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;
}
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;
}
