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

View of /FigKernelScripts/make_sp_org_domain_table.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.2 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 2005 UTC (13 years, 11 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, caBIG-05Apr06-00, 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, caBIG-13Feb06-00, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Changes since 1.1: +17 -0 lines
Add license words.

# -*- 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.
#


$usage = "make_sp_org_domain_table [label (Def: sp)] < sprot.dat > ../sp_org_domain_table";

if ( @ARGV > 0 ) { $label = shift @ARGV; } else { $label = "sp"; }

$domain_code{"Archaea"}   = "V";
$domain_code{"Bacteria"}  = "B";
$domain_code{"Eukaryota"} = "E";
$domain_code{"Viruses"}   = "V";

while (defined($_ = <STDIN>) && ($_ !~ /^ID /)) {}
while ($_ && ($_ =~ /^ID /))
{
    $organelle="";
    $_ =~ /^ID\s+(\S+)/;
    $id = $1;
    undef $ac; @os = (); $os = "";
    $oc = (); $domain = "";

    while ($_ !~ /^\/\//)
    {
	if ($_ =~ /^OC\s+(\S.*\S)\s*$/)
	{
	    $oc .= "$1 ";
	}

	if ($_ =~ /^OS\s+(\S.*\S)\s*$/)
	{
	    $os .= "$1 ";
	}
	$_ = <STDIN>;
    }
    
    $domain = ( split(/\;\s+/, $oc) )[0];

    $domain =~ s/^([^\.\s]+)\.*\s*/$1/;

    $os =~ s/\([^\)]*\)//g;
    if ( $os =~ m/^\'([^\']+)\'\s/ )
    {
	$in_quotes  = $hyphenated = $1;
	$hyphenated =~ s/\s+/-/g;
	$os =~ s/\'$in_quotes\'/$hyphenated/;
    }
    
    if ($os =~ /^\s*(\S.*\S)\s*$/)
    {
	$orgs = $1;
	$orgs =~ s/\bAND //g;
	@orgs = split(/, /,$orgs);
	foreach $org (@orgs)
	{
	    $org =~ s/^\s*(\S.*\S)\s*$/$1/;
	    while ($org =~ s/\s*\([^\)]*\)\.*$//) {}
	    
	    if (($org =~ /\.$/) && ($org !~ /SP\.$/))
	    {
		$org =~ s/\.$//;
	    }

	    if ($org =~ /^(\S)(\S+)\s+(.+)$/)
	    {
		$p1 = $1; $p2 = $2; $p3 = $3;

		$p1 =~ tr/a-z/A-Z/;
		$p2 =~ tr/A-Z/a-z/;
		$p3 =~ tr/A-Z/a-z/;
		$p3 =~ s/\s+$//;
		$org = "$p1$p2 $p3";
	    }

	    if ($org)
	    {
		for ($i=0; ($i <= $#os) && ($os[$i] ne $org); $i++) {}
		if ($i > $#os)
		{
		    push(@os,$org);
		}
	    }
	}
    }

    if ($domain && ($#os >= 0))
    {
	foreach $org (@os)
	{
	    if ($domain_code{$domain})
	    {
	        if ( $dom = $org_domain{$org} )
		{
		    if ($dom ne $domain_code{$domain})
		    {
		        print "organism -- \"$org\" has more than one domains!\n";
			exit;
		    }
		}
		else
		{
	            $org_domain{$org} = $domain_code{$domain};
		}
	    }
	    else
	    {
	        print "no domain code -- **$domain**\n";
		exit;
	    }
	}
    }

    while ($_ && defined($_ = <STDIN>) && ($_ !~ /^ID /)) {}
}

foreach $org ( sort {$org_domain{$a} cmp $org_domain{$b} or $a cmp $b} keys %org_domain ) 
{
    print "$org\t$org_domain{$org}\n";
}




MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3