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 # Scan sequences in the stream or a specified genome for patterns using patscan.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
30 use Maasha::Biopieces;
42 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
45 my ( $options, $in, $out, $record, @args, $arg, $type, $tmp_dir, $seq_file, $pat_file, $out_file,
46 $fh_in, $fh_out, $patterns, $pattern, $entry, $result, %head_hash, $i );
48 $options = Maasha::Biopieces::parse_options(
50 { long => 'patterns', short => 'p', type => 'string', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
51 { long => 'patterns_in', short => 'P', type => 'file!', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
52 { long => 'comp', short => 'c', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
53 { long => 'max_hits', short => 'h', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 },
54 { long => 'max_misses', short => 'm', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 },
55 { long => 'genome', short => 'g', type => 'genome', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 },
59 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
60 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
62 $tmp_dir = Maasha::Biopieces::get_tmpdir();
64 $pat_file = "$tmp_dir/patscan.pat";
65 $out_file = "$tmp_dir/patscan.out";
67 $patterns = parse_patterns( $options );
68 $arg = parse_args( $options );
70 if ( defined $options->{ 'genome' } )
72 $seq_file = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna";
76 $seq_file = "$tmp_dir/patscan.seq";
78 $fh_out = Maasha::Filesys::file_write_open( $seq_file );
82 while ( $record = Maasha::Biopieces::get_record( $in ) )
84 if ( $entry = Maasha::Biopieces::biopiece2fasta( $record ) )
86 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } ) if not $type;
88 $entry->[ SEQ_NAME ] = $i;
90 Maasha::Fasta::put_entry( $entry, $fh_out );
92 $head_hash{ $i } = $record->{ "SEQ_NAME" };
100 $arg .= " -p" if $type eq "protein";
103 foreach $pattern ( @{ $patterns } )
105 pat_write( $pat_file, $pattern );
107 `scan_for_matches $arg $pat_file < $seq_file > $out_file`;
108 # Maasha::Common::run( "scan_for_matches", "$arg $pat_file < $seq_file > $out_file" );
110 $fh_in = Maasha::Filesys::file_read_open( $out_file );
112 while ( $entry = Maasha::Fasta::get_entry( $fh_in ) )
114 $result = Maasha::Patscan::parse_scan_result( $entry, $pattern );
116 if ( $options->{ 'genome' } )
118 $result->{ "CHR" } = $result->{ "S_ID" };
119 $result->{ "CHR_BEG" } = $result->{ "S_BEG" };
120 $result->{ "CHR_END" } = $result->{ "S_END" };
122 delete $result->{ "S_ID" };
123 delete $result->{ "S_BEG" };
124 delete $result->{ "S_END" };
128 $result->{ "S_ID" } = $head_hash{ $result->{ "S_ID" } };
131 Maasha::Biopieces::put_record( $result, $out );
139 unlink $seq_file if not $options->{ 'genome' };
141 Maasha::Biopieces::close_stream( $in );
142 Maasha::Biopieces::close_stream( $out );
145 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SUBROUTINES <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
150 # Martin A. Hansen, May 2009.
152 # Parse pattern arguments based on information in the
153 # options hash and returns a list of patterns.
154 # Raises an error if no info.
156 my ( $options, # options hash
163 if ( $options->{ "patterns" } ) {
164 $patterns = Maasha::Patscan::parse_patterns( $options->{ "patterns" } );
165 } elsif ( -f $options->{ "patterns_in" } ) {
166 $patterns = Maasha::Patscan::read_patterns( $options->{ "patterns_in" } );
168 Maasha::Common::error( qq(no patterns specified.) );
171 return wantarray ? @{ $patterns } : $patterns;
177 # Martin A. Hansen, May 2009.
179 # Generate an argument string for executing scan_for_matches based
180 # on information in the option hash.
182 my ( $options, # options hash
189 push @args, "-c" if $options->{ "comp" };
190 push @args, "-m $options->{ 'max_hits' }" if $options->{ 'max_hits' };
191 push @args, "-n $options->{ 'max_misses' }" if $options->{ 'max_hits' };
193 return join " ", @args;
199 # Martin A. Hansen, May 2009.
201 # Write a scan_for_matches pattern to file.
203 my ( $file, # target file to write pattern to.
204 $pattern, # pattern to write.
211 $fh_out = Maasha::Common::write_open( $pat_file );
213 print $fh_out "$pattern\n";
219 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
224 Maasha::Biopieces::status_set();
230 Maasha::Biopieces::status_log();
234 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<