bool TestGtrGammaLikelihood::run( void ) {
    
    /* First, we read in the data */
    // the matrix
    NclReader reader = NclReader();
    std::vector<AbstractCharacterData*> data = reader.readMatrices(alignmentFilename);
	
	AbstractDiscreteCharacterData *discrD = dynamic_cast<AbstractDiscreteCharacterData* >(data[0]);
    
	std::cout << "Read " << data.size() << " matrices." << std::endl;
    
    std::vector<TimeTree*> trees = NclReader().readTimeTrees( treeFilename );
    std::cout << "Read " << trees.size() << " trees." << std::endl;
    std::cout << trees[0]->getNewickRepresentation() << std::endl;
    
    /* set up the model graph */
    
    //////////////////////
    // first the priors //
    //////////////////////
        
    // then the parameters
    ConstantNode<RbVector<double> > *pi = new ConstantNode<RbVector<double> >( "pi", new RbVector<double>(4, 1.0/4.0) );
    ConstantNode<RbVector<double> > *er = new ConstantNode<RbVector<double> >( "er", new RbVector<double>(6, 1.0/6.0) );
    
    //Rate heterogeneity
    ConstantNode<double> *alpha = new ConstantNode<double>("alpha", new double(0.5) );
    
    std::cout << "alpha:\t" << alpha->getValue() << std::endl;
    
    ConstantNode<double> *q1 = new ConstantNode<double>("q1", new double(0.125) );
    DeterministicNode<double> *q1_value = new DeterministicNode<double>("q1_value", new QuantileFunction(q1, new GammaDistribution(alpha, alpha) ) );
    ConstantNode<double> *q2 = new ConstantNode<double>("q2", new double(0.375) );
    DeterministicNode<double> *q2_value = new DeterministicNode<double>("q2_value", new QuantileFunction(q2, new GammaDistribution(alpha, alpha) ) );
    ConstantNode<double> *q3 = new ConstantNode<double>("q3", new double(0.625) );
    DeterministicNode<double> *q3_value = new DeterministicNode<double>("q3_value", new QuantileFunction(q3, new GammaDistribution(alpha, alpha) ) );
    ConstantNode<double> *q4 = new ConstantNode<double>("q4", new double(0.875) );
    DeterministicNode<double> *q4_value = new DeterministicNode<double>("q4_value", new QuantileFunction(q4, new GammaDistribution(alpha, alpha) ) );
    
//    ConstantNode<double> *q1_value = new ConstantNode<double>("q1_value", new double(1.0) );
//    ConstantNode<double> *q2_value = new ConstantNode<double>("q2_value", new double(1.0) );
//    ConstantNode<double> *q3_value = new ConstantNode<double>("q3_value", new double(1.0) );
//    ConstantNode<double> *q4_value = new ConstantNode<double>("q4_value", new double(1.0) );
    
    
    std::vector<const TypedDagNode<double>* > gamma_rates = std::vector<const TypedDagNode<double>* >();
    gamma_rates.push_back(q1_value);
    gamma_rates.push_back(q2_value);
    gamma_rates.push_back(q3_value);
    gamma_rates.push_back(q4_value);
    
    DeterministicNode<RbVector<double> > *site_rates = new DeterministicNode<RbVector<double> >( "site_rates", new VectorFunction<double>(gamma_rates) );
    ConstantNode<double> *sumNV = new ConstantNode<double>("sumnv", new double(1.0) );
//    ConstantNode<std::vector<double> > *site_rate_probs = new ConstantNode<std::vector<double> >( "site_rate_probs", new std::vector<double>(4,1.0/4.0) );
        
//    std::cout << "pi:\t" << pi->getValue() << std::endl;
//    std::cout << "er:\t" << er->getValue() << std::endl;
    std::cout << "rates:\t" << site_rates->getValue() << std::endl;
    
    DeterministicNode<RbVector<double> > *site_rates_norm = new DeterministicNode<RbVector<double> >( "site_rates_norm", new NormalizeVectorFunction(site_rates, sumNV) );
    std::cout << "rates:\t" << site_rates_norm->getValue() << std::endl;
    
    DeterministicNode<RateMatrix> *q = new DeterministicNode<RateMatrix>( "Q", new GtrRateMatrixFunction(er, pi) );
    
    std::cout << "Q:\t" << q->getValue() << std::endl;
    
    ConstantNode<TimeTree> *tau = new ConstantNode<TimeTree>( "tau", new TimeTree( *trees[0] ) );
    std::cout << "tau:\t" << tau->getValue() << std::endl;
    
    // and the character model
    size_t numChar = data[0]->getNumberOfCharacters();
//    GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree> *charModel = new GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree>(tau, 4, true, numChar );
    PhyloCTMCSiteHomogeneousNucleotide<DnaState, TimeTree> *charModel = new PhyloCTMCSiteHomogeneousNucleotide<DnaState, TimeTree>(tau, true, numChar );
    charModel->setRateMatrix( q );
    charModel->setSiteRates( site_rates_norm );
//    charModel->setClockRate( clockRate );
    
    StochasticNode< AbstractDiscreteCharacterData > *charactermodel = new StochasticNode< AbstractDiscreteCharacterData >("S", charModel );
    charactermodel->clamp( discrD );
    
    std::cout << "BEAST LnL:\t\t\t\t" << -6281.4026 << std::endl;
    std::cout << "RevBayes LnL:\t\t" << charactermodel->getLnProbability() << std::endl;
    
    std::cout << "Finished GTR+Gamma model test." << std::endl;
    
    return true;
}
bool TestUCLNRelaxedClockBHT92Model::run( void ) {
    
    std::vector<unsigned int> seeds;
    seeds.push_back(7);
    seeds.push_back(4);
    GLOBAL_RNG->setSeed( seeds );
    
    /* First, we read in the data */
    // the matrix
    std::vector<AbstractCharacterData*> data = NclReader::getInstance().readMatrices(alignmentFilename);
    std::cout << "Read " << data.size() << " matrices." << std::endl;
    std::cout << data[0] << std::endl;
    
    std::vector<TimeTree*> trees = NclReader::getInstance().readTimeTrees( treeFilename );
    std::cout << "Read " << trees.size() << " trees." << std::endl;
    std::cout << trees[0]->getNewickRepresentation() << std::endl;
    
    
    /* set up the model graph */
    
    //////////////////////
    // first the priors //
    //////////////////////
    
    // birth-death process priors
    StochasticNode<double> *div = new StochasticNode<double>("diversification", new UniformDistribution(new ConstantNode<double>("div_lower", new double(0.0)), new ConstantNode<double>("div_upper", new double(100.0)) ));
    ConstantNode<double> *turn = new ConstantNode<double>("turnover", new double(0.0));
    ConstantNode<double> *rho = new ConstantNode<double>("rho", new double(1.0));
    
	
    // Setting up the substitution model //
	
    //ts/tv ratio:
    ConstantNode<double > *tstv_prior = new ConstantNode<double >( "tstv_prior", new double(0.25) );
    ContinuousStochasticNode *tstv = new ContinuousStochasticNode("tstv", new ExponentialDistribution(tstv_prior) );
	
    //GC content prior:
    ConstantNode<double > *eq_gc_prior = new ConstantNode<double >( "eq_gc_prior_ab", new double(1.0) );    
	
    //Root GC frequency
    
    StochasticNode< double  > *omega = new StochasticNode< double >( "omega", new BetaDistribution(eq_gc_prior,eq_gc_prior) );
    DeterministicNode<std::vector<double> > *rf = new DeterministicNode< std::vector<double> >( "rf", new NucleotideFrequenciesFromGcContentFunction( omega ) );
	
    std::cout << "omega:\t" << omega->getValue() << std::endl;
    std::cout << "rf:\t" << rf->getValue() << std::endl;
    std::cout << "tstv:\t" << tstv->getValue() << std::endl;
    
    //Declaring a vector of matrices, one per branch
    size_t numBranches = 2*data[0]->getNumberOfTaxa() - 2;
    std::vector<ContinuousStochasticNode*> thetas;
    std::vector< const TypedDagNode < RateMatrix >* > qs;
	
	//Equilibrium GC frequency: one per branch, defined in the loop along with the T92 rate matrices.
    for (unsigned int i = 0 ; i < numBranches ; i++ ) {
        std::ostringstream eq_gc_name;
        eq_gc_name << "eq_gc(" << i << ")";
        thetas.push_back(new ContinuousStochasticNode( eq_gc_name.str(), new BetaDistribution(eq_gc_prior,eq_gc_prior) ) );
		std::ostringstream q_name;
        q_name << "q(" << i << ")";
		qs.push_back(new DeterministicNode< RateMatrix >( q_name.str(), new Tamura92RateMatrixFunction( thetas[i], tstv) ));
        //std::cout << "Matrix Q:\t"<<i<<"\t" << qs[i]->getValue() << std::endl;
    }
    
	//Build a node out of the vector of nodes
    DeterministicNode< RbVector< RateMatrix > >* qs_node = new DeterministicNode< RbVector< RateMatrix > >( "q_vector", new RbVectorFunction<RateMatrix>(qs) );
    
	
	// Setting up the relaxed clock model //

    ConstantNode<double> *a = new ConstantNode<double>("a", new double(0.5) );
    ConstantNode<double> *b = new ConstantNode<double>("b", new double(0.25) );

	
	std::vector<const TypedDagNode<double> *> branchRates;
	std::vector< ContinuousStochasticNode *> branchRates_nonConst;
	for( size_t i=0; i<numBranches; i++){
        std::ostringstream br_name;
        br_name << "br(" << i << ")";
		ContinuousStochasticNode* tmp_branch_rate = new ContinuousStochasticNode( br_name.str(), new LognormalDistribution(a, b, new ConstantNode<double>("offset", new double(0.0) )));
		branchRates.push_back( tmp_branch_rate );
		branchRates_nonConst.push_back( tmp_branch_rate );
	}
	//Build a node out of the vector of nodes
    DeterministicNode< std::vector< double > >* br_vector = new DeterministicNode< std::vector< double > >( "br_vector", new VectorFunction< double >( branchRates ) );

	
	
	// Putting it all together //

	
    std::vector<std::string> names = data[0]->getTaxonNames();
    ConstantNode<double>* origin = new ConstantNode<double>( "origin", new double( trees[0]->getRoot().getAge()*2.0 ) );
    StochasticNode<TimeTree> *tau = new StochasticNode<TimeTree>( "tau", new ConstantRateBirthDeathProcess(origin, div, turn, rho, "uniform", "survival", int(names.size()), names, std::vector<Clade>()) );
    
	//If we want to get a good starting tree
	//    tau->setValue( trees[0] );
    std::cout << "tau:\t" << tau->getValue() << std::endl;
    
    // and the character model
	//    StochasticNode<CharacterData<DnaState> > *charactermodel = new StochasticNode<CharacterData <DnaState> >("S", new SimpleGTRBranchRateTimeCharEvoModel<DnaState, TimeTree>(tau, q, br_vector, true, data[0]->getNumberOfCharacters()) );
    
    GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree> *phyloCTMC = new GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree>(tau, 4, true, data[0]->getNumberOfCharacters());
    phyloCTMC->setRootFrequencies( rf );
    phyloCTMC->setRateMatrix( qs_node );
    phyloCTMC->setClockRate( br_vector );
	StochasticNode< AbstractCharacterData > *charactermodel = new StochasticNode< AbstractCharacterData >("S", phyloCTMC );
	charactermodel->clamp( data[0] );
    	
    
    /* add the moves */
    RbVector<Move> moves;
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(div, 1.0), 2, true ) );
    moves.push_back( new NearestNeighborInterchange( tau, 5.0 ) );
    moves.push_back( new NarrowExchange( tau, 10.0 ) );
    moves.push_back( new FixedNodeheightPruneRegraft( tau, 2.0 ) );
    moves.push_back( new SubtreeScale( tau, 5.0 ) );
    moves.push_back( new TreeScale( tau, 1.0, true, 2.0 ) );
    moves.push_back( new NodeTimeSlideUniform( tau, 30.0 ) );
    moves.push_back( new RootTimeSlide( tau, 1.0, true, 2.0 ) );
    moves.push_back( new BetaSimplexMove( omega, 10.0, true, 2.0 ) );
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(tstv, 1.0), 2, true ) );
	
    for (unsigned int i = 0 ; i < numBranches ; i ++ ) {
        moves.push_back( new BetaSimplexMove( dynamic_cast<StochasticNode<double>* >(thetas[i]), 10.0, true, 2.0 ) );
        moves.push_back( new SlidingMove( thetas[i], 0.05, true, 2.0) );
        //    moves.push_back( new SimplexMove( ers[i], 100.0, 6, true, 2.0 ) );
		//        moves.push_back( new SimplexMove( pis[i], 100.0, 4, true, 2.0 ) );
    }
    
    // add some tree stats to monitor
    DeterministicNode<double> *treeHeight = new DeterministicNode<double>("TreeHeight", new TreeHeightStatistic(tau) );
    
    /* add the monitors */
    RbVector<Monitor> monitors;
    std::set<DagNode*> monitoredNodes;
    //    monitoredNodes.insert( er );
    //    monitoredNodes.insert( pi );
    monitoredNodes.insert( div );
    monitors.push_back( new FileMonitor( monitoredNodes, 10, "TestUCLNRelaxedClockBHT92Model.log", "\t" ) );
    std::set<DagNode*> monitoredNodes1;
	//    monitoredNodes1.insert( er );
    for (unsigned int i = 0 ; i < numBranches ; i ++ ) {
        monitoredNodes1.insert( thetas[i] );
    }
    monitoredNodes1.insert( rf );
    monitoredNodes1.insert( treeHeight );
    monitors.push_back( new FileMonitor( monitoredNodes1, 10, "TestUCLNRelaxedClockBHT92ModelSubstRates.log", "\t" ) );
    monitors.push_back( new ScreenMonitor( monitoredNodes1, 10, "\t" ) );
    std::set<DagNode*> monitoredNodes2;
    monitoredNodes2.insert( tau );
    monitors.push_back( new FileMonitor( monitoredNodes2, 10, "TestUCLNRelaxedClockBHT92Model.tree", "\t", false, false, false ) );
    
    /* instantiate the model */
    Model myModel = Model(qs[0]);
    
    /* instiate and run the MCMC */
    Mcmc myMcmc = Mcmc( myModel, moves, monitors );
    myMcmc.run(mcmcGenerations);
    
    myMcmc.printOperatorSummary();
    
    /* clean up */
    //    for (size_t i = 0; i < 10; ++i) {
    //        delete x[i];
    //    }
    //    delete [] x;
    delete div;
    //    delete sigma;
    //    delete a;
    //    delete b;
    //    delete c;
    
    std::cout << "Finished GTR model test." << std::endl;
    
    return true;
}
예제 #3
0
bool TestGtrGammaModel::run( void ) {
    
    /* First, we read in the data */
    // the matrix
    NclReader& reader = NclReader::getInstance();
    std::vector<AbstractCharacterData*> data = reader.readMatrices(alignmentFilename);
    std::cout << "Read " << data.size() << " matrices." << std::endl;
    
    std::vector<TimeTree*> trees = NclReader::getInstance().readTimeTrees( treeFilename );
    std::cout << "Read " << trees.size() << " trees." << std::endl;
    std::cout << trees[0]->getNewickRepresentation() << std::endl;
    
    /* set up the model graph */
    
    //////////////////////
    // first the priors //
    //////////////////////
    
    // birth-death process priors
    StochasticNode<double> *div = new StochasticNode<double>("diversification", new UniformDistribution(new ConstantNode<double>("", new double(0.0)), new ConstantNode<double>("", new double(100.0)) ));
    ConstantNode<double> *turn = new ConstantNode<double>("turnover", new double(0.0));
    ConstantNode<double> *rho = new ConstantNode<double>("rho", new double(1.0));
    // gtr model priors
    ConstantNode<std::vector<double> > *bf = new ConstantNode<std::vector<double> >( "bf", new std::vector<double>(4,1.0) );
    ConstantNode<std::vector<double> > *e = new ConstantNode<std::vector<double> >( "e", new std::vector<double>(6,1.0) );
    
    std::cout << "bf:\t" << bf->getValue() << std::endl;
    std::cout << "e:\t" << e->getValue() << std::endl;
    
    // then the parameters
    StochasticNode<std::vector<double> > *pi = new StochasticNode<std::vector<double> >( "pi", new DirichletDistribution(bf) );
    StochasticNode<std::vector<double> > *er = new StochasticNode<std::vector<double> >( "er", new DirichletDistribution(e) );
    
    //Rate heterogeneity
    ConstantNode<double> *alpha_prior = new ConstantNode<double>("alpha_prior", new double(0.5) );
    ContinuousStochasticNode *alpha = new ContinuousStochasticNode("alpha", new ExponentialDistribution(alpha_prior) );
    
    alpha->setValue( new double(0.5) );
    std::cout << "alpha:\t" << alpha->getValue() << std::endl;
    
    ConstantNode<double> *q1 = new ConstantNode<double>("q1", new double(0.125) );
    DeterministicNode<double> *q1_value = new DeterministicNode<double>("q1_value", new QuantileFunction(q1, new GammaDistribution(alpha, alpha) ) );
//    StochasticNode<double> *q1_value = new StochasticNode<double>("q1_value", new GammaDistribution(alpha, alpha) );
    ConstantNode<double> *q2 = new ConstantNode<double>("q2", new double(0.375) );
    DeterministicNode<double> *q2_value = new DeterministicNode<double>("q2_value", new QuantileFunction(q2, new GammaDistribution(alpha, alpha) ) );
//    StochasticNode<double> *q2_value = new StochasticNode<double>("q2_value", new GammaDistribution(alpha, alpha) );
    ConstantNode<double> *q3 = new ConstantNode<double>("q3", new double(0.625) );
    DeterministicNode<double> *q3_value = new DeterministicNode<double>("q3_value", new QuantileFunction(q3, new GammaDistribution(alpha, alpha) ) );
//    StochasticNode<double> *q3_value = new StochasticNode<double>("q3_value", new GammaDistribution(alpha, alpha) );
    ConstantNode<double> *q4 = new ConstantNode<double>("q4", new double(0.875) );
    DeterministicNode<double> *q4_value = new DeterministicNode<double>("q4_value", new QuantileFunction(q4, new GammaDistribution(alpha, alpha) ) );
//    StochasticNode<double> *q4_value = new StochasticNode<double>("q4_value", new GammaDistribution(alpha, alpha) );
    std::vector<const TypedDagNode<double>* > gamma_rates = std::vector<const TypedDagNode<double>* >();
    gamma_rates.push_back(q1_value);
    gamma_rates.push_back(q2_value);
    gamma_rates.push_back(q3_value);
    gamma_rates.push_back(q4_value);
    
    DeterministicNode<std::vector<double> > *site_rates = new DeterministicNode<std::vector<double> >( "site_rates", new VectorFunction<double>(gamma_rates) );
    // currently unused
    // ConstantNode<std::vector<double> > *site_rate_probs = new ConstantNode<std::vector<double> >( "site_rate_probs", new std::vector<double>(4,1.0/4.0) );

    DeterministicNode<std::vector<double> > *site_rates_norm = new DeterministicNode<std::vector<double> >( "site_rates_norm", new NormalizeVectorFunction(site_rates) );
    
    pi->setValue( new std::vector<double>(4,1.0/4.0) );
    er->setValue( new std::vector<double>(6,1.0/6.0) );
    
    std::cout << "pi:\t" << pi->getValue() << std::endl;
    std::cout << "er:\t" << er->getValue() << std::endl;
    std::cout << "rates:\t" << site_rates->getValue() << std::endl;
    std::cout << "rates:\t" << site_rates_norm->getValue() << std::endl;

    DeterministicNode<RateMatrix> *q = new DeterministicNode<RateMatrix>( "Q", new GtrRateMatrixFunction(er, pi) );
    
    std::cout << "Q:\t" << q->getValue() << std::endl;
    
    std::vector<std::string> names = data[0]->getTaxonNames();
    ConstantNode<double>* origin = new ConstantNode<double>( "origin", new double( trees[0]->getRoot().getAge()*2.0 ) );
    std::vector<RevBayesCore::Taxon> taxa;
    for (size_t i = 0; i < names.size(); ++i)
    {
        taxa.push_back( Taxon( names[i] ) );
    }
    StochasticNode<TimeTree> *tau = new StochasticNode<TimeTree>( "tau", new ConstantRateBirthDeathProcess(origin, NULL, div, turn, rho, "uniform", "survival", taxa, std::vector<Clade>()) );
    
    tau->setValue( trees[0] );
    std::cout << "tau:\t" << tau->getValue() << std::endl;
    
    // and the character model
// (unused)    size_t numChar = data[0]->getNumberOfCharacters();
    GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree> *phyloCTMC = new GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree>(tau, 4, true, data[0]->getNumberOfCharacters());
    phyloCTMC->setSiteRates( site_rates_norm );
    phyloCTMC->setRateMatrix( q );
    StochasticNode< AbstractCharacterData > *charactermodel = new StochasticNode< AbstractCharacterData >("S", phyloCTMC );
    charactermodel->clamp( static_cast<DiscreteCharacterData<DnaState> *>( data[0] ) );
    
    std::cout << "LnL:\t\t" << charactermodel->getLnProbability() << std::endl;
    
    /* add the moves */
    RbVector<Move> moves;
//    moves.push_back( new ScaleMove(div, 1.0, true, 2.0) );
//    moves.push_back( new NearestNeighborInterchange( tau, 5.0 ) );
//    moves.push_back( new NarrowExchange( tau, 10.0 ) );
//    moves.push_back( new FixedNodeheightPruneRegraft( tau, 2.0 ) );
//    moves.push_back( new SubtreeScale( tau, 5.0 ) );
//    moves.push_back( new TreeScale( tau, 1.0, true, 2.0 ) );
//    moves.push_back( new NodeTimeSlideUniform( tau, 30.0 ) );
//    moves.push_back( new RootTimeSlide( tau, 1.0, true, 2.0 ) );
//    moves.push_back( new SimplexMove( er, 10.0, 1, 0, true, 2.0 ) );
//    moves.push_back( new SimplexMove( pi, 10.0, 1, 0, true, 2.0 ) );
//    moves.push_back( new SimplexMove( er, 100.0, 6, 0, true, 2.0 ) );
//    moves.push_back( new SimplexMove( pi, 100.0, 4, 0, true, 2.0 ) );
    
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(alpha, 1.0), 1, true) );
//    moves.push_back( new ScaleMove(q1_value, 1.0, true, 2.0) );
//    moves.push_back( new ScaleMove(q2_value, 1.0, true, 2.0) );
//    moves.push_back( new ScaleMove(q3_value, 1.0, true, 2.0) );
//    moves.push_back( new ScaleMove(q4_value, 1.0, true, 2.0) );
    
    // add some tree stats to monitor
    DeterministicNode<double> *treeHeight = new DeterministicNode<double>("TreeHeight", new TreeHeightStatistic(tau) );
    
    /* add the monitors */
    RbVector<Monitor> monitors;
    std::set<DagNode*> monitoredNodes;
//    monitoredNodes.insert( er );
//    monitoredNodes.insert( pi );
//    monitoredNodes.insert( q );
//    monitoredNodes.insert( q1_value );
//    monitoredNodes.insert( q2_value );
//    monitoredNodes.insert( q3_value );
//    monitoredNodes.insert( q4_value );
    monitoredNodes.insert( site_rates_norm );
    monitoredNodes.insert( alpha );
    monitoredNodes.insert( treeHeight );
    monitors.push_back( new FileMonitor( monitoredNodes, 1000, "TestGtrGammaModelSubstRates.log", "\t" ) );
    monitors.push_back( new ScreenMonitor( monitoredNodes, 1000, "\t" ) );
    std::set<DagNode*> monitoredNodes2;
    monitoredNodes2.insert( tau );
    monitors.push_back( new FileMonitor( monitoredNodes2, 1000, "TestGtrGammaModel.tree", "\t", false, false, false ) );
    
    /* instantiate the model */
    Model myModel = Model(q);
    
    /* instiate and run the MCMC */
    Mcmc myMcmc = Mcmc( myModel, moves, monitors );
    myMcmc.run(mcmcGenerations);
    
    myMcmc.printOperatorSummary();
    
    /* clean up */
    //    for (size_t i = 0; i < 10; ++i) {
    //        delete x[i];
    //    }
    //    delete [] x;
    delete div;
    //    delete sigma;
    //    delete a;
    //    delete b;
    //    delete c;
    
    std::cout << "Finished GTR+Gamma model test." << std::endl;
    
    return true;
}
예제 #4
0
bool TestACLNRatesGen::run( void ) {

//    alignmentFilename = "/Users/tracyh/Code/RevBayes_proj/tests/time_trees/tt_CLK_GTRG.nex";
//    treeFilename = "/Users/tracyh/Code/RevBayes_proj/tests/time_trees/tt_CLK_true_relx.tre";
	
	std::vector<AbstractCharacterData*> data = NclReader::getInstance().readMatrices(alignmentFilename);
    std::cout << "Read " << data.size() << " matrices." << std::endl;
    std::cout << data[0] << std::endl;
	
	// First, we read in the data 
    std::vector<TimeTree*> trees = NclReader::getInstance().readTimeTrees( treeFilename );
    std::cout << "Read " << trees.size() << " trees." << std::endl;
    std::cout << trees[0]->getNewickRepresentation() << std::endl;
    
    
	// #######################################
    // ###### birth-death process priors #####
	// #######################################
	
	//   Constant nodes
	ConstantNode<double> *dLambda = new ConstantNode<double>("div_rate", new double(1.0 / 5.0));		// Exponential rate for prior on div
	ConstantNode<double> *turnA   = new ConstantNode<double>("turn_alpha", new double(2.0));			// Beta distribution alpha
	ConstantNode<double> *turnB   = new ConstantNode<double>("turn_beta", new double(2.0));				// Beta distribution beta
    ConstantNode<double> *rho     = new ConstantNode<double>("rho", new double(1.0));					// assume 100% sampling for now
	ConstantNode<double> *meanOT  = new ConstantNode<double>("meanOT", new double(trees[0]->getRoot().getAge()*1.5));
	ConstantNode<double> *stdOT   = new ConstantNode<double>("stdOT", new double(10.0));
	
	//   Stochastic nodes
    StochasticNode<double> *origin  = new StochasticNode<double>( "origin", new NormalDistribution(meanOT, stdOT) );
    StochasticNode<double> *div   = new StochasticNode<double>("diversification", new ExponentialDistribution(dLambda));
    StochasticNode<double> *turn  = new StochasticNode<double>("turnover", new BetaDistribution(turnA, turnB));
	
	//   Deterministic nodes
	//    birthRate = div / (1 - turn)
	DeterministicNode<double> *birthRate = new DeterministicNode<double>("birth_rate", new BirthRateConstBDStatistic(div, turn));
	//    deathRate = (div * turn) / ( 1 - turn)
	DeterministicNode<double> *deathRate = new DeterministicNode<double>("death_rate", new DeathRateConstBDStatistic(div, turn));
	// For some datasets with large root ages, if div>1.0 (or so), the probability is NaN
	RandomNumberGenerator* rng = GLOBAL_RNG;
	div->setValue(rng->uniform01() / 1.5);
	
	// Birth-death tree
    std::vector<std::string> names = data[0]->getTaxonNames();
    std::vector<RevBayesCore::Taxon> taxa;
    for (size_t i = 0; i < names.size(); ++i)
    {
        taxa.push_back( Taxon( names[i] ) );
    }
    StochasticNode<TimeTree> *tau = new StochasticNode<TimeTree>( "tau", new ConstantRateBirthDeathProcess(origin, NULL, birthRate, deathRate, rho, "uniform", "nTaxa", taxa, std::vector<Clade>()) );

    DeterministicNode<double> *treeHeight = new DeterministicNode<double>("TreeHeight", new TreeHeightStatistic(tau) );
	
	
	// ##############################################
	// #### ACLN Model on Branch Rates #####
	// ##############################################
	
	size_t numBranches = 2 * data[0]->getNumberOfTaxa() - 2;
	size_t numNodes = numBranches + 1; // model rates at nodes
	
    ConstantNode<double> *a      = new ConstantNode<double>("a", new double(4.0) );
    ConstantNode<double> *b      = new ConstantNode<double>("b", new double(4.0) );
    ConstantNode<double> *anu    = new ConstantNode<double>("a_nu", new double(1.0) );
    ConstantNode<double> *bnu    = new ConstantNode<double>("b_nu", new double(8.0) );
	
	StochasticNode<double> *rootRate = new StochasticNode<double>("root.rate", new GammaDistribution(a, b));
	StochasticNode<double> *bmNu = new StochasticNode<double>("BM_var", new GammaDistribution(anu, bnu));
	
	size_t rootID = trees[0]->getRoot().getIndex();

	ConstantNode<double> *crInv  = new ConstantNode<double>("invCr", new double(1.0) );
	DeterministicNode<double> *scaleRate = new DeterministicNode<double>("scaleRate", new BinaryDivision<double, double, double>(crInv, treeHeight));

	StochasticNode< std::vector< double > > *nodeRates = new StochasticNode< std::vector< double > >( "NodeRates", new AutocorrelatedLognormalRateDistribution(tau, bmNu, rootRate, scaleRate) );
	
	std::cout << nodeRates->getValue().size() << std::endl;
	

	std::vector<const TypedDagNode<double> *> branchRates;
	for( size_t i=0; i<numBranches; i++){
		std::ostringstream brName;
        brName << "br(" << i << ")";
		DeterministicNode<double> *tmpBrRt = new DeterministicNode<double>(brName.str(), new RateOnBranchAve(nodeRates, tau, scaleRate, i));
		branchRates.push_back( tmpBrRt );
	}
    DeterministicNode< std::vector< double > >* brVector = new DeterministicNode< std::vector< double > >( "branchRates", new VectorFunction< double >( branchRates ) );
	
	// making a combined DagNode for a compound move
	std::vector<DagNode*> treeAndRates;
	treeAndRates.push_back( tau );
	treeAndRates.push_back(nodeRates);
	treeAndRates.push_back(rootRate);

	
	// ####################################
	
	
    // ###### GTR model priors ######
	//    Constant nodes
    ConstantNode<std::vector<double> > *bf   = new ConstantNode<std::vector<double> >( "bf", new std::vector<double>(4,1.0) );
    ConstantNode<std::vector<double> > *e    = new ConstantNode<std::vector<double> >( "e", new std::vector<double>(6,1.0) );
    //    Stochastic nodes
    StochasticNode<std::vector<double> > *pi = new StochasticNode<std::vector<double> >( "pi", new DirichletDistribution(bf) );
    StochasticNode<std::vector<double> > *er = new StochasticNode<std::vector<double> >( "er", new DirichletDistribution(e) );
	
    DeterministicNode<RateMatrix> *q = new DeterministicNode<RateMatrix>( "Q", new GtrRateMatrixFunction(er, pi) );
    std::cout << "Q:\t" << q->getValue() << std::endl;

	// ####### Gamma Rate Het. ######
	
	ConstantNode<double> *shapePr = new ConstantNode<double>("gammaShPr", new double(0.5));
	StochasticNode<double> *srAlpha = new StochasticNode<double>("siteRates.alpha", new ExponentialDistribution(shapePr));
    ConstantNode<double> *q1 = new ConstantNode<double>("q1", new double(0.125) );
    DeterministicNode<double> *q1Value = new DeterministicNode<double>("q1_value", new QuantileFunction(q1, new GammaDistribution(srAlpha, srAlpha) ) );
    ConstantNode<double> *q2 = new ConstantNode<double>("q2", new double(0.375) );
    DeterministicNode<double> *q2Value = new DeterministicNode<double>("q2_value", new QuantileFunction(q2, new GammaDistribution(srAlpha, srAlpha) ) );
    ConstantNode<double> *q3 = new ConstantNode<double>("q3", new double(0.625) );
    DeterministicNode<double> *q3Value = new DeterministicNode<double>("q3_value", new QuantileFunction(q3, new GammaDistribution(srAlpha, srAlpha) ) );
    ConstantNode<double> *q4 = new ConstantNode<double>("q4", new double(0.875) );
    DeterministicNode<double> *q4Value = new DeterministicNode<double>("q4_value", new QuantileFunction(q4, new GammaDistribution(srAlpha, srAlpha) ) );
    std::vector<const TypedDagNode<double>* > gammaRates = std::vector<const TypedDagNode<double>* >();
    gammaRates.push_back(q1Value);
    gammaRates.push_back(q2Value);
    gammaRates.push_back(q3Value);
    gammaRates.push_back(q4Value);
    DeterministicNode<std::vector<double> > *siteRates = new DeterministicNode<std::vector<double> >( "site_rates", new VectorFunction<double>(gammaRates) );
    DeterministicNode<std::vector<double> > *siteRatesNormed = new DeterministicNode<std::vector<double> >( "site_rates_norm", new NormalizeVectorFunction(siteRates) );
    
	
	tau->setValue( trees[0] );
    std::cout << "tau:\t" << tau->getValue() << std::endl;
	std::cout << " ** origin   " << origin->getValue() << std::endl;
	std::cout << " ** root age " << trees[0]->getRoot().getAge() << std::endl;
	
    GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree> *phyloCTMC = new GeneralBranchHeterogeneousCharEvoModel<DnaState, TimeTree>(tau, 4, true, data[0]->getNumberOfCharacters());
	phyloCTMC->setClockRate( brVector ); 
    phyloCTMC->setRateMatrix( q );
	phyloCTMC->setSiteRates( siteRatesNormed );
    StochasticNode< AbstractCharacterData > *charactermodel = new StochasticNode< AbstractCharacterData >("S", phyloCTMC );
	charactermodel->clamp( data[0] );
	
	std::cout << " diversification: " << div->getValue() << std::endl;
	std::cout << " turnover: " << turn->getValue() << std::endl;
	std::cout << " birth rate: " << birthRate->getValue() << std::endl;
	std::cout << " death rate: " << deathRate->getValue() << std::endl;
	
	/* add the moves */
    RbVector<Move> moves;
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(div, 1.0), 1.0, true ) );
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(turn, 1.0), 1.0, true ) );
	//	moves.push_back( new NearestNeighborInterchange( tau, 5.0 ) );
	//	moves.push_back( new NarrowExchange( tau, 10.0 ) );
	//	moves.push_back( new FixedNodeheightPruneRegraft( tau, 2.0 ) );
	//	moves.push_back( new SubtreeScale( tau, 5.0 ) );
	//	moves.push_back( new TreeScale( tau, 1.0, true, 2.0 ) );
	moves.push_back( new RootTimeSlide( tau, 50.0, true, 10.0 ) );
	moves.push_back( new OriginTimeSlide( origin, tau, 50.0, true, 10.0 ) );
	moves.push_back( new NodeTimeSlideUniform( tau, 30.0 ) );
	moves.push_back( new SimplexMove( er, 450.0, 6, 0, true, 2.0, 0.5 ) );
	moves.push_back( new SimplexMove( pi, 250.0, 4, 0, true, 2.0, 0.5 ) ); 
	moves.push_back( new SimplexMove( er, 200.0, 1, 0, false, 0.5 ) );
	moves.push_back( new SimplexMove( pi, 100.0, 1, 0, false, 0.5 ) );
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(srAlpha, log(2.0)), 1, true ) );
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(bmNu, 0.75), 4, true ) );
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(rootRate, 0.5), 2, false ) );
    moves.push_back( new MetropolisHastingsMove( new ScaleProposal(rootRate, 1.0), 2, false ) );
	moves.push_back( new ScaleSingleACLNRatesMove( nodeRates, 1.0, false, 8.0 * (double)numNodes) );
	moves.push_back( new ScaleSingleACLNRatesMove( nodeRates, 2.0, false, 8.0 * (double)numNodes) );
	moves.push_back( new RateAgeACLNMixingMove( treeAndRates, 0.02, false, 2.0 ) ); 
	
    // add some tree stats to monitor
	DeterministicNode<double> *meanNdRate = new DeterministicNode<double>("MeanNodeRate", new MeanVecContinuousValStatistic(nodeRates) );
	
    /* add the monitors */
    RbVector<Monitor> monitors;
    std::vector<DagNode*> monitoredNodes;
	monitoredNodes.push_back( meanNdRate );
	monitoredNodes.push_back( treeHeight );
	monitoredNodes.push_back( origin );
	monitoredNodes.push_back( nodeRates );
	monitoredNodes.push_back( rootRate );
	monitoredNodes.push_back( bmNu );
	monitoredNodes.push_back( scaleRate );
	monitors.push_back( new ScreenMonitor( monitoredNodes, 10, "\t" ) );
	
	monitoredNodes.push_back( div );
	monitoredNodes.push_back( turn );
	monitoredNodes.push_back( birthRate );
	monitoredNodes.push_back( deathRate );
	monitoredNodes.push_back( pi );
    monitoredNodes.push_back( er );
    monitoredNodes.push_back( srAlpha );
	monitoredNodes.push_back( brVector );
	
	std::string logFN = "clock_test/test_rb_ACLN_6June_rn_3.log";
	monitors.push_back( new FileMonitor( monitoredNodes, 10, logFN, "\t" ) );
	
    std::set<DagNode*> monitoredNodes2;
    monitoredNodes2.insert( tau );
	
//	std::string treFN = "clock_test/test_rb_ACLN_6June_pr.tre";
//	monitors.push_back( new FileMonitor( monitoredNodes2, 10, treFN, "\t", false, false, false ) );
    
    /* instantiate the model */
    Model myModel = Model(q);
	
	mcmcGenerations = 200000;

    /* instiate and run the MCMC */
    Mcmc myMcmc = Mcmc( myModel, moves, monitors );
    myMcmc.run(mcmcGenerations);
    
    myMcmc.printOperatorSummary();
	
	
	/* clean up */
	//	delete div;
	//	delete turn;
	//	delete rho;
	//	delete cp;
	//	delete branchRates;
	//	delete q;
	//	delete tau;
	delete charactermodel;
	//	delete a;
	//	delete birthRate;
	//	delete phyloCTMC;
	//	delete dLambda;
	
	
	monitors.clear();
	moves.clear();
	
    return true;
}
bool TestFilteredStandardLikelihood::run( void ) {
    std::cerr << "  starting TestFilteredStandardLikelihood...\n" ;
    /* First, we read in the data */
    // the matrix
    NclReader reader = NclReader();
    std::vector<AbstractCharacterData*> data = reader.readMatrices(alignmentFilename);
    AbstractDiscreteCharacterData * discrD = dynamic_cast<AbstractDiscreteCharacterData *>(data[0]);
#   if defined(USE_TIME_TREE)
        std::vector<TimeTree*> trees = reader.readTimeTrees( treeFilename );
        ConstantNode<TimeTree> *tau = new ConstantNode<TimeTree>( "tau", new TimeTree( *trees[0] ) );
#   else
        std::vector<BranchLengthTree*> *trees = reader.readBranchLengthTrees( treeFilename );
        ConstantNode<BranchLengthTree> *tau = new ConstantNode<BranchLengthTree>( "tau", new BranchLengthTree( *(*trees)[0] ) );
#   endif
    std::cout << "tau:\t" << tau->getValue() << std::endl;
#   if defined(USE_3_STATES)
        const size_t numStates = 3;
#   else
        const size_t numStates = 4;
#   endif
    size_t numChar = discrD->getNumberOfCharacters();

#   if defined(USE_RATE_HET)
        ConstantNode<double>* shape = new ConstantNode<double>("alpha", new double(0.5) );
        ConstantNode<double>* rate = new ConstantNode<double>("", new double(0.5) );
        ConstantNode<int>* numCats = new ConstantNode<int>("ncat", new int(4) );

        DiscretizeGammaFunction *dFunc = new DiscretizeGammaFunction( shape, rate, numCats, false );
        DeterministicNode<RbVector<double> > *site_rates_norm_2 = new DeterministicNode<RbVector<double> >( "site_rates_norm", dFunc );
        std::cout << "rates:\t" << site_rates_norm_2->getValue() << std::endl;
#   endif

#if defined(USE_3_STATES) && defined(USE_NUCLEOTIDE)
#error "cannot use 3 state and nucleotide type"
#endif
#if defined(USE_3_STATES) && defined(USE_GTR_RATE_MAT)
#error "cannot use 3 state and USE_GTR_RATE_MAT"
#endif

#   if defined(USE_GTR_RATE_MAT)
        ConstantNode<RbVector<double> > *pi = new ConstantNode<RbVector<double> >( "pi", new RbVector<double>(4, 1.0/4.0) );
        ConstantNode<RbVector<double> > *er = new ConstantNode<RbVector<double> >( "er", new RbVector<double>(6, 1.0/6.0) );
        DeterministicNode<RateMatrix> *q = new DeterministicNode<RateMatrix>( "Q", new GtrRateMatrixFunction(er, pi) );
        std::cout << "Q:\t" << q->getValue() << std::endl;
#       if defined (USE_NUCLEOTIDE)
#           if defined(USE_TIME_TREE)
                PhyloCTMCSiteHomogeneousNucleotide<DnaState, TimeTree> *charModel = new PhyloCTMCSiteHomogeneousNucleotide<DnaState, TimeTree>(tau, false, numChar);
#           else
                PhyloCTMCSiteHomogeneousNucleotide<DnaState, BranchLengthTree> *charModel = new PhyloCTMCSiteHomogeneousNucleotide<DnaState, BranchLengthTree>(tau, false, numChar );
#           endif
#       else
#           if defined(USE_TIME_TREE)
                PhyloCTMCSiteHomogeneous<DnaState, TimeTree> *charModel = new PhyloCTMCSiteHomogeneous<DnaState, TimeTree>(tau, 4, false, numChar);
#           else
                PhyloCTMCSiteHomogeneous<DnaState, BranchLengthTree> *charModel = new PhyloCTMCSiteHomogeneous<DnaState, BranchLengthTree>(tau, 4, false, numChar );
#           endif
#       endif
#   else
        DeterministicNode<RateMatrix> *q = new DeterministicNode<RateMatrix>( "Q", new JcRateMatrixFunction(numStates));
#       if defined (USE_NUCLEOTIDE)
#          if defined(USE_TIME_TREE)
                PhyloCTMCSiteHomogeneousNucleotide<StandardState, TimeTree> *charModel = new PhyloCTMCSiteHomogeneousNucleotide<StandardState, TimeTree>(tau, false, numChar);
#           else
                PhyloCTMCSiteHomogeneousNucleotide<StandardState, BranchLengthTree> *charModel = new PhyloCTMCSiteHomogeneousNucleotide<StandardState, BranchLengthTree>(tau, false, numChar );
#           endif
#       else
#          if defined(USE_TIME_TREE)
                PhyloCTMCSiteHomogeneous<StandardState, TimeTree> *charModel = new PhyloCTMCSiteHomogeneous<StandardState, TimeTree>(tau, numStates, false, numChar);
#           else
                PhyloCTMCSiteHomogeneous<StandardState, BranchLengthTree> *charModel = new PhyloCTMCSiteHomogeneous<StandardState, BranchLengthTree>(tau, numStates, false, numChar );
#           endif
#       endif
#   endif
#   if defined(USE_RATE_HET)
        charModel->setSiteRates( site_rates_norm_2 );
#   endif
    charModel->setRateMatrix( q );
    StochasticNode< AbstractDiscreteCharacterData > *charactermodel = new StochasticNode< AbstractDiscreteCharacterData >("S", charModel);
    charactermodel->clamp( discrD );
    double lnp = charactermodel->getLnProbability();
    std::cerr << "    lnProb = " << lnp << std::endl;
#   if defined(USE_3_STATES)
#       if defined(USE_RATE_HET)
            const double paupLnL = lnp; // can't check this against paup....
#       else
            const double paupLnL = -813.23060;
#       endif
#   else
#       if defined(USE_RATE_HET)
            const double paupLnL = -900.9122;
#       else
            const double paupLnL = -892.5822;
#       endif
#   endif
    const double tol = 0.01;
    if (fabs(lnp - paupLnL) > tol) {
        std::cerr << "    deviates too much from the likelihood from PAUP* of " << paupLnL << std::endl;
        return false;
    }
    if (lnp >= 0.0) {
        std::cerr << "    lnProb is too high!" << std::endl;
        return false;
    }

    std::cout << "RevBayes LnL:\t\t" << charactermodel->getLnProbability() << std::endl;
    std::cout << "Finished GTR+Gamma model test." << std::endl;
    return true;
}