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 # BLAT sequences in the stream against a genome.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
30 use Maasha::Biopieces;
34 use Maasha::UCSC::PSL;
37 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
40 my ( $options, $in, $out, $record, $blat_args, $genome_file, $query_file, $fh_in, $fh_out,
41 $tmp_dir, $type, $result_file, $entry );
43 $options = Maasha::Biopieces::parse_options(
45 { long => 'genome', short => 'g', type => 'genome', mandatory => 'yes', default => undef, allowed => undef, disallowed => undef },
46 { long => 'occ', short => 'c', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
47 { long => 'tile_size', short => 't', type => 'uint', mandatory => 'no', default => 11, allowed => undef, disallowed => 0 },
48 { long => 'step_size', short => 's', type => 'uint', mandatory => 'no', default => 11, allowed => undef, disallowed => 0 },
49 { long => 'min_identity', short => 'm', type => 'uint', mandatory => 'no', default => 90, allowed => undef, disallowed => 0 },
50 { long => 'min_score', short => 'M', type => 'uint', mandatory => 'no', default => 0, allowed => undef, disallowed => undef },
51 { long => 'one_off', short => 'o', type => 'uint', mandatory => 'no', default => 0, allowed => undef, disallowed => undef },
55 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
56 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
58 $genome_file = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna";
60 $blat_args .= " -tileSize=$options->{ 'tile_size' }";
61 $blat_args .= " -oneOff=$options->{ 'one_off' }";
62 $blat_args .= " -minIdentity=$options->{ 'min_identity' }";
63 $blat_args .= " -minScore=$options->{ 'min_score' }";
64 $blat_args .= " -stepSize=$options->{ 'step_size' }";
65 # $blat_args .= " -ooc=" . Maasha::Config::genome_blat_ooc( $options->{ "genome" }, 11 ) if $options->{ 'ooc' };
67 $tmp_dir = Maasha::Biopieces::get_tmpdir();
68 $query_file = "$tmp_dir/blat.seq";
70 $fh_out = Maasha::Filesys::file_write_open( $query_file );
72 while ( $record = Maasha::Biopieces::get_record( $in ) )
74 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
76 $type = Maasha::Seq::seq_guess_type( $record->{ 'SEQ' } ) if not $type;
77 Maasha::Fasta::put_entry( $entry, $fh_out, 80 );
80 Maasha::Biopieces::put_record( $record, $out );
85 $blat_args .= " -t=dnax" if $type eq "protein";
86 $blat_args .= " -q=$type";
88 $result_file = "$tmp_dir/blat.psl";
90 if ( $options->{ 'verbose' } ) {
91 Maasha::Common::run( "blat", "$genome_file $query_file $blat_args $result_file" );
93 Maasha::Common::run( "blat", "$genome_file $query_file $blat_args $result_file > /dev/null 2>&1" );
98 $fh_in = Maasha::Filesys::file_read_open( $result_file );
100 while ( $entry = Maasha::UCSC::PSL::psl_entry_get( $fh_in ) )
102 if ( $record = Maasha::UCSC::PSL::psl2biopiece( $entry ) ) {
103 Maasha::Biopieces::put_record( $record, $out );
110 Maasha::Biopieces::close_stream( $in );
111 Maasha::Biopieces::close_stream( $out );
114 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
119 Maasha::Biopieces::status_set();
125 Maasha::Biopieces::status_log();
129 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<