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 # Write Biopiece records to the KISS Genome browser.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
33 use Maasha::Biopieces;
43 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
46 my ( $data_dir, $user, $options, $path, $in, $out, $tmp_dir, %fh_hash, $fh_out, $record, $entry, $key, @dirs, $dir, $dst_dir, @nums, $num, $contig_dir );
48 $data_dir = Maasha::Biopieces::biopiecesrc( "KISS_DATA_DIR" );
49 $user = Maasha::Biopieces::biopiecesrc( "KISS_USER" );
51 $options = Maasha::Biopieces::parse_options(
53 { long => 'user', short => 'u', type => 'string', mandatory => 'no', default => $user, allowed => undef, disallowed => undef },
54 { long => 'clade', short => 'c', type => 'string', mandatory => 'yes', default => undef, allowed => undef, disallowed => undef },
55 { long => 'genome', short => 'g', type => 'string', mandatory => 'yes', default => undef, allowed => undef, disallowed => undef },
56 { long => 'assembly', short => 'a', type => 'string', mandatory => 'yes', default => undef, allowed => undef, disallowed => undef },
57 { long => 'track_name', short => 't', type => 'string', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
58 { long => 'no_stream', short => 'x', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
62 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
63 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
65 if ( $options->{ 'track_name' } )
67 $options->{ 'track_name' } =~ tr/ /_/;
69 $path = join "/", $data_dir, "Users/", $options->{ 'user' }, $options->{ 'clade' }, $options->{ 'genome' }, $options->{ 'assembly' };
71 Maasha::Common::error( qq(Path not found: "$path") ) if not -d $path;
73 $tmp_dir = Maasha::Biopieces::get_tmpdir();
75 while ( $record = Maasha::Biopieces::get_record( $in ) )
77 if ( $entry = Maasha::KISS::IO::biopiece2kiss( $record ) )
79 if ( not exists $fh_hash{ $entry->{ 'S_ID' } } ) {
80 $fh_hash{ $entry->{ 'S_ID' } } = Maasha::Filesys::file_write_open( "$tmp_dir/$entry->{ 'S_ID' }" );
83 $fh_out = $fh_hash{ $entry->{ 'S_ID' } };
85 Maasha::KISS::IO::kiss_entry_put( $entry, $fh_out );
88 Maasha::Biopieces::put_record( $record, $out ) if not $options->{ "no_stream" };
91 foreach $key ( keys %fh_hash )
93 close $fh_hash{ $key };
95 $dst_dir = Maasha::Filesys::dir_create_if_not_exists( "$path/$key" );
96 $dst_dir = Maasha::Filesys::dir_create_if_not_exists( "$dst_dir/Tracks" );
98 @dirs = Maasha::Filesys::ls_dirs( $dst_dir );
100 foreach $dir ( @dirs )
102 $dir = ( split "/", $dir )[ -1 ];
104 if ( $dir =~ /^(\d+)/ ) {
109 @nums = sort { $a <=> $b } @nums;
111 $num = $nums[ -1 ] || 0;
115 $dst_dir = "$dst_dir/$num" . "_$options->{ 'track_name' }";
117 Maasha::Filesys::dir_create( $dst_dir );
119 Maasha::Filesys::file_copy( "$tmp_dir/$key", "$dst_dir/track_data.kiss" );
121 Maasha::KISS::IO::kiss_sort( "$dst_dir/track_data.kiss" );
122 Maasha::KISS::IO::kiss_index( "$dst_dir/track_data.kiss" );
124 unlink "$tmp_dir/$key";
129 $path = join "/", $data_dir, "Users/", $options->{ 'user' }, $options->{ 'clade' };
131 Maasha::Common::error( qq(Path not found: "$path") ) if not -d $path;
133 $dst_dir = Maasha::Filesys::dir_create( "$path/$options->{ 'genome' }" );
134 $dst_dir = Maasha::Filesys::dir_create( "$dst_dir/$options->{ 'assembly' }" );
136 while ( $record = Maasha::Biopieces::get_record( $in ) )
138 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
140 $entry->[ SEQ_NAME ] = ( split " ", $entry->[ SEQ_NAME ] )[ 0 ];
141 $contig_dir = Maasha::Filesys::dir_create( "$dst_dir/$entry->[ SEQ_NAME ]" );
142 $contig_dir = Maasha::Filesys::dir_create( "$contig_dir/Sequence" );
144 $fh_out = Maasha::Filesys::file_write_open( "$contig_dir/sequence.txt" );
145 print $fh_out $entry->[ SEQ ];
151 Maasha::Biopieces::close_stream( $in );
152 Maasha::Biopieces::close_stream( $out );
155 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
160 Maasha::Biopieces::status_set();
166 Maasha::Biopieces::status_log();
170 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<