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

View of /FigKernelScripts/extract_data_to_keep.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.5 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 2005 UTC (14 years, 2 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 1.4: +17 -0 lines
Add license words.

#
# 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;

$usage = "usage: extract_data_to_keep [-v] FileOfKeptGenomes Data SkeletalToKeep";

my $to_del = 0;
if ((@ARGV == 4) && ($ARGV[0] eq "-v"))
{
    shift @ARGV;
    ($deleted,$data_dir,$kept) = @ARGV;
    %deleted_genomes = map { $_ =~ /(\S+)/; $1 => 1 } `cat $deleted`;
    %kept_genomes = map { $_ => 1 } grep { ! $deleted{$_} } $fig->genomes;
}
elsif (@ARGV == 3)
{
    ($kept_genomes,$data_dir,$kept) = @ARGV;
    %kept_genomes = map { $_ =~ /(\S+)/; $1 => 1 } `cat $kept_genomes`;
}
else
{
    die $usage;
}

(! -d $kept) || die "$kept already exists";
mkdir($kept,0777) || die "could not make $kept";
mkdir("$kept/Organisms",0777) || die "could not make $kept/Organisms";

opendir(ORG,"$data_dir/Organisms") || die "could not open $data_dir/Organisms";
@orgs = grep { ($_ =~ /^\d+\.\d+$/) && $kept_genomes{$_} }  readdir(ORG);
closedir(ORG);
foreach $org (@orgs)
{
    mkdir("$kept/Organisms/$org",0777) || die "could not make $kept/$org";
    if (-s "$data_dir/Organisms/$org/assigned_functions")
    {
	&FIG::run("cp $data_dir/Organisms/$org/assigned_functions $kept/Organisms/$org/assigned_functions");
    }
    if (-s "$data_dir/Organisms/$org/annotations")
    {
	&FIG::run("cp $data_dir/Organisms/$org/annotations $kept/Organisms/$org/annotations");
    }
    if (-d "$data_dir/Organisms/$org/UserModels")
    {
	&FIG::run("cp -r $data_dir/Organisms/$org/UserModels $kept/Organisms/$org/UserModels");
    }
}

&copy_subsystems(\%kept_genomes,"$data_dir/Subsystems","$kept/Subsystems");

sub copy_subsystems {
    my($kept_genomes,$subsystemsF,$subsystemsT) = @_;
    my($file,$ssa);

    if (opendir(TMP,$subsystemsF))
    {
	mkdir($subsystemsT,0777) || die "could not make $subsystemsT";
	my @ssas = grep { $_ !~ /^\./ } readdir(TMP);
	closedir(TMP);

	foreach $ssa (@ssas)
	{
	    mkdir("$subsystemsT/$ssa",0777) || die "could not make $subsystemsT/$ssa";
	    if (opendir(TMP,"$subsystemsF/$ssa"))
	    {
		my @files = grep { $_ !~ /^\./ } readdir(TMP);
		closedir(TMP);
		foreach $file (@files)
		{
		    if ($file ne "spreadsheet")
		    {
			system "cp -r \"$subsystemsF/$ssa/$file\" \"$subsystemsT/$ssa/$file\"";
		    }
		    else
		    {
			open(IN,"<$subsystemsF/$ssa/spreadsheet") || die "could not open $subsystemsF/$ssa/spreadsheet";
			open(OUT,">$subsystemsT/$ssa/spreadsheet") || die "could not open $subsystemsT/$ssa/spreadsheet";
			$/ = "//\n";
			my($set,$line);
			if ($set = <IN>)
			{
			    print OUT $set;
			    if ($set = <IN>)
			    {
				print OUT $set;
				$/ = "\n";
				while (($line = <IN>) && ($line !~ /^\/\//))
				{
				    if (($line =~ /^(\d+\.\d+)/) && $kept_genomes->{$1})
				    {
					print OUT $line;
				    }
				}
				
				while ($line)
				{
				    print OUT $line;
				    $line = <IN>;
				}
			    }
			}
			close(IN);
			close(OUT);
			
		    }
		}
	    }
	}
    }
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3