[Bio] / FigKernelScripts / compute_contig_md5.pl Repository:
ViewVC logotype

View of /FigKernelScripts/compute_contig_md5.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.4 - (download) (as text) (annotate)
Wed Apr 11 17:47:15 2007 UTC (12 years, 10 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
Changes since 1.3: +90 -25 lines
rollup of metagenome server changes

#
# 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.
#

#
# Compute the MD5 checksum of a set of contigs.
#

use strict;
use Data::Dumper;
use Digest::MD5 'md5_hex';

my %contigs;
my $cur;

my $sig = 1;
if ($ARGV[0] eq '-nosig')
{
    $sig = 0;
    shift;
}

if ($sig)
{
    compute_contigs_with_sig();
}
else
{
    compute_contigs_streaming();
}

sub compute_contigs_streaming
{
    my $contig;
    my $cur;
    my $md5 = Digest::MD5->new;

    while (<>)
    {
	chomp;
	
	if (/^>(\S+).*/)
	{
	    if ($cur)
	    {
		show_contig($cur, $contig, $md5);
	    }
	    $cur = $1;
	    $md5 = Digest::MD5->new;
	}
	else
	{
	    #
	    # Remove whitespace and coerce to lower case.
	    #
	    s/\s*//;
	    $md5->add(lc($_));
	}
    }
    if ($cur)
    {
	show_contig($cur, $contig, $md5);
    }
}

sub show_contig
{
    my($id, $contig, $md5) = @_;
    
    my $contig_md5 = $md5->hexdigest;
	
    my $len = length($contig);

    print join("\t", $id, $len, $contig_md5) . "\n";
}

sub compute_contigs_with_sig
{
    
    while (<>)
    {
	chomp;
	
	if (/^>(\S+).*/)
	{
	    $cur = $1;
	}
	else
	{
	    #
	    # Remove whitespace and coerce to lower case.
	    #
	    s/\s*//;
	    $contigs{$cur} .= lc($_);
	}
    }
    
    #
    # The signature file consists of tab-separated lines
    # with contig name, length of nucleotide sequence, and md5checksum,
    # in order of contig name.
    # 
    
    my $signature = "";
    
    for my $contig_name (sort keys %contigs)
    {
	my $contig_md5 = md5_hex($contigs{$contig_name});
	
	my $len = length($contigs{$contig_name});
	$signature .= "$contig_name\t$len\t$contig_md5\n";
    }
    print "Signature:\n$signature";
    
    my $genome_md5sum = md5_hex($signature);

    print "Genome md5sum: $genome_md5sum\n";
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3