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

View of /FigKernelScripts/remove_sims_not_in_nr.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (download) (as text) (annotate)
Thu May 31 19:24:43 2007 UTC (12 years, 5 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, 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
Missing scripts.

########################################################################
#
# 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;
use Data::Dumper;
use strict;

my $usage = "Usage: $0 NR sims-in sims-out removed-file\n";

my($nrF,$in_dir, $out_dir, $removed_file);

(
 ($nrF     = shift @ARGV) &&
 ($in_dir = shift @ARGV) &&
 ($out_dir   = shift @ARGV) &&
 ($removed_file   = shift @ARGV)
)
    || die $usage;

opendir(SIMS,$in_dir)
    || die "could not open $in_dir";
my @files = grep { $_ !~ /^\./ } readdir(SIMS);
closedir(SIMS);

-d $out_dir and die "Output directory $out_dir already exists\n";

open(REM, ">$removed_file") or die "Cannot open $removed_file: $!\n";

mkdir($out_dir,0777) || die "could not make $out_dir";

#
# Scan the NR, collecting IDs into %seen.
#

print "Reading NR\n";
open(NR,"<$nrF") || die "could not open $nrF";

my %seen;
while (<NR>)
{
    if ($_ =~ /^>(\S+)/)
    {
	$seen{$1}++;
    }
}
close(NR);
system("ps u$$");

#
# Scan the sims, throwing out (writing to the removed file) sims that are not in
# the NR.
#

foreach my $file (sort @files)
{
    print STDERR "processing $file\n";

    open(OLD,"<$in_dir/$file")
        || die "could not open $in_dir/$file";
    open(NEW,">$out_dir/$file")
        || die "could not open $out_dir/$file";

    while (<OLD>)
    {
        if (/^(\S+)\t(\S+)/)
        {
	    if ($seen{$1} and $seen{$2})
	    {
		print NEW $_;
	    }
	    else
	    {
		print REM $_;
	    }
        }
        else
        {
	    warn "Invalid sim at $file line $.\n";
        }
    }
    close(NEW);
    close(OLD);
}
close(REM);

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3