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

View of /FigKernelScripts/make_protein_sets.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.

# -*- 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 Carp;
use Data::Dumper;
use strict;
use FIG;

my $fig = new FIG;
$| = 1;

my $usage = "usage: make_protein_sets Exemplars Nohits CutOff < sorted.counts > sets.file";

my($pair,$exemplars,$nohits,$cutoff);

(($exemplars = shift @ARGV) && open(EXEMPLARS,">$exemplars") &&
 ($nohits = shift @ARGV) && open(NOHITS,">$nohits") &&
 ($cutoff = shift @ARGV) 
 ) || die $usage;

my(%nr,$n,$id,@against,$id2,$x,$count,$id1,$sc);

open(TMP, "grep \"^>\" $FIG_Config::global/nr |") || die "Could not pipe-open $FIG_Config::global/nr";
while (defined($_ = <TMP>))
{
    if ($_ =~ /^>(\S+)/)
    {
	$nr{$1} = 1;
    }
}

print STDERR "processed nr\n";

$n = 1;
while (defined($_ = <STDIN>))
{
    if (($_ =~ /^(\d+)\t(\S+)/) && (($count,$id) = ($1,$2)) && $nr{$id})
    {
	if ($count >= 2)
	{
	    @against = ();
	    foreach $id2 (map { $_->id2 } $fig->sims($id,100000,1.0e-5,"raw"))
	    {
		if ($nr{$id2})
		{
		    push(@against,$id2);
		}
	    }

	    if (@against > 2)
	    {
		print EXEMPLARS "$n\t$id\n";
		foreach $_ (($id,@against))
		{
		    $nr{$_} = 0;
		    print "$n\t$_\n";
		}
		$n++;
	    }
	}
    }
}

foreach $id (sort keys(%nr))
{
    if ($nr{$id})
    {
	print NOHITS "$id\n";
    }
}

undef $fig;

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3