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

View of /FigKernelScripts/add_sim_data_for_start_predictions.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.8 - (download) (as text) (annotate)
Fri Nov 30 21:53:05 2007 UTC (12 years, 2 months ago) by gdpusch
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 1.7: +4 -5 lines
Added FIGV support. -- /gdp

# -*- 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 = "add_sim_data_for_start_predictions Sims [use-close] < stream_of_ORF_objects > with_sim_scores";

(($sims = shift @ARGV) && open(SIMS,"<$sims"))
    || die "usage: $usage";

if ((@ARGV > 0) && ($ARGV[0] =~ /use-close/i))
{
#   print STDERR "Using very close similarities, as well as more distant\n";
    $use_close = 1;
}
else
{
    $use_close = 0;
}

while (defined($_ = <SIMS>))
{
    chop;
    ($id1,$id2,$iden,undef,undef,undef,$b1,undef,$b2,undef,$psc,undef) = split(/\t/,$_);
    $psc = ($psc =~ /^e-/) ? "1.0" . $psc : $psc;
    if ( ($id1 ne $id2) && (! $seen{"$id1,$id2"}) && ($psc < 1.0e-20) && (($iden < 95) || $use_close))
    {
	push(@{$sims_close_to_id{$id1}},[$id2,$b1,$b2,$iden,$psc]);
	$seen{"$id1,$id2"} = 1;
    }
}

$/ = "///\n";
while (defined($obj = <STDIN>))
{
    chomp $obj;
    if ($obj =~ /^(.*?\n)\/\/\n(.*)/s)
    {
	($hdr,$start_data) = ($1,$2);
	print $hdr;
	
	$kv = &load_kv($hdr);
	$id = $kv->{"ID"};
	$old_start = $kv->{'OLD_START_POS'};

	@poss_starts = split(/\n\/\/\n/,$start_data);
	foreach $poss_start (@poss_starts)
	{
	    if ($poss_start =~ /START=(\d+)/s)
	    {
		$start = $1;
		$sc = 0;

		foreach $tuple (@{$sims_close_to_id{$id}}) # ($id2,$b1,$b2,$iden,$psc)
		{
		    $num_close = scalar(@{$sims_close_to_id{$id}});
		    $predicted = (($tuple->[1] - $tuple->[2]) * 3) + $old_start;
		    if (abs($predicted - $start) < 30)
		    {
			$incr = ((1 / $num_close) * (1 - (abs($predicted - $start)/30)));
			$sc += $incr;
		    }
		}
		print "//\n$poss_start\nSIM=$sc\n";
	    }
	}
	if (@poss_starts) { print "//\n"; }
	print "///\n";
    }
}

sub load_kv {
    my($obj) = @_;
    my($kv,$kvH);

    $kvH = {};
    foreach $kv (split(/\n/,$obj))
    {
	if ($kv =~ /^([^=]+)=(.*)$/)
	{
	    $kvH->{$1} = $2;
	}
    }
    return $kvH;
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3