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

View of /FigKernelScripts/start_data_for_set_of_pegs.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.6 - (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 1.5: +28 -8 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 = "usage: start_data_for_set_of_pegs [-help] [-orgdir=OrgDir] [use-close] < start.objects > objects.with.evidence";

$trouble   = 0;
$use_close = "";
$orgdir_flag   = "";
while (@ARGV)
{
    if ($ARGV[0] =~ m/-h(elp)?/) {
	die "\n\tusage: $usage\n\n";
    }
    elsif ($ARGV[0] =~ /-orgdir=(\S+)/) {
	$fig = new FIGV($1);
	$orgdir_flag = $ARGV[0];
    }
    elsif ($ARGV[0] =~ /use-close/) {
	$use_close = "use-close";
    }
    else {
	warn "Invalid argument $ARGV[0]\n";
    }
    shift @ARGV;
}
die "\nusage: $usage\n\n" if $trouble;

$subdir = "$FIG_Config::temp/start.data.$$";
&FIG::verify_dir($subdir);

@pegs    = map { ($_ =~ /^(((fig\|\d+\.\d+\.peg\.\d+)|(new\|\d+\.\d+\.peg\.\d+\t\S+\t\S+))(\tno_recall)?)/) ? $1 : () } <STDIN>;
@objects = grep { $_ !~ /no_recall/ } @pegs;

if (@objects > 0)
{
    open(TMP,">$subdir/objects.to.build") || die "could not open $subdir/objects.to.build";
    print TMP join("\n",@objects),"\n";
    close(TMP);

    &FIG::run("build_initial_objects_for_start_predictions $orgdir_flag < $subdir/objects.to.build > $subdir/initial.objects");
    &FIG::run("get_potential_starts_for_start_predictions           < $subdir/initial.objects  > $subdir/objects.with.potential.starts");
    open(AA,">$subdir/AA_for_called_genes") || die "could not open $subdir/AA_for_called_genes";
    foreach $peg (@pegs)
    {
	if ($peg =~ /^(fig\|\d+\.\d+\.peg\.\d+)/)
	{
	    $peg = $1;
	    if ($seq = $fig->get_translation($peg))
	    {
		print AA ">$peg\n$seq\n";
	    }
	}
	elsif ($peg =~ /^(new\|\d+\.\d+\.peg\.\d+)\t(\S+)\t(\S+)/)
	{
	    print AA ">$1\n$3\n";
	}
    }
    close(AA);
    &FIG::run("add_rbs_data_for_start_predictions < $subdir/objects.with.potential.starts > $subdir/objects.with.rbs.scores");
    &FIG::run("add_start_data_for_start_predictions < $subdir/objects.with.rbs.scores > $subdir/objects.with.rbs.and.start.scores");

    if ((system("get_sims_for_start_predictions $orgdir_flag $subdir/AA_for_called_genes < $subdir/objects.to.build > $subdir/similarities") == 0) && 
	(system("add_sim_data_for_start_predictions $subdir/similarities $use_close < $subdir/objects.with.rbs.and.start.scores > $subdir/objects.with.all.scores") == 0))
    {
	&FIG::run("cat $subdir/objects.with.all.scores");
    }
    else
    {
	&FIG::run("cat $subdir/objects.with.rbs.and.start.scores");
    }
}
system("rm -rf $subdir");


MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3