Summary

G::Seq::Operon - Retrieves operon information for bacterial genoms

Package variables

Included modules

Inherit

Exporter

Synopsis

No synopsis!

Description

    This class is a part of G-language Genome Analysis Environment, 
    collecting sequence analysis methods related to operons.

Methods

Methods description

  Name: set_operon   -   set operon information from RegulonDB/ODB

  Description:
    This program retrieves the operon information from 
      1. RegulonDB for Escherichia coli K12 chromosome
      2. DOOR for other bacteria and plasmids
    and annotation to the given genome data. 

    Two attributes are added to each CDS hash.
        $genome->{$cds}->{operon}
    contains the name of the operon to which the gene belongs, and 
        $genome->{$cds}->{operonN}
    contains the rank order of the gene within the operon.
        $genome->{$cds}->{operonEvidence}
    contains evidence of the operon information (available for E.coli only)

  Usage:
    set_operon($gb);

 Options:
   None.

  References:
   1. Gama-Castro S et al. (2008) "RegulonDB (version 6.0): gene regulation model 
      of Escherichia coli K-12 beyond transcription, active (experimental) annotated 
      promoters and Textpresso navigation.", Nucleic Acids Res. 1;36(Database issue):D120-4

   2. Mao F et al. (2009) "DOOR: a database for prokaryotic operons", 
      Nucleic Acids Res. 1;37(Database issue):D459-D463

  Author: 
    Kazuharu Arakawa (gaou@sfc.keio.ac.jp)

  History:
   20090322-01 added support for DOOR (stopped using Operon Database)
   20090313-01 added support for other organisms using Operon Database
   20090313-02 modified to match latest version of RegulonDB format (6.0)
   20070829-01 patched to match latest version of RegulonDB formamt
               (patch by Hiroyuki Nakamura <t04632hn@sfc.keio.ac.jp>
   20061003-01 updated to use data from RegulonDB
   20020207-01 initial posting

Methods code

sub set_operon {

    my @args = opt_get(@_);
    my $gb = opt_as_gb(shift @args);

    if ($gb->{LOCUS}->{id} eq 'U00096' || $gb->{LOCUS}->{id} eq 'NC_000913'){

	my $url = "http://regulondb.ccg.unam.mx:80/data/OperonSet.txt";
	my $dir = $ENV{HOME} . '/.glang/data/OperonSet.txt';
	mirror($url, $dir);
	die("setOperon: cannot retrieve data from RegulonDB.") unless(-e $dir);

	my $flag = 0;
	open(FILE, $dir) || die($!);
	while (<FILE>) {
	    chomp;
	    my $line = $_;

	    if (/^Columns\:/) {
	      $flag++;
	      next;
	    }
	    elsif(/^\s+\(\d\)\s/) {
	      $flag++;
	      next;
	    }

	    if($flag == 6){
		my %geneOrder;

		my ($operon, $num, $direction, $genes, $evidence) = split(/\t/, $_, 5);
		next unless($num >= 2);

		foreach my $genepair (split(/,/, $genes)){
		    my ($gene, $locustag) = split(/\|/, $genepair, 2);
		    my $cds = $gb->gene2id($locustag);

		    $cds = $gb->gene2id($gene) unless(length $cds);

		    if($cds){
			$gb->{$cds}->{operon} = $operon;
			$gb->{$cds}->{operonEvidence} = $evidence;
			$geneOrder{$cds} = $gb->{$cds}->{start};
		    }
		}

		my $i = 1;
		if($direction eq 'forward'){
		    foreach my $cds (sort {$geneOrder{$a} <=> $geneOrder{$b}} keys %geneOrder){
			$gb->{$cds}->{operonN} = $i;
			$i ++;
		    }
		}else{
		    foreach my $cds (sort {$geneOrder{$b} <=> $geneOrder{$a}} keys %geneOrder){
			$gb->{$cds}->{operonN} = $i;
			$i ++;
		    }
		}
	    }else{
		$line =~ s/[^a-zA-Z0-9\-,\.\(\):\"\' ]//g;
		msg_error($line, "\n");
	    }
	}
	close(FILE);

	foreach my $cds ($gb->cds()){
	    $gb->{$cds}->{operonN} = 0 unless(length $gb->{$cds}->{operon});
	}

    }else{
	my $url = 'http://csbl1.bmb.uga.edu/OperonDB/downloadNCoperon.php?NC_id=' . $gb->{LOCUS}->{id};
	my $dir = $ENV{HOME} . '/.glang/data/Operon' . $gb->{LOCUS}->{id} . '.txt';
	mirror($url, $dir);
	die("No Operon data for this species.\n\n") unless(-e $dir);

	my $data = {};
	open(FILE, $dir) || die($!);
	while (<FILE>) {
	    chomp;
	    my ($operonName, $gi, $gene, undef) = split(/\s+/, $_, 4);
	    push(@{$data->{$operonName}}, $gene);
	}
	close(FILE);

	foreach my $operonName (keys %{$data}){
	    my @list = @{$data->{$operonName}};
	    @list = reverse(@operons) if($gb->{$operons[0]}->{direction} eq 'complement');
	    
	    my $i = 1;
	    foreach my $cds (@list){
		$gb->{$cds}->{operon} = $operonName;
		$gb->{$cds}->{operonN} = $i;
		$i ++;
	    }
	}
	
	foreach my $cds ($gb->cds()){
	    $gb->{$cds}->{operonN} = 0 unless(length $gb->{$cds}->{operon});
	}
    }

    return $gb;

}

General documentation