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

View of /FigKernelScripts/check_subsystems.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.7 - (download) (as text) (annotate)
Thu Feb 1 14:58:06 2007 UTC (12 years, 9 months ago) by overbeek
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
Changes since 1.6: +11 -2 lines
strip comments on functions for subsystem checking

########################################################################
# -*- perl -*-
#
# Copyright (c) 2003-2006 University of Chicago and Fellowship
# for Interpretations of Genomes. All Rights Reserved.
#
# This file is part of the SEED Toolkit.
# 
# The SEED Toolkit is free software. You can redistribute
# it and/or modify it under the terms of the SEED Toolkit
# Public License. 
#
# You should have received a copy of the SEED Toolkit Public License
# along with this program; if not write to the University of Chicago
# at info@ci.uchicago.edu or the Fellowship for Interpretation of
# Genomes at veronika@thefig.info or download a copy from
# http://www.theseed.org/LICENSE.TXT.
#


use FIG;
my $fig = new FIG;

my $usage = "usage: check_subsystems [SubSystem1 Subsystem2 ...]";

my @subsystems;
if (@ARGV > 0)
{
    @subsystems = @ARGV;
}
else
{
    @subsystems = $fig->all_subsystems;
}

my $gsH = {};
my(@bad_in,@good,%good,@bad_out);

foreach $subsys (@subsystems)
{
    my $curator = $fig->subsystem_curator($subsys);
    my @roles   = $fig->subsystem_to_roles($subsys);
    @genomes = map { $_->[0] } @{$fig->subsystem_genomes($subsys,"all")};
    my $rdbH = $fig->db_handle;
    my $subsystemQ = quotemeta $subsys;
    my $query = "SELECT role,protein FROM subsystem_index WHERE subsystem='$subsystemQ'";
    my $relational_db_response = $rdbH->SQL($query);
    foreach $_ (@$relational_db_response)
    {
	my($role,$peg) = @$_;
	my $func = &stripped_function_of($fig,$peg);
	if ((index($func,$role) < 0) && ($fig->is_real_feature($peg)))
	{
	    push(@bad_in,[$peg,$func,$role,&gs_of_peg($fig,$peg,$gsH),$subsys,$curator]);
	}
	else
	{
	    push(@good,$peg);
	}
    }
    %good = map { $_ => 1 } @good;
    $org_constraint = "(" . join(" or ",map { "(org = '$_')" } @genomes) . ")";
    $role_constraint = "(" . join(" or ",map { $roleQ = quotemeta $_; "(role = '$roleQ')" } @roles) . ")";
    $query = "SELECT prot,role  FROM roles WHERE $role_constraint AND $org_constraint";
    my $relational_db_response = $rdbH->SQL($query);
    foreach $_ (grep { ! $good{$_->[0]} } @$relational_db_response)
    {
	($peg,$role) = @$_;
        {
	    if ($fig->is_real_feature($peg))
	    {
		$func = &stripped_function_of($fig,$peg);
		push(@bad_out,[$peg,$func,$role,&gs_of_peg($fig,$peg,$gsH),$subsys,$curator]);
	    }
        }
    }
}

foreach $x (sort { ($a->[2] cmp $b->[2]) or ($a->[1] cmp $b->[1]) or ($a->[3] cmp $b->[3]) } @bad_in)
{
    ($peg,$func,$role,$gs,$subsys,$curator) = @$x;
    print join("\t",("mismatch",$peg,$func,$role,$gs,$subsys,$curator)),"\n";
}

foreach $x (sort { ($a->[2] cmp $b->[2]) or ($a->[1] cmp $b->[1]) or ($a->[3] cmp $b->[3]) } @bad_out)
{
    ($peg,$func,$role,$gs,$subsys,$curator) = @$x;
    print join("\t",("left-out",$peg,$func,$role,$gs,$subsys,$curator)),"\n";
}

sub gs_of_peg {
    my($fig,$peg,$gsH) = @_;

    my $gs;
    if ($peg =~ /^fig\|(\d+\.\d+)/)
    {
	my $genome = $1;
	$gs = $gsH->{$genome};
	if (! $gs) 
	{ 
	    $gsH->{$genome} = $gs = $fig->genus_species($genome);
	}
    }
    return $gs;
}


sub stripped_function_of {
    my($fig,$peg) = @_;

    my $func = $fig->function_of($peg);
    $func =~ s/\s*\#.*$//;
    return $func;
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3