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

View of /FigKernelScripts/get_FIGfams_SS_NMPDR_stats.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (download) (as text) (annotate)
Tue Mar 24 21:00:09 2009 UTC (10 years, 7 months ago) by arodri7
Branch: MAIN
CVS Tags: mgrast_dev_08112011, rast_rel_2009_05_18, mgrast_dev_08022011, rast_rel_2014_0912, myrast_rel40, mgrast_dev_05262011, mgrast_dev_04082011, rast_rel_2010_0928, mgrast_version_3_2, mgrast_dev_12152011, mgrast_dev_06072011, 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, rast_rel_2011_0119, 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, mgrast_dev_04012011, rast_rel_2009_07_09, rast_rel_2010_0827, myrast_33, rast_rel_2011_0928, mgrast_dev_04052011, mgrast_dev_02222011, mgrast_dev_10262011, HEAD
*** empty log message ***

use FIG;
use FigFams;
use FF;
use strict;

my $families2c = $ARGV[0];
my $nmpdr_in_ff = {};
my $nmpdr_pegs_in_ffs;
my $org_in_ff = {};
my $ff_in_org = {};
my $pegs_in_ss_counter = 0;
my $nmpdr_pegs_in_ss = 0;

my $fig = new FIG;
#my $ffs = new FigFams($fig);
my $prevFam = "FIG";

open (FH, $families2c) || die "can't open $families2c\n";
while (my $line = <FH>){
    chomp ($line);
    my ($fam,$peg) = split (/\t/, $line);
    print STDERR "$fam\n" if ($prevFam ne $fam);
    $prevFam = $fam;

    my $genome = $fig->genome_of($peg);
#    my $org_name = $fig->org_of($peg);
    
    my $subs;
    $subs = 1 if ($fig->subsystems_for_peg($peg));
    $pegs_in_ss_counter++ if ($subs);

    if ($fig->is_NMPDR_genome($genome) ){
	$nmpdr_in_ff->{$fam}++;
	$nmpdr_pegs_in_ffs++;
	$nmpdr_pegs_in_ss++ if ($subs);
    }
    
    $org_in_ff->{$genome}++;
    $ff_in_org->{$genome}->{$fam}++;
}

print "IN_SEED?\tGenome_id\tOrganism_name\tPEGS_with_FF_in_orgs\tunique_FFs_in_orgs\n";
foreach my $genome (sort {$org_in_ff->{$b}<=>$org_in_ff->{$a}} keys %$org_in_ff){
    my $org_name = $fig->genus_species($genome);
    my $ff_qty = scalar (keys %{$ff_in_org->{$genome}});
    if ($fig->is_NMPDR_genome($genome)){
	print "NMPDR_SEED\t$genome\t$org_name\t" . $org_in_ff->{$genome} . "\t$ff_qty\n";
    }
    else{
	print "SEED\t$genome\t$org_name\t" . $org_in_ff->{$genome} . "\t$ff_qty\n";
    }
}

print "NMPDR figfams with NMPDR seqs: " . scalar (keys %$nmpdr_in_ff) . "\n";
print "NMPDR sequences in figfams: $nmpdr_pegs_in_ffs\n";
print "PEGS in Subsystems: $pegs_in_ss_counter\n";
print "NMPDR PEGS in Subsystems: $nmpdr_pegs_in_ss\n";

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3