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

View of /FigKernelScripts/complete_genomes.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.7 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 2005 UTC (14 years, 3 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 1.6: +17 -0 lines
Add license words.

# -*- 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.
#


=pod

=head1 complete_genomes.pl

This script will try and identify those genomes that are "complete". It is based on a heuristic developed by Gary Olsen, see http://fogbugz.nmpdr.org/default.php?pg=pgEditBug&command=view&ixBug=94 for more details.

The basic rule of thumb is that more than 70% of the nucleotides in total must be in contigs > 20 kb.

=cut

use strict;
use FIG;


my $usage=<<EOF;

$0 [-e|-b] -v


One of either -e or -b must be provided
	-e check eukaryotes
	-b check bacteria
	-a check archea
	-z check all genomes
	
-v verbose output

EOF


# figure out any command line options
my ($check_domain, $verbose)=(undef, 0);

while (@ARGV)
{
 my $try=shift(@ARGV);
 if ($try eq "-e") {$check_domain="Eukaryota"}
 elsif ($try eq "-b") {$check_domain="Bacteria"}
 elsif ($try eq "-a") {$check_domain="Archaea"}
 elsif ($try eq "-z") {$check_domain="all"}
 elsif ($try eq "-v") {$verbose=1}
}


die $usage unless ($check_domain);

my $fig=new FIG;

# first find out how many nucleotides we have, and how many contigs we have > 20 kb

print join "\t", "Genome ID", "Genome", "Domain", "Number of contigs", "Number of contigs > 20 kb", "Total length", "Total length in contigs > 20kb", "Fraction of bases in contigs > 20kb", "Complete", "Status", "Conflict", "\n";

if ($check_domain eq "all") {$check_domain=''}
foreach my $genome ($fig->genomes(undef, undef, $check_domain))
{
 my ($totallength, $contigs, $length_big, $number_big)=(0,0,0,0); 
 print STDERR "Checking ", $fig->genus_species($genome), "\n" if ($verbose);
 foreach my $contig ($fig->all_contigs($genome))
 {
  my $len=$fig->contig_ln($genome, $contig);
  $contigs++;
  $totallength+=$len;
  if ($len > 20000) {$length_big += $len; $number_big++}
 }
 
 # check to see whether the genome has the tag "status"
 my @statii=$fig->get_attributes($genome, "STATUS");
 my $status='';
 $statii[0] && ($status=$statii[0]->[2]);
 my $conflict='';
  
 # rules for the conflicts:
 # 1. >70% of sequence in contigs >20kb is complete
 # 2. status should be "complete"
 # 3. complete should be true
 
 if ($length_big/$totallength > 0.70)
 {
   # this should be considered complete
   $conflict = 1 if (lc($status) ne "complete");
   $conflict = 1 if (!$fig->is_complete($genome));
 }
 else 
 {
   # this should not be complete
   $conflict = 1 if (lc($status) ne "incomplete");
   $conflict = 1 if ($fig->is_complete($genome));
 }
 

 
 print join "\t", $genome, $fig->genus_species($genome), $fig->genome_domain($genome), $contigs, $number_big, $totallength, $length_big, $length_big/$totallength, $fig->is_complete($genome), $status, $conflict, "\n";
}
 

 

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3