[Bio] / FigKernelPackages / ANNO.pm Repository:
ViewVC logotype

View of /FigKernelPackages/ANNO.pm

Parent Directory Parent Directory | Revision Log Revision Log

Revision 1.1 - (download) (as text) (annotate)
Fri Dec 11 20:45:13 2009 UTC (10 years, 2 months ago) by olson
Branch: MAIN
new home for plain old methods to be invoked for the anno server. move metabolic reconstruction here.

#!/usr/bin/perl -w
use strict;

# 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.
package ANNO;

use strict;
use ERDB;
use Tracer;
use SeedUtils;
use ServerThing;

sub new {
    my ($class) = @_;
    # Create the sapling object.
    my $sap = ERDB::GetDatabase('Sapling');
    # Create the server object.
    my $retVal = { db => $sap };
    # Bless and return it.
    bless $retVal, $class;
    return $retVal;

=head2 Primary Methods

=head3 methods

    my $methodList =        $ssObject->methods();

Return a list of the methods allowed on this object.


use constant METHODS => [qw(metabolic_reconstruction

sub methods {
    # Get the parameters.
    my ($self) = @_;
    # Return the result.
    return METHODS;

# Docs are in ANNOserver.pm.

sub metabolic_reconstruction {
    # Get the parameters.
    my ($self, $args) = @_;

    my $sapling = $self->{db};
    my $retVal = [];

    # This counter will be used to generate user IDs for roles without them.
    my $next = 1000;

    my $id_roles = $args->{-roles};
    my @id_roles1 = map { (ref $_ ? $_ : [$_, "FR" . ++$next]) } @$id_roles;

    my @id_roles = ();
    foreach my $tuple (@id_roles1)
	my($function,$id) = @$tuple;
	foreach my $role (split(/(; )|( [\]\@] )/,$function))

    my %big;
    my $id_display = 1;
    map {push(@{$big{$_->[0]}}, $_->[1])} @id_roles;
    my @resultRows = $sapling->GetAll("Subsystem Includes Role", 
                            'ORDER BY Subsystem(id), Includes(sequence)', [], 
                            [qw(Subsystem(id) Role(id) Includes(abbreviation))]);
    my %ss_roles;
    foreach my $row (@resultRows) {
        my ($sub, $role, $abbr) = @$row;
        $ss_roles{$sub}->{$role} = $abbr;
    foreach my $sub (keys %ss_roles) {
        my $roles = $ss_roles{$sub};

        my @abbr = map{$roles->{$_}} grep { $big{$_}} keys %$roles;
        my $set =  join(" ",  @abbr);
        if (@abbr > 0) {
            my ($variant, $size) = $self->get_max_subset($sub, $set);
            if ($variant) {
                foreach my $role (keys %$roles) {
                    if ($id_display) {
                        foreach my $id (@{$big{$role}}) {
                            push (@$retVal, [$variant, $role, $id]);
                    } else {
                        push (@$retVal, [$variant, $role]);
    # Return the result.
    return $retVal;

=head2 Internal Utility Methods

=head3 get_max_subset

    my ($max_variant, $max_size) = $ssObject->get_max_subset($sub, $setA);

Given a subsystem ID and a role rule, return the ID of the variant for
the subsystem that matches the most roles in the rule and the number of
roles matched.

=over 4

=item sub

Name (ID) of the subsystem whose variants are to be examined.

=item setA

A space-delimited list of role abbreviations, lexically ordered. This provides
a unique specification of the roles in the set.

=item RETURN

Returns a 2-element list consisting of the ID of the variant found and the number
of roles matched.



sub get_max_subset {
    my ($self, $sub, $setA) = @_;
    my $sapling = $self->{db};
    my $max_size = 0;
    my $max_set;
    my $max_variant;
    my %set_hash;
    my $qh = $sapling->Get("Subsystem Describes Variant", 'Subsystem(id) = ? AND Variant(type) = ?', [$sub, 'normal']);
    while (my $resultRow = $qh->Fetch()) {
        my @variantRoleRule = $resultRow->Value('Variant(role-rule)');
        my ($variantCode) = $resultRow->Value('Variant(code)');
        my $variantId = $sub.":".$variantCode;
        foreach my $setB (@variantRoleRule) {
                    my $size = is_A_a_superset_of_B($setA, $setB);
                    if ($size  && $size > $max_size) {
                            $max_size = $size;
                            $max_set = $setB;
                            $max_variant = $variantId;
    #if ($max_size) {
            #print STDERR "Success $max_variant, $max_set\n";
    return($max_variant, $max_size);

=head3 is_A_a_superset_of_B

    my $size = SS::is_A_a_superset_of_B($a, $b);

This method takes as input two role rules, and returns 0 if the first
role rule is NOT a superset of the second; otherwise, it returns the size
of the second rule. A role rule is a space-delimited list of role
abbreviations in lexical order. This provides a unique identifier for a
set of roles in a subsystem.

=over 4

=item a

First role rule.

=item b

Second role rule.

=item RETURN

Returns 0 if the first rule is NOT a superset of the second and the size of the
second rule if it is. As a result, if the first rule IS a superset, this method
will evaluate to TRUE, and to FALSE otherwise.



sub is_A_a_superset_of_B {
    my ($a, $b) = @_;
    my @a = split(" ", $a);
    my @b = split(" ", $b);
    if (@b > @a) {
    my %given;
    map { $given{$_} = 1} @a;
    map { if (! $given{$_}) {return 0}} split(" ", $b);
    my $l = scalar(@b);
    return scalar(@b);


MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3