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

View of /FigKernelScripts/fill_in_roles.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.4 - (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 1.3: +17 -0 lines
Add license words.

#
# 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 Assignments;

use FIG;
my $fig = new FIG;

my $usage = "usage: fill_in_roles ProposedAssignments [ParmsFile] < CSS  > expanded_CSS";

my($parmsF,$assF);
(
 ($assF   = shift @ARGV) && open(ASSIGNMENTS,">$assF")
)
    || die $usage;

use strict;

my $parms;
if (@ARGV > 0)
{
    $parms = &Assignments::load_parms($ARGV[0]);
}
else
{
    $parms = &Assignments::load_parms();
}

if ($ENV{'VERBOSE'} ) {  &Assignments::print_parms($parms) }

my($sig_col,$min_sig,%sig_col);
if (($sig_col = <STDIN>) && ($min_sig = <STDIN>) && ($_ = <STDIN>) && ($_ =~ /^\/\//))
{
    chomp $sig_col;
    %sig_col = map { $_ => 1 } split(/\t/,$sig_col);
    chomp $min_sig;
    print "$sig_col\n$min_sig\n//\n";
}
else
{
    print STDERR &Dumper($sig_col,$min_sig,$_);
    die "Invalid input";
}

my($genomeM,$variantM,$colsM) = &read_row;

my @ss;
push(@ss,[$genomeM,$variantM,$colsM]);

my @row;
while ((@row = &read_row) && (@row == 3))
{
    push(@ss,[@row]);
}

if ($ENV{'VERBOSE'}) { print STDERR &Dumper(["ss",\@ss]) }
my(@abbr,$nsig,$sig,$i);
@abbr = ();
$nsig = 1;
$sig  = 1;
for ($i=0; ($i < @$colsM); $i++)
{
    if ($sig_col{$i})
    {
	push(@abbr,"SIG$sig");
	$sig++;
    }
    else
    {
	push(@abbr,"NSIG$nsig");
	$nsig++;
    }
}
if ($ENV{'VERBOSE'}) { print STDERR &Dumper(["abbr",\@abbr]) }

my(@roles,$colN,$pegs,$func,$peg);	
for ($colN=0; ($colN < @$colsM); $colN++)
{
    $pegs = &extract_col(\@ss,$colN);

    $func = &Assignments::choose_best_assignment($fig,$parms,$pegs,[]);
    print "$abbr[$colN]\t$func\n";

    foreach $peg (@$pegs)
    {
	if ($fig->function_of($peg) ne $func)
	{
	    print ASSIGNMENTS "$peg\t$func\n";
	}
    }
}
print "//\n";

my $row;

foreach $row (@ss)
{
    my($genome,$variant,$cols) = @$row;
    print "$genome\t$variant";

    my $col;
    foreach $col (@$cols)
    {
	print "\t",join(",",@$col);
    }
    print "\n";
}
print "//\n";

sub read_row {

    if (defined($_ = <STDIN>) && ($_ !~ /^\/\//))
    {
	chop;
	my($genome,$variant,@vals) = split(/\t/,$_);
	return ($genome,$variant,[map { [split(/,/,$_)] } @vals]);
    }
    return undef;
}

sub extract_col {
    my($ss,$colN) = @_;
    my($row,$genome,$cols,$col);

    my @pegs = ();
    foreach $row (@$ss)
    {
	($genome,undef,$cols) = @$row;
	if ($col = $cols->[$colN])
	{
	    push(@pegs,map { "fig|$genome.peg.$_" } @$col);
	}
    }
    return \@pegs;
}


MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3