
128 $record->{ 'REC_TYPE' } = "BOWTIE";
130 return wantarray ? %{ $record } : $record;
134 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
139 Maasha::Biopieces::status_set();
145 Maasha::Biopieces::status_log();
149 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<