pair<string,scalar_type> tree_LL_nucl(string tree,string aln_filename,bool optimize_bls,scalar_type tolerance)
{
//const Alphabet* alphabet = new ProteicAlphabet();
const Alphabet* alphabet = new RNA();
OrderedSequenceContainer *alignment;
VectorSiteContainer* sites;
Fasta Reader;
//NexusIOSequence Reader;
//Phylip * Reader=new Phylip(true,true,100,true,"\r");
alignment = Reader.read(aln_filename, alphabet);
sites = new VectorSiteContainer(*alignment);
SiteContainerTools::removeGapOnlySites(*sites);
SiteContainerTools::changeGapsToUnknownCharacters(*sites);
TreeTemplate<Node>* ttree1=TreeTemplateTools::parenthesisToTree(tree,false,"ID");
DiscreteRatesAcrossSitesTreeLikelihood* tl1;
SubstitutionModel* model = 0;
DiscreteDistribution* rDist = 0;
model = new GTR(&AlphabetTools::RNA_ALPHABET);
model->setFreqFromData(*sites);
rDist = new GammaDiscreteDistribution(8, 1, 1);
tl1 = new RHomogeneousTreeLikelihood(*ttree1, *sites, model, rDist, true, false, false);
tl1->initialize();
if (optimize_bls)
{
//Newton..
ParameterList * parameters= new ParameterList();
parameters->addParameters( tl1->getBranchLengthsParameters());
parameters->addParameters( tl1->getRateDistributionParameters());
OptimizationTools::optimizeNumericalParameters(
dynamic_cast<DiscreteRatesAcrossSitesTreeLikelihood*> (tl1),
//tl1->getParameters(),
*parameters,
0,
1,
tolerance,
1000,
0,
0,
false,
0,
OptimizationTools::OPTIMIZATION_NEWTON,
//OptimizationTools::OPTIMIZATION_BRENT);
OptimizationTools::OPTIMIZATION_BFGS);
delete parameters;
}
scalar_type LL=- tl1->getValue(); //Here's your log likelihood value !
//tl1->getParameters().printParameters(cout);
//cout << TreeTemplateTools::treeToParenthesis( tl1->getTree() ) <<endl;
pair<string,scalar_type> return_pair;
return_pair.first= TreeTemplateTools::treeToParenthesis( tl1->getTree() ) ;
return_pair.second=LL;
delete sites;
delete alphabet;
delete model;
delete rDist;
delete tl1;
return return_pair;
}
Fasta extractInterestingGenes(Fasta &repertoire, string name) {
Fasta interesting;
int size = repertoire.size();
for (int i = 0; i < size; i++) {
if (repertoire.label(i).find(name) != string::npos) {
interesting.add(repertoire.read(i));
}
}
return interesting;
}
scalar_type tree_LL(string tree,string aln_filename,bool optimize_bls,scalar_type tolerance)
{
const Alphabet* alphabet = new ProteicAlphabet();
OrderedSequenceContainer *alignment;
VectorSiteContainer* sites;
Fasta Reader;
//Phylip * Reader=new Phylip(true,true,100,true,"\r");
alignment = Reader.read(aln_filename, alphabet);
sites = new VectorSiteContainer(*alignment);
SiteContainerTools::changeGapsToUnknownCharacters(*sites);
TreeTemplate<Node>* ttree1=TreeTemplateTools::parenthesisToTree(tree,false,"ID");
//Newick newick1;
//ttree1 = newick1.read(tree);
DiscreteRatesAcrossSitesTreeLikelihood* tl1;
SubstitutionModel* model = 0;
DiscreteDistribution* rDist = 0;
model = new LG08(&AlphabetTools::PROTEIN_ALPHABET, new FullProteinFrequenciesSet(&AlphabetTools::PROTEIN_ALPHABET), true);
model->setFreqFromData(*sites);
rDist = new GammaDiscreteDistribution(4, 1, 1);
tl1 = new RHomogeneousTreeLikelihood(*ttree1, *sites, model, rDist, true, false, false);
tl1->initialize();
/*
if (optimize_bls)
{
Optimizer* optimizer = new PseudoNewtonOptimizer(tl1);
// Optimizer* optimizer = new PseudoNewtonOptimizer(tl1);
ParameterList * parameters= new ParameterList();
parameters->addParameters( tl1->getBranchLengthsParameters());
parameters->addParameters( tl1->getRateDistributionParameters());
//Newton..
optimizer->setConstraintPolicy(AutoParameter::CONSTRAINTS_AUTO);
optimizer->setProfiler(0);
optimizer->setMessageHandler(0);
optimizer->setVerbose(0);
optimizer->getStopCondition()->setTolerance(0.01);
optimizer->init(*parameters);
//optimizer->init(tl1->getParameters());
optimizer->setMaximumNumberOfEvaluations(1000);
optimizer->optimize();
delete parameters;
delete optimizer;
}
*/
if (optimize_bls)
{
//Newton..
ParameterList * parameters= new ParameterList();
parameters->addParameters( tl1->getBranchLengthsParameters());
parameters->addParameters( tl1->getRateDistributionParameters());
OptimizationTools::optimizeNumericalParameters(
dynamic_cast<DiscreteRatesAcrossSitesTreeLikelihood*> (tl1),
//tl1->getParameters(),
*parameters,
0,
1,
tolerance,
1000,
0,
0,
false,
0,
OptimizationTools::OPTIMIZATION_NEWTON,
//OptimizationTools::OPTIMIZATION_BRENT);
OptimizationTools::OPTIMIZATION_BFGS);
delete parameters;
}
scalar_type LL=- tl1->getValue(); //Here's your log likelihood value !
delete sites;
delete alphabet;
delete model;
delete rDist;
delete tl1;
return LL;
}
void align_against_collection(string &read, Fasta &rep, int forbidden_rep_id,
bool reverse_ref, bool reverse_both, bool local,
AlignBox *box, Cost segment_cost)
{
int best_score = MINUS_INF ;
box->ref_nb = MINUS_INF ;
int best_best_i = (int) string::npos ;
int best_best_j = (int) string::npos ;
int best_first_i = (int) string::npos ;
int best_first_j = (int) string::npos ;
vector<pair<int, int> > score_r;
DynProg::DynProgMode dpMode = DynProg::LocalEndWithSomeDeletions;
if (local==true) dpMode = DynProg::Local;
// With reverse_ref, the read is reversed to prevent calling revcomp on each reference sequence
string sequence_or_rc = revcomp(read, reverse_ref);
for (int r = 0 ; r < rep.size() ; r++)
{
if (r == forbidden_rep_id)
continue;
DynProg dp = DynProg(sequence_or_rc, rep.sequence(r),
dpMode, // DynProg::SemiGlobalTrans,
segment_cost, // DNA
reverse_both, reverse_both,
rep.read(r).marked_pos);
bool onlyBottomTriangle = !local ;
int score = dp.compute(onlyBottomTriangle, BOTTOM_TRIANGLE_SHIFT);
if (local==true){
dp.backtrack();
}
if (score > best_score)
{
best_score = score ;
best_best_i = dp.best_i ;
best_best_j = dp.best_j ;
best_first_i = dp.first_i ;
best_first_j = dp.first_j ;
box->ref_nb = r ;
box->ref_label = rep.label(r) ;
if (!local)
dp.backtrack();
box->marked_pos = dp.marked_pos_i ;
}
score_r.push_back(make_pair(score, r));
// #define DEBUG_SEGMENT
#ifdef DEBUG_SEGMENT
cout << rep.label(r) << " " << score << " " << dp.best_i << endl ;
#endif
}
sort(score_r.begin(),score_r.end(),comp_pair);
box->ref = rep.sequence(box->ref_nb);
box->del_right = reverse_both ? best_best_j : box->ref.size() - best_best_j - 1;
box->del_left = best_first_j;
box->start = best_first_i;
box->score = score_r;
#ifdef DEBUG_SEGMENT
cout << "best: " << box->ref_label << " " << best_score ;
cout << "del/del2/begin:" << (box->del_right) << "/" << (box->del_left) << "/" << (box->start) << endl;
cout << endl;
#endif
if (reverse_ref)
// Why -1 here and +1 in dynprog.cpp /// best_i = m - best_i + 1 ;
best_best_i = read.length() - best_best_i - 1 ;
box->end = best_best_i ;
}
