[Bio] / FigKernelScripts / compute_genome_similarity.pl Repository:
ViewVC logotype

View of /FigKernelScripts/compute_genome_similarity.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (download) (as text) (annotate)
Thu May 31 19:24:43 2007 UTC (12 years, 10 months ago) by olson
Branch: MAIN
CVS Tags: mgrast_dev_08112011, rast_rel_2009_05_18, mgrast_dev_08022011, rast_rel_2014_0912, rast_rel_2008_06_18, myrast_rel40, rast_rel_2008_06_16, mgrast_dev_05262011, rast_rel_2008_12_18, mgrast_dev_04082011, rast_rel_2008_07_21, rast_rel_2010_0928, rast_2008_0924, mgrast_version_3_2, mgrast_dev_12152011, rast_rel_2008_04_23, mgrast_dev_06072011, rast_rel_2008_09_30, rast_rel_2009_0925, rast_rel_2010_0526, rast_rel_2014_0729, mgrast_dev_02212011, rast_rel_2010_1206, mgrast_release_3_0, mgrast_dev_03252011, rast_rel_2010_0118, mgrast_rel_2008_0924, mgrast_rel_2008_1110_v2, rast_rel_2009_02_05, rast_rel_2011_0119, mgrast_rel_2008_0625, mgrast_release_3_0_4, mgrast_release_3_0_2, mgrast_release_3_0_3, mgrast_release_3_0_1, mgrast_dev_03312011, mgrast_release_3_1_2, mgrast_release_3_1_1, mgrast_release_3_1_0, mgrast_dev_04132011, rast_rel_2008_10_09, mgrast_dev_04012011, rast_release_2008_09_29, mgrast_rel_2008_0806, mgrast_rel_2008_0923, mgrast_rel_2008_0919, rast_rel_2009_07_09, rast_rel_2010_0827, mgrast_rel_2008_1110, myrast_33, rast_rel_2011_0928, rast_rel_2008_09_29, mgrast_rel_2008_0917, rast_rel_2008_10_29, mgrast_dev_04052011, mgrast_dev_02222011, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Missing scripts.

#
# Compute a cache of genome similarity data.
#
# The tied hash has an entry for keys {$g1,$g2} = $N where $N = 0 if
# not "too similar", $N = 1 if "too similar".
#
# The entry for key {$genome} is a comma-separated list of genomes for which the
# data has been computed.
#

use strict;
use FIG;
use Data::Dumper;

@ARGV == 1 or die "Usage: compute_genome_similarity cachefile\n";

my $cache = shift;

my $fig = new FIG;

use DB_File;

my %toosim;
my $tie = tie %toosim, 'DB_File', $cache, O_RDWR | O_CREAT, 0666, $DB_BTREE;
$tie or die "cannot tie: $!\n";

for my $genome ($fig->genomes)
{
    next unless $fig->is_archaeal($genome) or $fig->is_bacterial($genome);
    my $gs = $fig->genus_species($genome);
    print "$genome $gs\n";
    my @r = $fig->compute_genome_similarity($genome);

    print "Found " . int(@r) . " results\n";

    my %g2list;
    for my $ent (@r)
    {
	my($g2, $toosim, $c1, $c2) = @$ent;
	$toosim{$genome, $g2} = $toosim;
	$g2list{$g2}++;
    }
    $toosim{$genome} = join(",", keys %g2list);
}
untie %toosim;


MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3