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 or index.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
32 use Maasha::Biopieces;
44 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
47 my ( $options, $in, $out, $index, $tmp_dir, $tmp_in, $tmp_out, $fh_in, $fh_out, $record, $entry, $line, @fields, $type, @args, $arg );
49 $options = Maasha::Biopieces::parse_options(
51 { long => 'genome', short => 'g', type => 'genome', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
52 { long => 'index_name', short => 'i', type => 'string', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
53 { long => 'mismatches', short => 'm', type => 'uint', mandatory => 'no', default => 0, allowed => "0,1,2,3", disallowed => undef },
54 { long => 'max_hits', short => 'h', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 },
55 { long => 'seed_length', short => 's', type => 'uint', mandatory => 'no', default => 28, allowed => undef, disallowed => 0 },
56 { long => 'cpus', short => 'c', type => 'uint', mandatory => 'no', default => 1, allowed => undef, disallowed => 0 },
60 Maasha::Common::error( qq(both --index_name and --genome specified) ) if $options->{ "genome" } and $options->{ "index_name" };
61 Maasha::Common::error( qq(no --index_name or --genome specified) ) if not $options->{ "genome" } and not $options->{ "index_name" };
63 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
64 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
66 if ( defined $options->{ 'genome' } ) {
67 $index = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/bowtie/$options->{ 'genome' }";
68 } elsif (defined $options->{ 'index_name' } ) {
69 $index = $options->{ 'index_name' };
72 $tmp_dir = Maasha::Biopieces::get_tmpdir();
73 $tmp_in = "$tmp_dir/bowtie.seq";
74 $tmp_out = "$tmp_dir/bowtie.out";
76 $fh_out = Maasha::Filesys::file_write_open( $tmp_in );
78 while ( $record = Maasha::Biopieces::get_record( $in ) )
80 if ( $entry = Maasha::Fastq::biopiece2fastq( $record ) )
82 Maasha::Common::error( "Mixed FASTA and FASTQ entries in stream" ) if defined $type and $type ne "FASTQ";
83 Maasha::Common::error( "Sequence longer than 1024 not allowed") if length( $entry->[ SEQ ] ) > 1024;
84 Maasha::Fastq::put_entry( $entry, $fh_out );
88 elsif ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
90 Maasha::Common::error( "Mixed FASTA and FASTQ entries in stream" ) if defined $type and $type ne "FASTA";
91 Maasha::Common::error( "Sequence longer than 1024 not allowed") if length( $entry->[ SEQ ] ) > 1024;
92 Maasha::Fasta::put_entry( $entry, $fh_out );
97 Maasha::Biopieces::put_record( $record, $out );
102 push @args, "-n $options->{ 'mismatches' }";
103 push @args, "-v $options->{ 'mismatches' }"; # DANGER: using seed mismatches as alignment mismatches - may work, may not!
104 push @args, "-f" if $type eq "FASTA";
105 push @args, "-p $options->{ 'cpus' }";
106 push @args, "--phred64-quals" unless $type eq "FASTA";
108 if ( defined $options->{ 'max_hits' } ) {
109 push @args, "-k $options->{ 'max_hits' }";
114 $arg = join " ", @args;
116 if ( $options->{ 'verbose' } )
118 print STDERR qq(Running: bowtie $arg $index $tmp_in $tmp_out\n);
119 Maasha::Common::run( "bowtie", "$arg $index $tmp_in $tmp_out" );
123 Maasha::Common::run( "bowtie", "$arg $index $tmp_in $tmp_out > /dev/null 2>&1" );
128 $fh_in = Maasha::Filesys::file_read_open( $tmp_out );
130 while ( $line = <$fh_in> )
134 @fields = split /\t/, $line;
135 $record = bowtie2biopiece( \@fields );
137 Maasha::Biopieces::put_record( $record, $out );
144 Maasha::Biopieces::close_stream( $in );
145 Maasha::Biopieces::close_stream( $out );
148 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SUBROUTINES <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
153 # Martin A. Hansen, July 2009
155 # Convert a bowtie entry to a Biopiece record.
157 my ( $entry, # bowtie entry
162 my ( $record, $s_id, $s_len, $hits );
164 $record->{ 'Q_ID' } = $entry->[ 0 ];
165 $record->{ 'STRAND' } = $entry->[ 1 ];
166 $record->{ 'S_ID' } = $entry->[ 2 ];
167 $record->{ 'S_BEG' } = $entry->[ 3 ];
168 $record->{ 'SEQ' } = $entry->[ 4 ];
169 $record->{ 'SCORES' } = $entry->[ 5 ];
170 $record->{ 'SCORE' } = $entry->[ 6 ] + 1;
171 $record->{ 'ALIGN' } = $entry->[ 7 ] || '.';
172 $record->{ 'S_LEN' } = length $entry->[ 4 ];
173 $record->{ 'SEQ_LEN' } = length $entry->[ 4 ];
174 $record->{ 'S_END' } = $record->{ 'S_BEG' } + $record->{ 'SEQ_LEN' } - 1;
175 $record->{ 'SCORES' } =~ s/(.)/chr( ( ord( $1 ) - 33 ) + 64 )/ge; # convert phred scores to illumina scores
177 $record->{ 'HITS' } = '.';
178 $record->{ 'REC_TYPE' } = "BOWTIE";
180 return wantarray ? %{ $record } : $record;
184 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
189 Maasha::Biopieces::status_set();
195 Maasha::Biopieces::status_log();
199 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<