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;
38 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
41 my ( $options, $in, $out, $index, $tmp_dir, $tmp_in, $tmp_out, $fh_in, $fh_out, $record, $entry, $line, @fields, $type, @args, $arg );
43 $options = Maasha::Biopieces::parse_options(
45 { long => 'genome', short => 'g', type => 'genome', mandatory => 'yes', default => undef, allowed => undef, disallowed => undef },
46 { long => 'mismatches', short => 'm', type => 'uint', mandatory => 'no', default => 0, allowed => "0,1,2,3", disallowed => undef },
47 { long => 'max_hits', short => 'h', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 },
48 { long => 'seed_length', short => 's', type => 'uint', mandatory => 'no', default => 28, allowed => undef, disallowed => 0 },
49 { long => 'cpus', short => 'c', type => 'uint', mandatory => 'no', default => 1, allowed => undef, disallowed => 0 },
53 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
54 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
56 $index = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/bowtie/$options->{ 'genome' }";
58 $tmp_dir = Maasha::Biopieces::get_tmpdir();
59 $tmp_in = "$tmp_dir/bowtie.seq";
60 $tmp_out = "$tmp_dir/bowtie.out";
62 $fh_out = Maasha::Filesys::file_write_open( $tmp_in );
64 while ( $record = Maasha::Biopieces::get_record( $in ) )
66 if ( $entry = Maasha::Fastq::biopiece2fastq( $record ) )
68 Maasha::Common::error( "Mixed FASTA and FASTQ entries in stream" ) if defined $type and $type ne "FASTQ";
69 Maasha::Fastq::put_entry( $entry, $fh_out );
73 elsif ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
75 Maasha::Common::error( "Mixed FASTA and FASTQ entries in stream" ) if defined $type and $type ne "FASTA";
76 Maasha::Fasta::put_entry( $entry, $fh_out );
81 Maasha::Biopieces::put_record( $record, $out );
86 push @args, "-n $options->{ 'mismatches' }";
87 push @args, "-f" if $type eq "FASTA";
89 if ( defined $options->{ 'max_hits' } ) {
90 push @args, "-k $options->{ 'max_hits' }";
95 $arg = join " ", @args;
97 if ( $options->{ 'verbose' } )
99 print STDERR qq(Running: bowtie $arg $index $tmp_in $tmp_out\n);
100 Maasha::Common::run( "bowtie", "$arg $index $tmp_in $tmp_out" );
104 Maasha::Common::run( "bowtie", "$arg $index $tmp_in $tmp_out > /dev/null 2>&1" );
109 $fh_in = Maasha::Filesys::file_read_open( $tmp_out );
111 while ( $line = <$fh_in> )
115 @fields = split /\t/, $line;
117 $record = bowtie2biopiece( \@fields );
119 Maasha::Biopieces::put_record( $record, $out );
126 Maasha::Biopieces::close_stream( $in );
127 Maasha::Biopieces::close_stream( $out );
130 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SUBROUTINES <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
135 # Martin A. Hansen, July 2009
137 # Convert a bowtie entry to a Biopiece record.
139 my ( $entry, # bowtie entry
144 my ( $record, @scores );
146 $record->{ 'Q_ID' } = $entry->[ 0 ];
147 $record->{ 'STRAND' } = $entry->[ 1 ];
148 $record->{ 'S_ID' } = $entry->[ 2 ];
149 $record->{ 'S_BEG' } = $entry->[ 3 ];
150 $record->{ 'SEQ' } = $entry->[ 4 ];
151 $record->{ 'SCORES' } = $entry->[ 5 ];
152 $record->{ 'MISMATCH' } = $entry->[ 6 ];
154 $record->{ 'SEQ_LEN' } = length $entry->[ 4 ];
155 $record->{ 'S_END' } = $record->{ 'S_BEG' } + $record->{ 'SEQ_LEN' } - 1;
156 $record->{ 'SCORES' } =~ s/(.)/ord( $1 ) - 33 . ";"/ge; # http://maq.sourceforge.net/fastq.shtml
157 $record->{ 'SCORE_MEAN' } = sprintf( "%.2f", Maasha::Calc::mean( [ split /;/, $record->{ 'SCORES' } ] ) );
159 $record->{ 'REC_TYPE' } = "BOWTIE";
161 return wantarray ? %{ $record } : $record;
165 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
170 Maasha::Biopieces::status_set();
176 Maasha::Biopieces::status_log();
180 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<