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

View of /FigKernelScripts/merge_families.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.3 - (download) (as text) (annotate)
Mon Aug 27 18:27:33 2007 UTC (12 years, 2 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 1.2: +1 -1 lines
add strip comments argument on function_of

########################################################################
#
# 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;
my $fig = new FIG;

use Subsystem;

$usage = "usage: merge_families FamDir membership-table1";

(
 ($fam_dir   = shift @ARGV) &&
 ($members   = shift @ARGV)
)
    || die $usage;

if (-e $fam_dir)
{
    die "$fam_dir already exists.  You should probably delete or save it and rerun";
}

&FIG::verify_dir("$fam_dir");
$dref = {};
open(LOG,">$fam_dir/log") || die "could not open $fam_dir/log";
open(MEMS,"sort -k2 -k1 $members |") || die "could not open $members";
$last = <MEMS>;
while ($last && ($last =~ /^(\S+)\t(\S+)/))
{
    $peg = $2;
    @fams = ();
    while ($last && ($last =~ /^(\S+)\t(\S+)/) && ($peg eq $2))
    {
	push(@fams,$1);
	$last = <MEMS>;
    }
    
    if (@fams > 1)
    {
	@fams = sort @fams;
	&merge($dref,\@fams,$peg,\*LOG);
    }
}
close(MEM);

$mergedF = "$FIG_Config::temp/merged$$";
open(MERGED,"| sort -u > $mergedF")
    || die "could not open $FIG_Config::temp/merged$$";
open(MEMS,"<$members") || die "could not open $members";
while (defined($_ = <MEMS>))
{
    if ($_ =~ /^(\S+)\t(\S+)/)
    {
	$peg = $2;
	$fam = $1;
	$fam = &dereference($fam,$dref);
	print MERGED "$fam\t$peg\n";
    }
}
close(MEM);
close(MERGED);
open(MERGED,"<$mergedF")
    || die "could not open $mergedF";
open(ALL,">$fam_dir/families") || die "could not open $fam_dir";

$_ = <MERGED>;
while ($_ && ($_ =~ /^(\S+)/))
{
    $fam = $1;
    @set = ();
    while ($_ && ($_ =~ /^(\S+)/) && ($fam eq $1))
    {
	push(@set,$_);
	$_ = <MERGED>;
    }

    if (@set > 1)
    {
	print ALL join("",@set);
    }
}
close(MERGED);
unlink($mergedF);

sub dereference {
    my($fam,$dref) = @_;

    while (my $to = $dref->{$fam})
    {
	$fam = $to;
    }
    return $fam;
}

sub merge {
    my($dref,$fams,$peg,$log_fh) = @_;
    
    my(%derefed,$fam,@whats_left,$i);
    my $in = join(",",@$fams);
    foreach $fam (@$fams)
    {
	$derefed{&dereference($fam,$dref)} = 1;
    }
    @whats_left = sort keys(%derefed);
    for ($i=1; ($i < @whats_left); $i++)
    {
	$dref->{$whats_left[$i]} = $whats_left[0];
	print $log_fh "$whats_left[$i]\t$whats_left[0]\t$peg\t$in\n";
    }
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3