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 # Assemble tag contigs from overlapping BED type records in the stream.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
30 use Maasha::Biopieces;
32 use Maasha::UCSC::BED;
35 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
38 my ( $options, $in, $out, $tmp_dir, $bed_file, $tag_file, $fh_in, $fh_out,
39 $cols, $record, $bed_entry, $file_hash, $chr, $strand );
41 $options = Maasha::Biopieces::parse_options(
43 { long => 'check', short => 'C', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
47 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
48 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
50 $tmp_dir = Maasha::Biopieces::get_tmpdir();
52 $bed_file = "$tmp_dir/assemble_tag_contigs.bed";
53 $fh_out = Maasha::Filesys::file_write_open( $bed_file );
54 $cols = 6; # we only need the first 6 BED columns
56 while ( $record = Maasha::Biopieces::get_record( $in ) )
58 if ( $bed_entry = Maasha::UCSC::BED::biopiece2bed( $record, $cols ) )
60 $strand = $record->{ 'STRAND' } || '+';
62 Maasha::UCSC::BED::bed_entry_put( $bed_entry, $fh_out, $cols, $options->{ 'check' } );
68 $file_hash = Maasha::UCSC::BED::bed_file_split_on_chr( $bed_file, $tmp_dir, $cols );
72 foreach $chr ( sort keys %{ $file_hash } )
74 $bed_file = $file_hash->{ $chr };
75 $tag_file = "$bed_file.tc";
77 Maasha::Common::run( "bed2tag_contigs", "< $bed_file > $tag_file" );
79 $fh_in = Maasha::Filesys::file_read_open( $tag_file );
81 while ( $bed_entry = Maasha::UCSC::BED::bed_entry_get( $fh_in, $cols, $options->{ 'check' } ) )
83 if ( $record = Maasha::UCSC::BED::bed2biopiece( $bed_entry ) ) {
84 Maasha::Biopieces::put_record( $record, $out );
94 Maasha::Filesys::dir_remove( $tmp_dir );
96 Maasha::Biopieces::close_stream( $in );
97 Maasha::Biopieces::close_stream( $out );
100 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
105 Maasha::Biopieces::status_set();
111 Maasha::Biopieces::status_log();
115 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<