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

View of /FigKernelScripts/install_new_coupling_data.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.3 - (download) (as text) (annotate)
Thu Oct 4 19:27:00 2007 UTC (12 years, 1 month 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, 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: +20 -6 lines
add option to install from a jobdir

# -*- 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 strict;
use Carp;
use Data::Dumper;
use File::Copy;

#
# Install newly computed PCH data.
#
# For each file in the pchdir, skip if zero length.
# See if we already have a file with that name (genome) in the CouplingData/PCHs directory.
# If we do, we will replace it, and remove the scores for that genome's pegs from the
# CouplingData/scores file.
#
# Compute scores for the files we have added, and append to the scores file.
#

use FIG;
use FIG_Config;

my $usage = "usage: install_new_coupling_data [-jobdir jobdir] [Genome PCHs Scores]";

my($genome, $pchs_file, $scores_file);

if (@ARGV ==2 and $ARGV[0] eq '-jobdir')
{
    my $jd = $ARGV[1];

    $genome = &FIG::file_head("$jd/GENOME_ID");
    chomp $genome;
    $genome =~ /^\d+\.\d+$/ or die "Invalid jobdir or GENOME_ID file";
    $pchs_file = "$jd/rp/$genome/pchs";
    $scores_file = "$jd/rp/$genome/pchs.scored";
}
elsif (@ARGV == 3)
{
    $genome = shift;
    $pchs_file = shift;
    $scores_file = shift;
}
else
{
    die $usage;
}

$genome =~ /^\d+\.\d+$/ or die "Invalid genome identifier $genome\n";
open(PCHS, "<$pchs_file") or die "Cannot open pchs file $pchs_file: $!";
open(SCORES, "<$scores_file") or die "Cannot open scores file $scores_file: $!";

my $did_replace;

my $dest = "$FIG_Config::data/CouplingData/PCHs/$genome";
if (-f $dest)
{
    print "Replacing $genome\n";
    copy($dest, "$FIG_Config::temp/$genome.$$") or die "Cannot copy $dest to $FIG_Config::temp/$genome.$$: $!\n";
    print "Moved $dest to $FIG_Config::temp/pchs.$genome.$$\n";
    $did_replace = 1;
}
else
{
    print "New coupling data for $genome\n";
}
copy($pchs_file, $dest) or die "Cannot copy $pchs_file to $dest: $!\n";

#
# If we replaced, remove the replacement scores from the scores file.
#

my $scores = "$FIG_Config::data/CouplingData/scores";
if ($did_replace)
{
    my $bak = "$scores.bak.$$";
    rename($scores, $bak) or die "Cannot rename $scores $bak: $!\n";

    open(B, "<$bak") or die "Cannot open $bak: $!\n";
    open(S, ">$scores") or die "Cannot open $scores for writing: $!\n";

    while (<B>)
    {
	if (/^fig\|(\d+\.\d+)\.peg\.\d+/)
	{
	    if ($1 ne $genome)
	    {
		print S $_;
	    }
	}
    }
    close(B);
    close(S);
}

open(S, ">>$scores") or die "Cannot open $scores for append: $!\n";
copy(\*SCORES, \*S);
close(S);
close(SCORES);

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3