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

View of /FigKernelScripts/remove_clustered_pchs.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.10 - (download) (as text) (annotate)
Fri Dec 15 20:52:38 2006 UTC (13 years, 3 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: +30 -10 lines
fix rfemove_clustered_PCHs to count correctly

#
# 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.
#


#
# The input to this script now has pegs in form of pairs of numbers, a mapped genome ID and
# a peg ID within that genome.
#
# We pass in a genome mapping file which consists of pairs (genome_id, mapped_id).
#
# We do our internal calculations in terms of the pairs, and rewrite to genome IDS
# on output.
#
###########################################
#
# RAO: I have changed this to keep all PCHs, but adding a code (0 means "do not count in score")
#

use strict;

use FIG;
my $fig = new FIG;

use DBrtns;
my $dbh = $fig->db_handle;

my $usage = "usage: remove_clustered_pchs CutOff < all_pchs > filtered_pchs";

my($cutoff, $genome_map);

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

my $pch = <STDIN>;
while ($pch && ($pch =~ /^(\d+\t\d+\t\d+\t\d+)/))
{
    my $curr = $1;
    my @set = ();

    #
    # The input is four "columns" of pegs, followed by two iden columsn and two paranN columns.
    # Each peg column is really a pair of numbers.
    #

    while ($pch and
	   $pch =~ /^((\d+\t\d+)\t(\d+\t\d+))\t   # first two. $1 is the pair.
	             (\d+\t\d+)\t		    # third peg col, $4.
	             (\d+\t\d+)\t		    # fourth peg col, $5
	   	     (\S+)\t(\S+)\t		    # and the iden  columns. $6 and $7
	   	     (\S+)\t(\S+)  	    	    # and the paran cols $8 and $9
	            /x and
	   ($1 eq $curr))
    {
	# print "got 1='$1' 4='$4' 5='$5' 6='$6' 7='$7'\n";

	#
	# We remap the line for output.
	#

	my $remap = join("\t",
			 remap($2), remap($3), remap($4), remap($5),
			 $6, $7, $8, $9);
	my $max_iden = ($6 < $7) ? $7 : $6;
	push(@set,[$4,$5,$remap,$max_iden]);
	$pch = <STDIN>;
    }
    &process_set($dbh,\@set);
}

# You have a list of PCHs.  Basically, we sort them based on max % identity
# between the corresponding genes in each PCH.
#
# We are trying to build a set of PCHs (marked by 1s) such that
#
#    1. The % identity is below the cutoff for each PCH and
#
#    2. The % identity between the "other" pairs of the PCHs is
#       always below the cutoff.
#
# 

sub process_set {
    my($dbh,$set) = @_;
    my($pch,$i);

    my @unprocessed = sort { $a->[3] <=> $b->[3] } @$set;
    if (@unprocessed > 0)
    {
	while ($pch = shift @unprocessed)
	{
	    #
	    # $pch here is a triple (peg3, peg4, whole line from file)
	    #
	    if ($pch->[3] <= $cutoff)
	    {
		print $pch->[2] . "\t1\n";
		my $too_close1 = &get_too_close($dbh,$pch->[0]);
		my $too_close2 = &get_too_close($dbh,$pch->[1]);
		for ($i = $#unprocessed; ($i >= 0); $i--)
		{
		    if ($too_close1->{$unprocessed[$i]->[0]} ||
			$too_close2->{$unprocessed[$i]->[1]})
		    {
			print $unprocessed[$i]->[2] . "\t0\n";
			splice(@unprocessed,$i,1);
		    }
		}
	    }
	    else
	    {
		print $pch->[2] . "\t0\n";
	    }
	}
    }
}
    
sub get_too_close {
    my($dbh,$peg) = @_;

    my($g, $p) = split(/\t/, $peg);

    my $too_close = {};
    my $res = $dbh->SQL("SELECT g2, p2 FROM condensed_sims WHERE ( g1 = ? and p1 = ? and iden >= ?)",
			undef, $g, $p, $cutoff);

    foreach my $ent (@$res)
    {
	my $mpeg = join("\t", @$ent);
	$too_close->{$mpeg} = 1;
    }
    return $too_close;
}

sub remap
{
    my($peg) = @_;

    #
    # Remap a "genome\tpeg" pair to a fig ID.
    #

    
    if ($peg =~ /^(\d+)\t(\d+)$/)
    {
	my $mapped = $fig->map_ids_to_peg($1, $2);
	return $mapped;
    }
    else
    {
	die "Peg '$peg' is of the wrong form";
    }
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3