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

View of /FigKernelScripts/update_uniq_id_data.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.7 - (download) (as text) (annotate)
Thu Mar 1 02:04:55 2007 UTC (13 years 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
Changes since 1.6: +2 -2 lines
use function_of_quick

#
# 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;

# usage: upadte_uniq_id_data   ### updates ext_func.table and ext_org.table
#                              
#                               This script updates the two tables based on the current
#                               contents of peg.synonyms and then runs 
#                              
#                                   load_external_orgs
#                                   add_assertions_of_function
#
#                               which is needed to make the changes active

rename("$FIG_Config::global/ext_func.table","$FIG_Config::global/ext_func.table~")
    || die "could not rename $FIG_Config::global/ext_func.table";
open(IN,"<$FIG_Config::global/ext_func.table~")
    || die "could not open $FIG_Config::global/ext_func.table~";
open(FUNCS,">$FIG_Config::global/ext_func.table")
    || die "could not open $FIG_Config::global/ext_func.table";
while (defined($_ = <IN>))
{
    if ($_ !~ /^xxx/)
    {
	print FUNCS $_;
    }
}
close(IN);

rename("$FIG_Config::global/ext_org.table","$FIG_Config::global/ext_org.table~")
    || die "could not rename $FIG_Config::global/ext_org.table";
open(IN,"<$FIG_Config::global/ext_org.table~")
    || die "could not open $FIG_Config::global/ext_org.table~";
open(ORGS,">$FIG_Config::global/ext_org.table")
    || die "could not open $FIG_Config::global/ext_org.table";
while (defined($_ = <IN>))
{
    if ($_ !~ /^xxx/)
    {
	print ORGS $_;
    }
}
close(IN);

open(SYN,"<$FIG_Config::global/peg.synonyms")
    || die "could not open peg.synonyms";

while (defined($_ = <SYN>))
{
    if ($_ =~ /^xxx(\d+),\d+\t(.*)$/)
    {
	$id = $1;
	$rest = $2;
	@ids = map { $_ =~ /^([^,]+)/; $1 } split(/;/,$rest);
	@eval_ids = sort { $b->[1] <=> $a->[1] } map { [$_,&eval_id($fig,$_)] } @ids;
	$rep_id = $eval_ids[0]->[0];

	$func = $fig->function_of_quick($rep_id);
	$func = $func ? $func : "hypothetical protein";
	print FUNCS "xxx$id\t$func\n";

	undef $org;
	my $i;
	for ($i=0; (! $org) && ($i < @eval_ids); $i++)
	{
	    $org = $fig->org_of($eval_ids[$i]->[0]);
	}
	if (! $org)  { $org = "" }
	print ORGS "xxx$id\t$org\n";
    }
}
close(SYN);
close(ORGS);
close(FUNCS);
&FIG::run("load_external_orgs");
&FIG::run("add_assertions_of_function");

sub eval_id {
    my($fig,$id) = @_;
    my($func);

    if ($id =~ /^fig\|/)
    {
	my @tmp = $fig->peg_to_subsystems($id);
	if (@tmp > 0)
	{
	    return 100 + @tmp;
	}
	elsif (($func = $fig->function_of_quick($id)) && (! &FIG::hypo($id)))
	{
	    return 10;
	}
	else
	{
	    return 7;
	}
    }
    elsif ($id =~ /^sp\|/)
    {
	return 20;
    }
    elsif ($id =~ /^kegg/)
    {
	return 9;
    }
    elsif ($id =~ /^(uni|tr)\|/)
    {
	return 8;
    }

    return 1;
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3