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

View of /FigKernelScripts/order_corrections_for_start_predictions.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.5 - (download) (as text) (annotate)
Fri Nov 30 21:53:05 2007 UTC (11 years, 11 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 1.4: +10 -3 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.
########################################################################

use FIG;
use FIGV;
my $fig = new FIG;

$usage = "order_corrections_for_start_predictions [-orgdir=OrgDir] [min_diff (D: 0.2)] < objects.with.calls > proposed.calls 2> clear.calls";

if ($ARGV[0] =~ /-orgdir=(\S+)/) {
    $fig = new FIGV($1);
    shift @ARGV;
}

($min_diff = shift @ARGV)
    || ($min_diff = 0.2);

$/ = "///\n";
while (defined($obj = <STDIN>))
{
    chomp $obj;
    if ($obj =~ /^(.*?\n)\/\/\n(.*)/s)
    {
        ($hdr,$start_data) = ($1,$2);
        
        $kv = &load_kv($hdr);
        $id      = $kv->{'ID'};
        $old_start_pos = $kv->{'OLD_START_POS'};
        $new_start_pos = $kv->{'NEW_START_POS'};
    }
    if ($old_start_pos != $new_start_pos)
    {
        $new_start_loc = $kv->{'NEW_START_LOC'};
        @starts  = split(/\n\/\/\n/,$start_data);
	@scored = ();
        foreach $poss_start (@starts)
        {
            $kv2        = &load_kv($poss_start);
            $start      = $kv2->{'START'};
	    $score      = $kv2->{'SCORE'};
	    push(@scored,[$start,$score]);
	}
	@scored = sort { $b->[1] <=> $a->[1] } @scored;
	if ((@scored > 1) && ($scored[0]->[0] != $old_start_pos))
	{
	    for ($i=1; ($i < @scored) && ($scored[$i]->[0] != $old_start_pos); $i++) {}
	    
	    if (($i < @scored) || (($id =~ /^(fig|new)\|(\d+\.\d+)/) && (! $fig->possibly_truncated($2,$new_start_loc))))
	    {
		push(@mismatches,[$id,$scored[0]->[1] - $scored[1]->[1],$obj . $/,$scored[0]->[1] - $scored[$i]->[1]]);
	    }
	}
    }
}

foreach $_ (sort { $b->[3] <=> $a->[3] } @mismatches)
{
    $_->[2] =~ s/(NEW_START_POS=\d+)/$1\nCONF_GAP=$_->[1]/s;
    if ($_->[3] >= $min_diff)
    {
	print STDERR join("\t",$_->[0],$_->[3],$_->[1]),"\n";
    }
    print $_->[2];
}

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