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

View of /FigKernelScripts/assign_to_close_strains.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.10 - (download) (as text) (annotate)
Wed May 3 15:55:21 2006 UTC (13 years, 6 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 1.9: +1 -1 lines
fixes to Assignments.pm

########################################################################
#
# 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 strict;

use Assignments;

use FIG;
my $fig = new FIG;

my($parmsF,$sets,$parms,@pegs_in_set,$pegs,$external_ids,$functions,$peg);
my($id,$best_function,$func,$i,$only_inconsistent);

my $usage = "usage: assign_to_close_strains Sets Parms [only_inconsistent] > proposed.assignments";

#  I have modified this program to run properly using as input sets that are
#  composed of a single line with tab-separated PEGs or with 2-column tables
#  in which the first column is a family name and the second a PEG (any extra fields
#  get ignored in this format)
#


for ($i=0; ($i < @ARGV) && ($ARGV[$i] !~ /only_inconsistent/i); $i++) {}
if ($i < @ARGV)
{
    $only_inconsistent = 1;
    splice(@ARGV,$i,1);
}

(
 ($sets   = shift @ARGV)
)
    || die $usage;

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

open(SETS,"<$sets") || die "could not open $sets";
my($pegs_in_set,%read_control);

my %read_control;
$read_control{fh} = \*SETS;
$read_control{last} = <SETS>;

while ($pegs_in_set = &get_set(\%read_control))
{
    if (! ($only_inconsistent && &all_same($fig,$pegs_in_set)))
    {

	($pegs,$external_ids) = &Assignments::equivalent_ids($fig,$parms,$pegs_in_set);
#       print STDERR &Dumper(["equiv.ids",$pegs,$external_ids]);

	if ($best_function = &Assignments::choose_best_assignment($fig,$parms,$pegs,$external_ids))
	{
#	    print STDERR "best_function: $best_function\n";
	    foreach $peg (@$pegs)
	    {
		$func = $fig->function_of($peg);
		if ($func ne $best_function)
		{
		    print "$peg\t$best_function\n";
		}
	    }
	}
    }
}

sub get_set {
    my($read_control) = @_;

    my $fh = $read_control->{fh};
    my $last = $read_control->{last};
    if (! $last)  { return undef }

    if ($last =~ /^fig\|\d+\.\d+\.peg\.\d+\t/)
    {
	
	$read_control->{last} = <$fh>;
	chomp $last;
	return [split(/\t/,$last)];
    }
    elsif ($last =~ /^(\S+)\tfig\|\d+\.\d+\.peg\.\d+/)
    {
	my $fam = $1;
	my $set = [];
	while ($last && ($last =~ /^(\S+)\t(fig\|\d+\.\d+\.peg\.\d+)/) && ($1 eq $fam))
	{
	    push(@$set,$2);
	    $last = <$fh>;
	}
	$read_control->{last} = $last;
	return $set;
    }
    else
    {
	die "What is this? - $last";
    }
}

sub all_same {
    my($fig,$pegs) = @_;

    my $func = $fig->function_of($pegs->[0]);
    my $i;
    for ($i = 1; ($i < @$pegs) && ($func eq scalar $fig->function_of($pegs->[$i])); $i++) {}
    return ($i == @$pegs);
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3