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 # Read BLAST records in tabular format from one or more files.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 use Maasha::Biopieces;
35 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
38 my ( $options, $in, $out, $file, $record, $line, @fields, $data_in, $num );
40 $options = Maasha::Biopieces::parse_options(
42 { long => 'data_in', short => 'i', type => 'files!', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
43 { long => 'num', short => 'n', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => '0' },
47 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
48 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
50 while ( $record = Maasha::Biopieces::get_record( $in ) ) {
51 Maasha::Biopieces::put_record( $record, $out );
54 if ( $options->{ 'data_in' } )
58 $data_in = Maasha::Filesys::files_read_open( $options->{ 'data_in' } );
60 while ( $line = <$data_in> )
64 next if $line =~ /^#/;
66 @fields = split /\t/, $line;
68 $record->{ "REC_TYPE" } = "BLAST";
69 $record->{ "Q_ID" } = $fields[ 0 ];
70 $record->{ "S_ID" } = $fields[ 1 ];
71 $record->{ "IDENT" } = $fields[ 2 ];
72 $record->{ "ALIGN_LEN" } = $fields[ 3 ];
73 $record->{ "MISMATCHES" } = $fields[ 4 ];
74 $record->{ "GAPS" } = $fields[ 5 ];
75 $record->{ "Q_BEG" } = $fields[ 6 ] - 1; # BLAST is 1-based
76 $record->{ "Q_END" } = $fields[ 7 ] - 1; # BLAST is 1-based
77 $record->{ "S_BEG" } = $fields[ 8 ] - 1; # BLAST is 1-based
78 $record->{ "S_END" } = $fields[ 9 ] - 1; # BLAST is 1-based
79 $record->{ "E_VAL" } = $fields[ 10 ];
80 $record->{ "BIT_SCORE" } = $fields[ 11 ];
82 if ( $record->{ "S_BEG" } > $record->{ "S_END" } )
84 $record->{ "STRAND" } = '-';
86 ( $record->{ "S_BEG" }, $record->{ "S_END" } ) = ( $record->{ "S_END" }, $record->{ "S_BEG" } );
90 $record->{ "STRAND" } = '+';
93 Maasha::Biopieces::put_record( $record, $out );
95 last if $options->{ "num" } and $num == $options->{ "num" };
103 Maasha::Biopieces::close_stream( $in );
104 Maasha::Biopieces::close_stream( $out );
107 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
112 Maasha::Biopieces::status_set();
118 Maasha::Biopieces::status_log();
122 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<