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

View of /FigKernelScripts/compute_new_ids.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.2 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 2005 UTC (13 years, 11 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 1.1: +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.
#


#
# Given:
#
#    an ID mapping file that looks like this:
#
# fig|9999999.1.peg.929074	fig|9999999.1.peg.929074
# fig|9999999.1.peg.568952	fig|9999999.1.peg.568952
# fig|9999999.1.peg.902009	fig|9999999.1.peg.902009
# fig|9999999.1.peg.954630	fig|9999999.1.peg.954630
# fig|9999999.1.peg.550866	fig|9999999.1.peg.550866
# fig|9999999.1.peg.886341	fig|9999999.1.peg.886341
# gi|48786064	gi|48786064
# uni|Q7XX34	uni|Q7XX34
# uni|Q7SIE1	uni|Q7SIE1
# uni|Q9TL34	uni|Q9TL34
#
# and a new NR, we wish to determine which sequences are in the new NR but
# not in the old mapping file. These are sequences for which we need
# to compute new sims. We do this by building a mapping from
# new sequence -> old sequence from the mapping file, walking the new NR,
# and writing any sequences that do not have a mapping.
#

use strict;

my($usage, $new_nr, $mapfile);

$usage = "usage: $0 NewNR id-mapping";

(($new_nr = shift @ARGV) &&
 ($mapfile = shift @ARGV)
 ) || die $usage;


my $idmap = load_mapfile($mapfile);

my $nrfh;

open($nrfh, "<$new_nr") or die;

while (<$nrfh>)
{
    chomp;

    if (/^>(\S+)\s*/)
    {
	my $id = $1;
	if (!$idmap->{$id})
	{
	    print "$id\n";
	}
    }
}


sub load_mapfile
{
    my($mapfile) = @_;
    my $fh;
    my $map = {};

    open($fh, "<$mapfile") or die;

    my $n = 0;
    while (<$fh>)
    {
	chomp;
	my($old, $new) = split(/\t/);
	$map->{$new} = $old;

    }
    warn "Done with loadmap\n";
    
    return $map;
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3