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 # Plot chromosome distribution histogram.
26 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
31 use Maasha::Biopieces;
35 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
38 my ( $options, $in, $out, $default, $terminals, $record, %data_hash, @data_list, $elem, $sort_key, $count, $result, $fh );
40 $default = "Chromosome Distribution";
41 $terminals = "dumb,x11,aqua,post,svg";
43 $options = Maasha::Biopieces::parse_options(
45 { long => 'no_stream', short => 'x', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
46 { long => 'data_out', short => 'o', type => 'file', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
47 { long => 'terminal', short => 't', type => 'string', mandatory => 'no', default => 'dumb', allowed => $terminals, disallowed => undef },
48 { long => 'title', short => 'T', type => 'string', mandatory => 'no', default => $default, allowed => undef, disallowed => undef },
49 { long => 'xlabel', short => 'X', type => 'string', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
50 { long => 'ylabel', short => 'Y', type => 'string', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
51 { long => 'logscale_y', short => 'L', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef },
55 $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } );
56 $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } );
58 while ( $record = Maasha::Biopieces::get_record( $in ) )
60 if ( $record->{ "CHR" } ) { # generic
61 $data_hash{ $record->{ "CHR" } }++;
62 } elsif ( $record->{ "REC_TYPE" } eq "PATSCAN" and $record->{ "S_ID" } =~ /^chr/i ) { # patscan
63 $data_hash{ $record->{ "S_ID" } }++;
64 } elsif ( $record->{ "REC_TYPE" } eq "PSL" and $record->{ "S_ID" } =~ /^chr/i ) { # BLAT / PSL
65 $data_hash{ $record->{ "S_ID" } }++;
66 } elsif ( $record->{ "REC_TYPE" } eq "BLAST" and $record->{ "S_ID" } =~ /^chr/i ) { # BLAST
67 $data_hash{ $record->{ "S_ID" } }++;
70 Maasha::Biopieces::put_record( $record, $out ) if not $options->{ "no_stream" };
73 foreach $elem ( keys %data_hash )
77 $sort_key =~ s/chr//i;
79 $sort_key =~ s/^X(.*)/99$1/;
80 $sort_key =~ s/^Y(.*)/99$1/;
81 $sort_key =~ s/^Z(.*)/999$1/;
82 $sort_key =~ s/^M(.*)/9999$1/;
83 $sort_key =~ s/^U(.*)/99999$1/;
85 $count = $sort_key =~ tr/_//;
87 $sort_key =~ s/_.*/"999999" x $count/ex;
89 push @data_list, [ $elem, $data_hash{ $elem }, $sort_key ];
92 @data_list = sort { $a->[ 2 ] <=> $b->[ 2 ] } @data_list;
94 $result = Maasha::Plot::histogram_chrdist( \@data_list, $options );
96 $fh = Maasha::Biopieces::write_stream( $options->{ "data_out" } );
98 print $fh "$_\n" foreach @{ $result };
102 Maasha::Biopieces::close_stream( $in );
103 Maasha::Biopieces::close_stream( $out );
106 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
111 Maasha::Biopieces::status_set();
117 Maasha::Biopieces::status_log();
121 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<