Tree* TreeTools::MRPMultilabel(const vector<Tree*>& vecTr)
{
// matrix representation
VectorSiteContainer* sites = TreeTools::MRPEncode(vecTr);
// starting bioNJ tree
const DNA* alphabet = dynamic_cast<const DNA*>(sites->getAlphabet());
JCnuc* jc = new JCnuc(alphabet);
ConstantDistribution* constRate = new ConstantDistribution(1.);
DistanceEstimation distFunc(jc, constRate, sites, 0, true);
BioNJ bionjTreeBuilder(false, false);
bionjTreeBuilder.setDistanceMatrix(*(distFunc.getMatrix()));
bionjTreeBuilder.computeTree();
if (ApplicationTools::message)
ApplicationTools::message->endLine();
TreeTemplate<Node>* startTree = new TreeTemplate<Node>(*bionjTreeBuilder.getTree());
// MP optimization
DRTreeParsimonyScore* MPScore = new DRTreeParsimonyScore(*startTree, *sites, false);
MPScore = OptimizationTools::optimizeTreeNNI(MPScore, 0);
delete startTree;
Tree* retTree = new TreeTemplate<Node>(MPScore->getTree());
delete MPScore;
return retTree;
}
VectorSiteContainer* SiteContainerTools::sampleSites(const SiteContainer& sites, size_t nbSites, vector<size_t>* index)
{
VectorSiteContainer* sample = new VectorSiteContainer(sites.getSequencesNames(), sites.getAlphabet());
for (size_t i = 0; i < nbSites; i++)
{
size_t pos = static_cast<size_t>(RandomTools::giveIntRandomNumberBetweenZeroAndEntry(static_cast<int>(sites.getNumberOfSites())));
sample->addSite(sites.getSite(pos), false);
if (index)
index->push_back(pos);
}
return sample;
}
SiteContainer* SiteContainerTools::getCompleteSites(const SiteContainer& sites)
{
vector<string> seqNames = sites.getSequencesNames();
VectorSiteContainer* noGapCont = new VectorSiteContainer(seqNames.size(), sites.getAlphabet());
noGapCont->setSequencesNames(seqNames, false);
CompleteSiteContainerIterator csi(sites);
while (csi.hasMoreSites())
{
noGapCont->addSite(*csi.nextSite());
}
return noGapCont;
}
SiteContainer* SiteContainerTools::removeGapSites(const SiteContainer& sites, double maxFreqGaps)
{
vector<string> seqNames = sites.getSequencesNames();
VectorSiteContainer* noGapCont = new VectorSiteContainer(seqNames.size(), sites.getAlphabet());
noGapCont->setSequencesNames(seqNames, false);
for (unsigned int i = 0; i < sites.getNumberOfSites(); ++i) {
map<int, double> freq;
SiteTools::getFrequencies(sites.getSite(i), freq);
if (freq[-1] <= maxFreqGaps)
noGapCont->addSite(sites.getSite(i), false);
}
return noGapCont;
}
SiteContainer* SiteContainerTools::removeGapOrUnresolvedOnlySites(const SiteContainer& sites)
{
vector<string> seqNames = sites.getSequencesNames();
VectorSiteContainer* noGapCont = new VectorSiteContainer(seqNames.size(), sites.getAlphabet());
noGapCont->setSequencesNames(seqNames, false);
for (unsigned int i = 0; i < sites.getNumberOfSites(); i++)
{
const Site* site = &sites.getSite(i);
if (!SiteTools::isGapOrUnresolvedOnly(*site))
noGapCont->addSite(*site, false);
}
return noGapCont;
}
SiteContainer* SiteContainerTools::getSelectedSites(
const SiteContainer& sequences,
const SiteSelection& selection)
{
vector<string> seqNames = sequences.getSequencesNames();
VectorSiteContainer* sc = new VectorSiteContainer(seqNames.size(), sequences.getAlphabet());
sc->setSequencesNames(seqNames, false);
for (unsigned int i = 0; i < selection.size(); i++)
{
sc->addSite(sequences.getSite(selection[i]), false);
// We do not check names, we suppose that the container passed as an argument is correct.
// WARNING: what if selection contains many times the same indice? ...
}
sc->setGeneralComments(sequences.getGeneralComments());
return sc;
}
SiteContainer* SiteContainerTools::removeStopCodonSites(const SiteContainer& sites) throw (AlphabetException)
{
const CodonAlphabet* pca = dynamic_cast<const CodonAlphabet*>(sites.getAlphabet());
if (!pca)
throw AlphabetException("Not a Codon Alphabet", sites.getAlphabet());
vector<string> seqNames = sites.getSequencesNames();
VectorSiteContainer* noStopCont = new VectorSiteContainer(seqNames.size(), sites.getAlphabet());
noStopCont->setSequencesNames(seqNames, false);
for (unsigned int i = 0; i < sites.getNumberOfSites(); i++)
{
const Site* site = &sites.getSite(i);
if (!SiteTools::hasStopCodon(*site))
noStopCont->addSite(*site, false);
}
return noStopCont;
}
VectorSiteContainer::VectorSiteContainer(const VectorSiteContainer& vsc) :
AbstractSequenceContainer(vsc),
sites_(0),
names_(vsc.names_),
comments_(vsc.getNumberOfSequences()),
sequences_(vsc.getNumberOfSequences())
{
// Now try to add each site:
for (size_t i = 0; i < vsc.getNumberOfSites(); i++)
{
addSite(vsc.getSite(i), false); // We assume that positions are correct.
}
// Seq comments:
for (size_t i = 0; i < vsc.getNumberOfSequences(); i++)
{
comments_[i] = new Comments(vsc.getComments(i));
}
}
VectorSiteContainer* SequenceApplicationTools::getSiteContainer(
const Alphabet* alpha,
map<string, string>& params,
const string& suffix,
bool suffixIsOptional,
bool verbose,
int warn)
{
string sequenceFilePath = ApplicationTools::getAFilePath("input.sequence.file", params, true, true, suffix, suffixIsOptional, "none", warn);
string sequenceFormat = ApplicationTools::getStringParameter("input.sequence.format", params, "Fasta()", suffix, suffixIsOptional, warn);
BppOAlignmentReaderFormat bppoReader(warn);
unique_ptr<IAlignment> iAln(bppoReader.read(sequenceFormat));
map<string, string> args(bppoReader.getUnparsedArguments());
if (verbose)
{
ApplicationTools::displayResult("Sequence file " + suffix, sequenceFilePath);
ApplicationTools::displayResult("Sequence format " + suffix, iAln->getFormatName());
}
const Alphabet* alpha2;
if (AlphabetTools::isRNYAlphabet(alpha))
alpha2 = &dynamic_cast<const RNY*>(alpha)->getLetterAlphabet();
else
alpha2 = alpha;
const SequenceContainer* seqCont = iAln->readAlignment(sequenceFilePath, alpha2);
VectorSiteContainer* sites2 = new VectorSiteContainer(*dynamic_cast<const OrderedSequenceContainer*>(seqCont));
delete seqCont;
VectorSiteContainer* sites;
if (AlphabetTools::isRNYAlphabet(alpha))
{
const SequenceTools ST;
sites = new VectorSiteContainer(alpha);
for (unsigned int i = 0; i < sites2->getNumberOfSequences(); i++)
{
sites->addSequence(*(ST.RNYslice(sites2->getSequence(i))));
}
delete sites2;
}
else
sites = sites2;
// Look for site selection:
if (iAln->getFormatName() == "MASE file")
{
// getting site set:
string siteSet = ApplicationTools::getStringParameter("siteSelection", args, "none", suffix, suffixIsOptional, warn + 1);
if (siteSet != "none")
{
VectorSiteContainer* selectedSites;
try
{
selectedSites = dynamic_cast<VectorSiteContainer*>(MaseTools::getSelectedSites(*sites, siteSet));
if (verbose)
ApplicationTools::displayResult("Set found", TextTools::toString(siteSet) + " sites.");
}
catch (IOException& ioe)
{
throw ioe;
}
if (selectedSites->getNumberOfSites() == 0)
{
throw Exception("Site set '" + siteSet + "' is empty.");
}
delete sites;
sites = selectedSites;
}
}
else
{
// getting site set:
size_t nbSites = sites->getNumberOfSites();
string siteSet = ApplicationTools::getStringParameter("input.site.selection", params, "none", suffix, suffixIsOptional, warn + 1);
VectorSiteContainer* selectedSites = 0;
if (siteSet != "none")
{
vector<size_t> vSite;
try
{
vector<int> vSite1 = NumCalcApplicationTools::seqFromString(siteSet,",",":");
for (size_t i = 0; i < vSite1.size(); ++i)
{
int x = (vSite1[i] >= 0 ? vSite1[i] : static_cast<int>(nbSites) + vSite1[i]+ 1);
if (x<=(int)nbSites)
{
if (x > 0)
vSite.push_back(static_cast<size_t>(x - 1));
else
throw Exception("SequenceApplicationTools::getSiteContainer(). Incorrect null index: " + TextTools::toString(x));
}
else
throw Exception("SequenceApplicationTools::getSiteContainer(). Too large index: " + TextTools::toString(x));
}
selectedSites = dynamic_cast<VectorSiteContainer*>(SiteContainerTools::getSelectedSites(*sites, vSite));
selectedSites->reindexSites();
}
catch (Exception& e)
{
string seln;
map<string, string> selArgs;
KeyvalTools::parseProcedure(siteSet, seln, selArgs);
if (seln == "Sample")
{
size_t n = ApplicationTools::getParameter<size_t>("n", selArgs, nbSites, "", true, warn + 1);
bool replace = ApplicationTools::getBooleanParameter("replace", selArgs, false, "", true, warn + 1);
vSite.resize(n);
vector<size_t> vPos;
for (size_t p = 0; p < nbSites; ++p)
{
vPos.push_back(p);
}
RandomTools::getSample(vPos, vSite, replace);
selectedSites = dynamic_cast<VectorSiteContainer*>(SiteContainerTools::getSelectedSites(*sites, vSite));
if (replace)
selectedSites->reindexSites();
}
else
throw Exception("Unknown site selection description: " + siteSet);
}
if (verbose)
ApplicationTools::displayResult("Selected sites", TextTools::toString(siteSet));
if (selectedSites && (selectedSites->getNumberOfSites() == 0))
{
throw Exception("Site set '" + siteSet + "' is empty.");
}
delete sites;
sites = selectedSites;
}
}
return sites;
}
VectorSiteContainer* VectorSiteContainer::createEmptyContainer() const
{
VectorSiteContainer* vsc = new VectorSiteContainer(getAlphabet());
vsc->setGeneralComments(getGeneralComments());
return vsc;
}
int main(int args, char** argv)
{
cout << "******************************************************************" << endl;
cout << "* Bio++ Sequence Manipulator, version 2.3.0. *" << endl;
cout << "* Author: J. Dutheil Last Modif. 25/11/14 *" << endl;
cout << "******************************************************************" << endl;
cout << endl;
if (args == 1)
{
help();
return 0;
}
try {
BppApplication bppseqman(args, argv, "BppSeqMan");
bppseqman.startTimer();
// Get alphabet
Alphabet* alphabet = SequenceApplicationTools::getAlphabet(bppseqman.getParams(), "", false, true, true);
unique_ptr<GeneticCode> gCode;
CodonAlphabet* codonAlphabet = dynamic_cast<CodonAlphabet*>(alphabet);
// Get sequences:
bool aligned = ApplicationTools::getBooleanParameter("input.alignment", bppseqman.getParams(), false, "", true, 1);
OrderedSequenceContainer* sequences = 0;
if (aligned) {
VectorSiteContainer* allSites = SequenceApplicationTools::getSiteContainer(alphabet, bppseqman.getParams());
sequences = SequenceApplicationTools::getSitesToAnalyse(*allSites, bppseqman.getParams(), "", true, false);
delete allSites;
} else {
SequenceContainer* tmp = SequenceApplicationTools::getSequenceContainer(alphabet, bppseqman.getParams(), "", true, true);
sequences = new VectorSequenceContainer(*tmp);
delete tmp;
}
ApplicationTools::displayResult("Number of sequences", sequences->getNumberOfSequences());
// Perform manipulations
vector<string> actions = ApplicationTools::getVectorParameter<string>("sequence.manip", bppseqman.getParams(), ',', "", "", false, 1);
for (size_t a = 0; a < actions.size(); a++)
{
string cmdName;
map<string, string> cmdArgs;
KeyvalTools::parseProcedure(actions[a], cmdName, cmdArgs);
ApplicationTools::displayResult("Performing action", cmdName);
// +-----------------+
// | Complementation |
// +-----------------+
if (cmdName == "Complement")
{
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(sequences->getAlphabet());
else sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); i++)
{
Sequence* seq = SequenceTools::getComplement(sequences->getSequence(i));
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
// +------------------------+
// | (Reverse)Transcription |
// +------------------------+
else if (cmdName == "Transcript")
{
if (sequences->getAlphabet()->getAlphabetType() == AlphabetTools::DNA_ALPHABET.getAlphabetType())
{
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(&AlphabetTools::RNA_ALPHABET);
else sc = new VectorSequenceContainer(&AlphabetTools::RNA_ALPHABET);
for (unsigned int i = 0; i < sequences->getNumberOfSequences(); i++)
{
Sequence* seq = SequenceTools::transcript(sequences->getSequence(i));
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
else if (sequences->getAlphabet()->getAlphabetType() == AlphabetTools::RNA_ALPHABET.getAlphabetType())
{
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(&AlphabetTools::DNA_ALPHABET);
else sc = new VectorSequenceContainer(&AlphabetTools::DNA_ALPHABET);
for (unsigned int i = 0; i < sequences->getNumberOfSequences(); i++)
{
Sequence* seq = SequenceTools::reverseTranscript(sequences->getSequence(i));
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
else throw Exception("Transcription error: input alphabet must be of type 'nucleic'.");
}
// +-------------------------------+
// | Switching nucleotide alphabet |
// +-------------------------------+
else if (cmdName == "Switch")
{
const Alphabet* alpha = 0;
if (sequences->getAlphabet()->getAlphabetType() == AlphabetTools::DNA_ALPHABET.getAlphabetType())
{
alpha = &AlphabetTools::RNA_ALPHABET;
}
else if (sequences->getAlphabet()->getAlphabetType() == AlphabetTools::RNA_ALPHABET.getAlphabetType())
{
alpha = &AlphabetTools::DNA_ALPHABET;
}
else throw Exception("Cannot switch alphabet type, alphabet is not of type 'nucleic'.");
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(alpha);
else sc = new VectorSequenceContainer(alpha);
for (size_t i = 0; i < sequences->getNumberOfSequences(); i++)
{
const Sequence* old = &sequences->getSequence(i);
vector<int> content(old->size());
for (size_t j = 0; j < old->size(); ++j)
content[j] = (*old)[j];
Sequence* seq = new BasicSequence(old->getName(), content, old->getComments(), alpha);
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
// +-------------+
// | Translation |
// +-------------+
else if (cmdName == "Translate")
{
if (!AlphabetTools::isCodonAlphabet(sequences->getAlphabet()))
throw Exception("Error in translation: alphabet is not of type 'codon'.");
if (cmdArgs["code"] != "")
throw Exception("ERROR: 'code' argument is deprecated. The genetic code to use for translation is now set by the top-level argument 'genetic_code'.");
if (!gCode.get()) {
string codeDesc = ApplicationTools::getStringParameter("genetic_code", bppseqman.getParams(), "Standard", "", true, 1);
ApplicationTools::displayResult("Genetic Code", codeDesc);
gCode.reset(SequenceApplicationTools::getGeneticCode(codonAlphabet->getNucleicAlphabet(), codeDesc));
}
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(&AlphabetTools::PROTEIN_ALPHABET);
else sc = new VectorSequenceContainer(&AlphabetTools::PROTEIN_ALPHABET);
for (size_t i = 0; i < sequences->getNumberOfSequences(); ++i)
{
Sequence* seq = gCode->translate(sequences->getSequence(i));
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
// +-------------+
// | Remove gaps |
// +-------------+
else if (cmdName == "RemoveGaps")
{
VectorSequenceContainer* sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); i++)
{
unique_ptr<Sequence> seq(sequences->getSequence(i).clone());
SequenceTools::removeGaps(*seq);
sc->addSequence(*seq);
}
delete sequences;
sequences = sc;
aligned = false;
}
// +---------------------------+
// | Change gaps to unresolved |
// +---------------------------+
else if (cmdName == "GapToUnknown")
{
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(sequences->getAlphabet());
else sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); i++)
{
Sequence* seq = new BasicSequence(sequences->getSequence(i));
SymbolListTools::changeGapsToUnknownCharacters(*seq);
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
// +---------------------------+
// | Change unresolved to gaps |
// +---------------------------+
else if (cmdName == "UnknownToGap")
{
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(sequences->getAlphabet());
else sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); i++)
{
Sequence* seq = new BasicSequence(sequences->getSequence(i));
SymbolListTools::changeUnresolvedCharactersToGaps(*seq);
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
// +--------------+
// | Remove stops |
// +--------------+
else if (cmdName == "RemoveStops")
{
if (!gCode.get()) {
string codeDesc = ApplicationTools::getStringParameter("genetic_code", bppseqman.getParams(), "Standard", "", true, 1);
ApplicationTools::displayResult("Genetic Code", codeDesc);
gCode.reset(SequenceApplicationTools::getGeneticCode(codonAlphabet->getNucleicAlphabet(), codeDesc));
}
SiteContainer* sites = dynamic_cast<SiteContainer*>(sequences);
if (!sites)
{
VectorSequenceContainer* sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); ++i)
{
unique_ptr<Sequence> seq(sequences->getSequence(i).clone());
SequenceTools::removeStops(*seq, *gCode);
sc->addSequence(*seq);
}
delete sequences;
sequences = sc;
} else {
VectorSiteContainer* sc = new VectorSiteContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); ++i)
{
unique_ptr<Sequence> seq(sequences->getSequence(i).clone());
SequenceTools::replaceStopsWithGaps(*seq, *gCode);
sc->addSequence(*seq);
}
delete sequences;
sequences = sc;
}
}
// +--------------+
// | Remove stops |
// +--------------+
else if (cmdName == "RemoveColumnsWithStops")
{
SiteContainer* sites = dynamic_cast<SiteContainer*>(sequences);
if (!sites)
{
throw Exception("'RemoveColumnsWithStops' can only be used on alignment. You may consider using the 'CoerceToAlignment' command.");
}
if (!gCode.get()) {
string codeDesc = ApplicationTools::getStringParameter("genetic_code", bppseqman.getParams(), "Standard", "", true, 1);
ApplicationTools::displayResult("Genetic Code", codeDesc);
gCode.reset(SequenceApplicationTools::getGeneticCode(codonAlphabet->getNucleicAlphabet(), codeDesc));
}
for (size_t i = sites->getNumberOfSites(); i > 0; i--)
{
if (CodonSiteTools::hasStop(sites->getSite(i-1), *gCode))
sites->deleteSite(i - 1);
}
}
// +---------+
// | Get CDS |
// +---------+
else if (cmdName == "GetCDS")
{
if (!gCode.get()) {
string codeDesc = ApplicationTools::getStringParameter("genetic_code", bppseqman.getParams(), "Standard", "", true, 1);
ApplicationTools::displayResult("Genetic Code", codeDesc);
gCode.reset(SequenceApplicationTools::getGeneticCode(codonAlphabet->getNucleicAlphabet(), codeDesc));
}
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(sequences->getAlphabet());
else sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); ++i)
{
BasicSequence seq = sequences->getSequence(i);
size_t len = seq.size();
SequenceTools::getCDS(seq, *gCode, false, true, true, false);
if (aligned) {
for (size_t c = seq.size(); c < len; ++c)
seq.addElement(seq.getAlphabet()->getGapCharacterCode());
}
sc->addSequence(seq, false);
}
delete sequences;
sequences = sc;
}
// +--------------------------+
// | Resolve dotted alignment |
// +--------------------------+
else if (actions[a] == "CoerceToAlignment")
{
SiteContainer* sites = dynamic_cast<SiteContainer*>(sequences);
if(! sites)
{
sites = new VectorSiteContainer(*sequences);
delete sequences;
sequences = sites;
}
aligned = true;
}
else if (actions[a] == "ResolvedDotted")
{
SiteContainer* sites = dynamic_cast<SiteContainer *>(sequences);
if (!sites)
{
throw Exception("'ResolvedDotted' can only be used on alignment. You may consider using the 'CoerceToAlignment' command.");
}
const Alphabet* alpha = 0;
string alphastr = ApplicationTools::getStringParameter("alphabet", cmdArgs, "DNA", "", false, 1);
if (alphastr == "DNA") alpha = &AlphabetTools::DNA_ALPHABET;
else if (alphastr == "RNA") alpha = &AlphabetTools::RNA_ALPHABET;
else if (alphastr == "Protein") alpha = &AlphabetTools::PROTEIN_ALPHABET;
else throw Exception("Resolved alphabet must be one of [DNA|RNA|Protein] for solving dotted alignment.");
OrderedSequenceContainer* resolvedCont = SiteContainerTools::resolveDottedAlignment(*sites, alpha);
delete sequences;
sequences = resolvedCont;
}
// +---------------------+
// | Keep complete sites |
// +---------------------+
else if (cmdName == "KeepComplete")
{
SiteContainer* sites = dynamic_cast<SiteContainer *>(sequences);
if (!sites)
{
throw Exception("'KeepComplete' can only be used on alignment. You may consider using the 'CoerceToAlignment' command.");
}
string maxGapOption = ApplicationTools::getStringParameter("maxGapAllowed", cmdArgs, "100%", "", false, 1);
if (maxGapOption[maxGapOption.size()-1] == '%')
{
double gapFreq = TextTools::toDouble(maxGapOption.substr(0, maxGapOption.size()-1)) / 100.;
for (size_t i = sites->getNumberOfSites(); i > 0; i--)
{
map<int, double> freqs;
SiteTools::getFrequencies(sites->getSite(i - 1), freqs);
if (freqs[-1] > gapFreq) sites->deleteSite(i - 1);
}
}
else
{
size_t gapNum = TextTools::to<size_t>(maxGapOption);
for (size_t i = sites->getNumberOfSites(); i > 0; i--)
{
map<int, size_t> counts;
SiteTools::getCounts(sites->getSite(i - 1), counts);
counts[-1]; //Needed in case this entry does not exist in the map. This will set it to 0.
if (counts[-1] > gapNum) sites->deleteSite(i-1);
}
}
}
// +-----------------+
// | Invert sequence |
// +-----------------+
else if (cmdName == "Invert")
{
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(sequences->getAlphabet());
else sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); i++)
{
const Sequence* old = &sequences->getSequence(i);
Sequence* seq = SequenceTools::getInvert(*old);
sc->addSequence(*seq, false);
delete seq;
}
delete sequences;
sequences = sc;
}
// +------------------+
// | GetCodonPosition |
// +------------------+
else if (cmdName == "GetCodonPosition")
{
unsigned int pos = ApplicationTools::getParameter<unsigned int>("position", cmdArgs, 3, "", false, 1);
OrderedSequenceContainer* sc = dynamic_cast<OrderedSequenceContainer*>(SequenceContainerTools::getCodonPosition(*sequences, pos - 1));
delete sequences;
if (aligned) {
sequences = new VectorSiteContainer(*sc);
delete sc;
} else {
sequences = sc;
}
}
// +-----------------+
// | FilterFromTree |
// +-----------------+
else if (cmdName == "FilterFromTree")
{
unique_ptr<Tree> tree(PhylogeneticsApplicationTools::getTree(cmdArgs, ""));
vector<string> names = tree->getLeavesNames();
OrderedSequenceContainer* reorderedSequences = 0;
if (aligned) {
reorderedSequences = new VectorSiteContainer(sequences->getAlphabet());
} else {
reorderedSequences = new VectorSequenceContainer(sequences->getAlphabet());
}
for (size_t i = 0; i < names.size(); ++i) {
reorderedSequences->addSequence(sequences->getSequence(names[i]), false);
}
delete sequences;
sequences = reorderedSequences;
}
// +----------------------+
// | RemoveEmptySequences |
// +----------------------+
else if (cmdName == "RemoveEmptySequences")
{
OrderedSequenceContainer* sc = 0;
if (aligned) sc = new VectorSiteContainer(sequences->getAlphabet());
else sc = new VectorSequenceContainer(sequences->getAlphabet());
for (size_t i = 0; i < sequences->getNumberOfSequences(); ++i)
{
if (SequenceTools::getNumberOfSites(sequences->getSequence(i))!=0)
sc->addSequence(sequences->getSequence(i), false);
}
delete sequences;
sequences = sc;
}
else throw Exception("Unknown action: " + cmdName);
}
// Write sequences
ApplicationTools::displayBooleanResult("Final sequences are aligned", aligned);
if (aligned)
{
SequenceApplicationTools::writeAlignmentFile(*dynamic_cast<SiteContainer*>(sequences), bppseqman.getParams(), "", true, 1);
}
else
{
SequenceApplicationTools::writeSequenceFile(*sequences, bppseqman.getParams(), "", true, 1);
}
delete alphabet;
delete sequences;
bppseqman.done();
} catch(exception & e) {
cout << e.what() << endl;
return 1;
}
return 0;
}
int main(int args, char** argv)
{
cout << "******************************************************************" << endl;
cout << "* Bio++ Computation of site likelihoods inside mixed models *" << endl;
cout << "* Version 2.2.0. *" << endl;
cout << "* Author: L. Guéguen Last Modif.: 25/09/14 *" << endl;
cout << "******************************************************************" << endl;
cout << endl;
if (args == 1)
{
help();
return 0;
}
try
{
BppApplication bppmixedlikelihoods(args, argv, "BppMixedLikelihoods");
bppmixedlikelihoods.startTimer();
Alphabet* alphabet = SequenceApplicationTools::getAlphabet(bppmixedlikelihoods.getParams(), "", false);
auto_ptr<GeneticCode> gCode;
CodonAlphabet* codonAlphabet = dynamic_cast<CodonAlphabet*>(alphabet);
if (codonAlphabet) {
string codeDesc = ApplicationTools::getStringParameter("genetic_code", bppmixedlikelihoods.getParams(), "Standard", "", true, true);
ApplicationTools::displayResult("Genetic Code", codeDesc);
gCode.reset(SequenceApplicationTools::getGeneticCode(codonAlphabet->getNucleicAlphabet(), codeDesc));
}
// get the data
VectorSiteContainer* allSites = SequenceApplicationTools::getSiteContainer(alphabet, bppmixedlikelihoods.getParams());
VectorSiteContainer* sites = SequenceApplicationTools::getSitesToAnalyse(*allSites, bppmixedlikelihoods.getParams(), "", true, false);
delete allSites;
ApplicationTools::displayResult("Number of sequences", TextTools::toString(sites->getNumberOfSequences()));
ApplicationTools::displayResult("Number of sites", TextTools::toString(sites->getNumberOfSites()));
// Get the tree
Tree* tree = PhylogeneticsApplicationTools::getTree(bppmixedlikelihoods.getParams());
ApplicationTools::displayResult("Number of leaves", TextTools::toString(tree->getNumberOfLeaves()));
AbstractDiscreteRatesAcrossSitesTreeLikelihood* tl;
string nhOpt = ApplicationTools::getStringParameter("nonhomogeneous", bppmixedlikelihoods.getParams(), "no", "", true, false);
ApplicationTools::displayResult("Heterogeneous model", nhOpt);
MixedSubstitutionModel* model = 0;
MixedSubstitutionModelSet* modelSet = 0;
DiscreteDistribution* rDist = 0;
if (nhOpt == "no")
{
model = dynamic_cast<MixedSubstitutionModel*>(PhylogeneticsApplicationTools::getSubstitutionModel(alphabet, gCode.get(), sites, bppmixedlikelihoods.getParams()));
if (model == 0)
{
cout << "Model is not a Mixed model" << endl;
exit(0);
}
SiteContainerTools::changeGapsToUnknownCharacters(*sites);
if (model->getNumberOfStates() > model->getAlphabet()->getSize())
{
// Markov-modulated Markov model!
rDist = new ConstantRateDistribution();
}
else
{
rDist = PhylogeneticsApplicationTools::getRateDistribution(bppmixedlikelihoods.getParams());
}
tl = new RHomogeneousMixedTreeLikelihood(*tree, *sites, model, rDist, true);
}
else if (nhOpt == "one_per_branch")
{
model = dynamic_cast<MixedSubstitutionModel*>(PhylogeneticsApplicationTools::getSubstitutionModel(alphabet, gCode.get(), sites, bppmixedlikelihoods.getParams()));
if (model == 0)
{
cout << "Model is not a Mixed model" << endl;
exit(0);
}
SiteContainerTools::changeGapsToUnknownCharacters(*sites);
if (model->getNumberOfStates() > model->getAlphabet()->getSize())
{
// Markov-modulated Markov model!
rDist = new ConstantRateDistribution();
}
else
{
rDist = PhylogeneticsApplicationTools::getRateDistribution(bppmixedlikelihoods.getParams());
}
vector<double> rateFreqs;
if (model->getNumberOfStates() != alphabet->getSize())
{
// Markov-Modulated Markov Model...
unsigned int n = (unsigned int)(model->getNumberOfStates() / alphabet->getSize());
rateFreqs = vector<double>(n, 1. / (double)n); // Equal rates assumed for now, may be changed later (actually, in the most general case,
// we should assume a rate distribution for the root also!!!
}
std::map<std::string, std::string> aliasFreqNames;
FrequenciesSet* rootFreqs = PhylogeneticsApplicationTools::getRootFrequenciesSet(alphabet, gCode.get(), sites, bppmixedlikelihoods.getParams(), aliasFreqNames, rateFreqs);
vector<string> globalParameters = ApplicationTools::getVectorParameter<string>("nonhomogeneous_one_per_branch.shared_parameters", bppmixedlikelihoods.getParams(), ',', "");
modelSet = dynamic_cast<MixedSubstitutionModelSet*>(SubstitutionModelSetTools::createNonHomogeneousModelSet(model, rootFreqs, tree, aliasFreqNames, globalParameters));
model = 0;
tl = new RNonHomogeneousMixedTreeLikelihood(*tree, *sites, modelSet, rDist, true);
}
else if (nhOpt == "general")
{
modelSet = dynamic_cast<MixedSubstitutionModelSet*>(PhylogeneticsApplicationTools::getSubstitutionModelSet(alphabet, gCode.get(), sites, bppmixedlikelihoods.getParams()));
if (modelSet == 0)
{
cout << "Missing a Mixed model" << endl;
exit(0);
}
SiteContainerTools::changeGapsToUnknownCharacters(*sites);
if (modelSet->getNumberOfStates() > modelSet->getAlphabet()->getSize())
{
// Markov-modulated Markov model!
rDist = new ConstantDistribution(1.);
}
else
{
rDist = PhylogeneticsApplicationTools::getRateDistribution(bppmixedlikelihoods.getParams());
}
tl = new RNonHomogeneousMixedTreeLikelihood(*tree, *sites, modelSet, rDist, true);
}
else
throw Exception("Unknown option for nonhomogeneous: " + nhOpt);
tl->initialize();
double logL = tl->getValue();
if (isinf(logL))
{
// This may be due to null branch lengths, leading to null likelihood!
ApplicationTools::displayWarning("!!! Warning!!! Likelihood is zero.");
ApplicationTools::displayWarning("!!! This may be due to branch length == 0.");
ApplicationTools::displayWarning("!!! All null branch lengths will be set to 0.000001.");
ParameterList pl = tl->getBranchLengthsParameters();
for (unsigned int i = 0; i < pl.size(); i++)
{
if (pl[i].getValue() < 0.000001)
pl[i].setValue(0.000001);
}
tl->matchParametersValues(pl);
logL = tl->getValue();
}
if (isinf(logL))
{
ApplicationTools::displayError("!!! Unexpected likelihood == 0.");
ApplicationTools::displayError("!!! Looking at each site:");
for (unsigned int i = 0; i < sites->getNumberOfSites(); i++)
{
(*ApplicationTools::error << "Site " << sites->getSite(i).getPosition() << "\tlog likelihood = " << tl->getLogLikelihoodForASite(i)).endLine();
}
ApplicationTools::displayError("!!! 0 values (inf in log) may be due to computer overflow, particularily if datasets are big (>~500 sequences).");
exit(-1);
}
// Write parameters to screen:
ApplicationTools::displayResult("Log likelihood", TextTools::toString(tl->getValue(), 15));
ParameterList parameters = tl->getSubstitutionModelParameters();
for (unsigned int i = 0; i < parameters.size(); i++)
{
ApplicationTools::displayResult(parameters[i].getName(), TextTools::toString(parameters[i].getValue()));
}
parameters = tl->getRateDistributionParameters();
for (unsigned int i = 0; i < parameters.size(); i++)
{
ApplicationTools::displayResult(parameters[i].getName(), TextTools::toString(parameters[i].getValue()));
}
// /////////////////////////////////////////////
// Getting likelihoods per submodel
string outputFile;
outputFile = ApplicationTools::getAFilePath("output.likelihoods.file", bppmixedlikelihoods.getParams(), true, false);
ApplicationTools::displayResult("Output file for likelihoods", outputFile);
ofstream out(outputFile.c_str(), ios::out);
size_t nSites = sites->getNumberOfSites();
size_t nummodel = ApplicationTools::getParameter<size_t>("likelihoods.model_number", bppmixedlikelihoods.getParams(), 1, "", true, true);
string parname = ApplicationTools::getStringParameter("likelihoods.parameter_name", bppmixedlikelihoods.getParams(), "", "", true, false);
if (modelSet && ((nummodel <= 0) || (nummodel > modelSet->getNumberOfModels())))
{
ApplicationTools::displayError("Bad number of model " + TextTools::toString(nummodel) + ".");
exit(-1);
}
MixedSubstitutionModel* p0 = dynamic_cast<MixedSubstitutionModel*>(model ? model : modelSet->getModel(nummodel - 1));
if (!p0)
{
ApplicationTools::displayError("Model " + TextTools::toString(nummodel) + " is not a Mixed Model.");
exit(-1);
}
const AbstractBiblioMixedSubstitutionModel* ptmp = dynamic_cast<const AbstractBiblioMixedSubstitutionModel*>(p0);
if (ptmp) {
p0 = ptmp->getMixedModel().clone();
if (nhOpt == "no")
model = p0;
else {
modelSet->replaceModel(nummodel-1, p0);
modelSet->isFullySetUpFor(*tree);
}
}
//////////////////////////////////////////////////
// Case of a MixtureOfSubstitutionModels
MixtureOfSubstitutionModels* pMSM = dynamic_cast<MixtureOfSubstitutionModels*>(p0);
if (pMSM)
{
vector<string> colNames;
colNames.push_back("Sites");
size_t nummod = pMSM->getNumberOfModels();
for (unsigned int i = 0; i < nummod; i++)
{
colNames.push_back(pMSM->getNModel(i)->getName());
}
DataTable* rates = new DataTable(nSites, colNames.size());
rates->setColumnNames(colNames);
for (unsigned int i = 0; i < nSites; i++)
{
const Site* currentSite = &sites->getSite(i);
int currentSitePosition = currentSite->getPosition();
(*rates)(i, "Sites") = string("[" + TextTools::toString(currentSitePosition) + "]");
}
Vdouble vprob = pMSM->getProbabilities();
for (unsigned int i = 0; i < nummod; i++)
{
string modname = pMSM->getNModel(i)->getName();
for (unsigned int j = 0; j < nummod; j++)
{
pMSM->setNProbability(j, (j == i) ? 1 : 0);
}
if (tl)
delete tl;
if (nhOpt == "no")
tl = new RHomogeneousMixedTreeLikelihood(*tree, *sites, model, rDist, true, false, true);
else
tl = new RNonHomogeneousMixedTreeLikelihood(*tree, *sites, modelSet, rDist, false, true);
tl->initialize();
logL = tl->getValue();
Vdouble Vd = tl->getLogLikelihoodForEachSite();
for (unsigned int j = 0; j < nSites; j++)
{
(*rates)(j, modname) = TextTools::toString(Vd[j]);
}
ApplicationTools::displayMessage("\n");
ApplicationTools::displayMessage("Model " + modname + ":");
ApplicationTools::displayResult("Log likelihood", TextTools::toString(tl->getValue(), 15));
ApplicationTools::displayResult("Probability", TextTools::toString(vprob[i], 15));
}
DataTable::write(*rates, out, "\t");
}
//////////////////////////////////////////////////
// Case of a MixtureOfASubstitutionModel
else
{
MixtureOfASubstitutionModel* pMSM2 = dynamic_cast<MixtureOfASubstitutionModel*>(p0);
if (pMSM2 != NULL)
{
size_t nummod = pMSM2->getNumberOfModels();
if (parname == "")
{
ParameterList pl=pMSM2->getParameters();
for (size_t i2 = 0; i2 < pl.size(); i2++)
{
string pl2n = pl[i2].getName();
if (dynamic_cast<const ConstantDistribution*>(pMSM2->getDistribution(pl2n))==NULL)
{
parname=pl2n;
while (parname.size()>0 && pMSM2->getDistribution(parname)==NULL)
parname=pl2n.substr(0,pl2n.rfind("_"));
if (parname.size()>0){
ApplicationTools::displayResult("likelihoods.parameter_name", parname);
break;
}
}
}
}
if (parname == "")
{
ApplicationTools::displayError("Argument likelihoods.parameter_name is required.");
exit(-1);
}
vector< Vint > vvnmod;
size_t i2 = 0;
while (i2 < nummod)
{
string par2 = parname + "_" + TextTools::toString(i2 + 1);
Vint vnmod = pMSM2->getSubmodelNumbers(par2);
if (vnmod.size() == 0)
break;
vvnmod.push_back(vnmod);
i2++;
}
size_t nbcl = vvnmod.size();
if (nbcl==0)
throw Exception("Parameter " + parname + " is not mixed.");
Vdouble vprob = pMSM2->getProbabilities();
vector<vector<double> > vvprob;
vector<double> vsprob;
for (size_t i = 0; i < nbcl; i++)
{
vector<double> vprob2;
for (size_t j = 0; j < vvnmod[i].size(); j++)
{
vprob2.push_back(vprob[static_cast<size_t>(vvnmod[i][j])]);
}
vvprob.push_back(vprob2);
vsprob.push_back(VectorTools::sum(vvprob[i]));
}
vector<string> colNames;
colNames.push_back("Sites");
Vdouble dval;
for (unsigned int i = 0; i < nbcl; i++)
{
SubstitutionModel* pSM = pMSM2->getNModel(static_cast<size_t>(vvnmod[i][0]));
double valPar = pSM->getParameterValue(pSM->getParameterNameWithoutNamespace(parname));
dval.push_back(valPar);
colNames.push_back("Ll_" + parname + "=" + TextTools::toString(valPar));
}
for (unsigned int i = 0; i < nbcl; i++)
colNames.push_back("Pr_" + parname + "=" + TextTools::toString(dval[i]));
colNames.push_back("mean");
DataTable* rates = new DataTable(nSites, colNames.size());
rates->setColumnNames(colNames);
for (unsigned int i = 0; i < nSites; i++)
{
const Site* currentSite = &sites->getSite(i);
int currentSitePosition = currentSite->getPosition();
(*rates)(i,"Sites")=TextTools::toString(currentSitePosition);
}
VVdouble vvd;
vector<double> vRates = pMSM2->getVRates();
for (size_t i = 0; i < nbcl; ++i)
{
string par2 = parname + "_" + TextTools::toString(i + 1);
for (unsigned int j = 0; j < nummod; ++j)
pMSM2->setNProbability(j, 0);
for (size_t j = 0; j < vvprob[i].size(); ++j)
pMSM2->setNProbability(static_cast<size_t>(vvnmod[i][j]), vvprob[i][j] / vsprob[i]);
if (tl)
delete tl;
if (nhOpt == "no")
tl = new RHomogeneousMixedTreeLikelihood(*tree, *sites, model, rDist, true, false, true);
else
tl = new RNonHomogeneousMixedTreeLikelihood(*tree, *sites, modelSet, rDist, false, true);
tl->initialize();
logL = tl->getValue();
Vdouble vd = tl->getLogLikelihoodForEachSite();
for (unsigned int j = 0; j < nSites; j++)
(*rates)(j, i + 1) = TextTools::toString(vd[j]);
vvd.push_back(vd);
ApplicationTools::displayMessage("\n");
ApplicationTools::displayMessage("Parameter " + par2 + "=" + TextTools::toString(dval[i]) + " with rate=" + TextTools::toString(vRates[i]));
ApplicationTools::displayResult("Log likelihood", TextTools::toString(tl->getValue(), 15));
ApplicationTools::displayResult("Probability", TextTools::toString(vsprob[i], 15));
}
for (unsigned int j = 0; j < nSites; j++)
{
Vdouble vd;
for (unsigned int i = 0; i < nbcl; i++)
vd.push_back(std::log(vsprob[i])+vvd[i][j]);
VectorTools::logNorm(vd);
for (unsigned int i = 0; i < nbcl; i++)
(*rates)(j,nbcl + i + 1) = TextTools::toString(std::exp(vd[i]));
(*rates)(j, 2 * nbcl + 1) = TextTools::toString(VectorTools::sumExp(vd, dval));
}
DataTable::write(*rates, out, "\t");
}
}
delete alphabet;
delete sites;
if (model)
delete model;
if (modelSet)
delete modelSet;
delete rDist;
delete tl;
delete tree;
ApplicationTools::displayMessage("\n");
bppmixedlikelihoods.done();
}
catch (exception& e)
{
cout << e.what() << endl;
return 1;
}
return 0;
}
VectorSiteContainer * SequenceApplicationTools::getSitesToAnalyse(
const SiteContainer & allSites,
map<string, string> & params,
string suffix,
bool suffixIsOptional,
bool gapAsUnknown,
bool verbose)
{
// Fully resolved sites, i.e. without jokers and gaps:
VectorSiteContainer * sitesToAnalyse;
string option = ApplicationTools::getStringParameter("sequence.sites_to_use", params, "complete", suffix, suffixIsOptional);
if(verbose) ApplicationTools::displayResult("Sites to use", option);
sitesToAnalyse = new VectorSiteContainer(allSites);
if(option == "all")
{
string maxGapOption = ApplicationTools::getStringParameter("sequence.max_gap_allowed", params, "100%", suffix, suffixIsOptional);
if(maxGapOption[maxGapOption.size()-1] == '%')
{
double gapFreq = TextTools::toDouble(maxGapOption.substr(0,maxGapOption.size()-1)) / 100.;
for(unsigned int i = sitesToAnalyse->getNumberOfSites(); i > 0; i--)
{
map<int, double> freq;
SiteTools::getFrequencies(*sitesToAnalyse->getSite(i-1), freq);
if(freq[-1] > gapFreq) sitesToAnalyse->deleteSite(i-1);
}
}
else
{
unsigned int gapNum=TextTools::to<unsigned int>(maxGapOption);
for(unsigned int i = sitesToAnalyse->getNumberOfSites(); i > 0; i--)
{
map<int, unsigned int> counts;
SiteTools::getCounts(*sitesToAnalyse->getSite(i-1), counts);
if(counts[-1] > gapNum) sitesToAnalyse->deleteSite(i-1);
}
}
if(gapAsUnknown)
{
SiteContainerTools::changeGapsToUnknownCharacters(*sitesToAnalyse);
}
}
else if(option == "complete")
{
sitesToAnalyse = dynamic_cast<VectorSiteContainer *>(SiteContainerTools::getCompleteSites(allSites));
int nbSites = sitesToAnalyse->getNumberOfSites();
if(verbose) ApplicationTools::displayResult("Complete sites", TextTools::toString(nbSites));
}
else if(option == "nogap")
{
sitesToAnalyse = dynamic_cast<VectorSiteContainer *>(SiteContainerTools::getSitesWithoutGaps(allSites));
int nbSites = sitesToAnalyse->getNumberOfSites();
if(verbose) ApplicationTools::displayResult("Sites without gap", TextTools::toString(nbSites));
}
else
{
ApplicationTools::displayError("Option '" + option + "' unknown in parameter 'sequence.sitestouse'.");
exit(-1);
}
return sitesToAnalyse;
}
VectorSiteContainer * SequenceApplicationTools::getSiteContainer(
const Alphabet * alpha,
map<string, string> & params,
const string & suffix,
bool suffixIsOptional,
bool verbose)
{
string sequenceFilePath = ApplicationTools::getAFilePath("sequence.file",params, true, true, suffix, suffixIsOptional);
string sequenceFormat = ApplicationTools::getStringParameter("sequence.format", params, "Fasta", suffix, suffixIsOptional);
if(verbose) ApplicationTools::displayResult("Sequence format " + suffix, sequenceFormat);
ISequence * iSeq = NULL;
if(sequenceFormat == "Mase")
{
iSeq = new Mase();
}
else if(sequenceFormat == "Phylip")
{
bool sequential = true, extended = true;
string split = " ";
if(params.find("sequence.format_phylip.order") != params.end())
{
if(params["sequence.format_phylip.order"] == "sequential" ) sequential = true;
else if(params["sequence.format_phylip.order"] == "interleaved") sequential = false;
else ApplicationTools::displayWarning("Argument '" +
params["sequence.format_phylip.order"] +
"' for parameter 'sequence.format_phylip.order' is unknown. " +
"Default used instead: sequential.");
}
else ApplicationTools::displayWarning("Argument 'sequence.format_phylip.order' not found. Default used instead: sequential.");
if(params.find("sequence.format_phylip.ext") != params.end())
{
if(params["sequence.format_phylip.ext"] == "extended")
{
extended = true;
split = ApplicationTools::getStringParameter("sequence.format_phylip.extended.split", params, "spaces", suffix, suffixIsOptional);
if(split == "spaces") split = " ";
else if(split == "tab") split = "\t";
else throw Exception("Unknown option for sequence.format_phylip.extended.split: " + split);
}
else if(params["sequence.format_phylip.ext"] == "classic" ) extended = false;
else ApplicationTools::displayWarning("Argument '" +
params["sequence.format_phylip.ext"] +
"' for parameter 'sequence.format_phylip.ext' is unknown. " +
"Default used instead: extended.");
}
else ApplicationTools::displayWarning("Argument 'sequence.format_phylip.ext' not found. Default used instead: extended.");
iSeq = new Phylip(extended, sequential, 100, true, split);
}
else if(sequenceFormat == "Fasta") iSeq = new Fasta();
else if(sequenceFormat == "Clustal") iSeq = new Clustal();
else
{
ApplicationTools::displayError("Unknown sequence format.");
exit(-1);
}
const SequenceContainer * seqCont = iSeq->read(sequenceFilePath, alpha);
VectorSiteContainer * sites = new VectorSiteContainer(* dynamic_cast<const OrderedSequenceContainer *>(seqCont));
delete seqCont;
delete iSeq;
if(verbose) ApplicationTools::displayResult("Sequence file " + suffix, sequenceFilePath);
// Look for site selection:
if(sequenceFormat == "Mase")
{
//getting site set:
string siteSet = ApplicationTools::getStringParameter("sequence.format_mase.site_selection", params, "none", suffix, suffixIsOptional, false);
if(siteSet != "none")
{
VectorSiteContainer * selectedSites;
try
{
selectedSites = dynamic_cast<VectorSiteContainer *>(MaseTools::getSelectedSites(* sites, siteSet));
if(verbose) ApplicationTools::displayResult("Set found", TextTools::toString(siteSet) + " sites.");
}
catch(IOException ioe)
{
ApplicationTools::displayError("Site Set '" + siteSet + "' not found.");
exit(-1);
}
if(selectedSites->getNumberOfSites() == 0)
{
ApplicationTools::displayError("Site Set '" + siteSet + "' is empty.");
exit(-1);
}
delete sites;
sites = selectedSites;
}
}
return sites;
}
SiteContainer* SiteContainerTools::resolveDottedAlignment(
const SiteContainer& dottedAln,
const Alphabet* resolvedAlphabet) throw (AlphabetException, Exception)
{
if (!AlphabetTools::isDefaultAlphabet(dottedAln.getAlphabet()))
throw AlphabetException("SiteContainerTools::resolveDottedAlignment. Alignment alphabet should of class 'DefaultAlphabet'.", dottedAln.getAlphabet());
// First we look for the reference sequence:
size_t n = dottedAln.getNumberOfSequences();
if (n == 0)
throw Exception("SiteContainerTools::resolveDottedAlignment. Input alignment contains no sequence.");
const Sequence* refSeq = 0;
for (size_t i = 0; i < n; ++i) // Test each sequence
{
const Sequence* seq = &dottedAln.getSequence(i);
bool isRef = true;
for (unsigned int j = 0; isRef && j < seq->size(); ++j) // For each site in the sequence
{
if (seq->getChar(j) == ".")
isRef = false;
}
if (isRef) // We found the reference sequence!
{
refSeq = new BasicSequence(*seq);
}
}
if (!refSeq)
throw Exception("SiteContainerTools::resolveDottedAlignment. No reference sequence was found in the input alignment.");
// Now we build a new VectorSiteContainer:
VectorSiteContainer* sites = new VectorSiteContainer(n, resolvedAlphabet);
// We add each site one by one:
size_t m = dottedAln.getNumberOfSites();
string state;
for (unsigned int i = 0; i < m; ++i)
{
string resolved = refSeq->getChar(i);
const Site* site = &dottedAln.getSite(i);
Site resolvedSite(resolvedAlphabet, site->getPosition());
for (unsigned int j = 0; j < n; j++)
{
state = site->getChar(j);
if (state == ".")
{
state = resolved;
}
resolvedSite.addElement(state);
}
// Add the new site:
sites->addSite(resolvedSite);
}
// Seq sequence names:
sites->setSequencesNames(dottedAln.getSequencesNames());
// Delete the copied sequence:
delete refSeq;
// Return result:
return sites;
}
int main(int args, char ** argv)
{
cout << "******************************************************************" << endl;
cout << "* Bio++ Distance Methods, version 2.2.0 *" << endl;
cout << "* Author: J. Dutheil Created 05/05/07 *" << endl;
cout << "* Last Modif. 04/02/15 *" << endl;
cout << "******************************************************************" << endl;
cout << endl;
if(args == 1)
{
help();
return 0;
}
try {
BppApplication bppdist(args, argv, "BppDist");
bppdist.startTimer();
Alphabet* alphabet = SequenceApplicationTools::getAlphabet(bppdist.getParams(), "", false);
auto_ptr<GeneticCode> gCode;
CodonAlphabet* codonAlphabet = dynamic_cast<CodonAlphabet*>(alphabet);
if (codonAlphabet) {
string codeDesc = ApplicationTools::getStringParameter("genetic_code", bppdist.getParams(), "Standard", "", true, true);
ApplicationTools::displayResult("Genetic Code", codeDesc);
gCode.reset(SequenceApplicationTools::getGeneticCode(codonAlphabet->getNucleicAlphabet(), codeDesc));
}
VectorSiteContainer* allSites = SequenceApplicationTools::getSiteContainer(alphabet, bppdist.getParams());
VectorSiteContainer* sites = SequenceApplicationTools::getSitesToAnalyse(* allSites, bppdist.getParams());
delete allSites;
ApplicationTools::displayResult("Number of sequences", TextTools::toString(sites->getNumberOfSequences()));
ApplicationTools::displayResult("Number of sites", TextTools::toString(sites->getNumberOfSites()));
SubstitutionModel* model = PhylogeneticsApplicationTools::getSubstitutionModel(alphabet, gCode.get(), sites, bppdist.getParams());
DiscreteDistribution* rDist = 0;
if (model->getNumberOfStates() > model->getAlphabet()->getSize())
{
//Markov-modulated Markov model!
rDist = new ConstantRateDistribution();
}
else
{
rDist = PhylogeneticsApplicationTools::getRateDistribution(bppdist.getParams());
}
DistanceEstimation distEstimation(model, rDist, sites, 1, false);
string method = ApplicationTools::getStringParameter("method", bppdist.getParams(), "nj");
ApplicationTools::displayResult("Tree reconstruction method", method);
TreeTemplate<Node>* tree;
AgglomerativeDistanceMethod* distMethod = 0;
if(method == "wpgma")
{
PGMA* wpgma = new PGMA(true);
distMethod = wpgma;
}
else if(method == "upgma")
{
PGMA* upgma = new PGMA(false);
distMethod = upgma;
}
else if(method == "nj")
{
NeighborJoining* nj = new NeighborJoining();
nj->outputPositiveLengths(true);
distMethod = nj;
}
else if(method == "bionj")
{
BioNJ* bionj = new BioNJ();
bionj->outputPositiveLengths(true);
distMethod = bionj;
}
else throw Exception("Unknown tree reconstruction method.");
string type = ApplicationTools::getStringParameter("optimization.method", bppdist.getParams(), "init");
ApplicationTools::displayResult("Model parameters estimation method", type);
if (type == "init") type = OptimizationTools::DISTANCEMETHOD_INIT;
else if (type == "pairwise") type = OptimizationTools::DISTANCEMETHOD_PAIRWISE;
else if (type == "iterations") type = OptimizationTools::DISTANCEMETHOD_ITERATIONS;
else throw Exception("Unknown parameter estimation procedure '" + type + "'.");
unsigned int optVerbose = ApplicationTools::getParameter<unsigned int>("optimization.verbose", bppdist.getParams(), 2);
string mhPath = ApplicationTools::getAFilePath("optimization.message_handler", bppdist.getParams(), false, false);
OutputStream* messenger =
(mhPath == "none") ? 0 :
(mhPath == "std") ? ApplicationTools::message :
new StlOutputStream(new ofstream(mhPath.c_str(), ios::out));
ApplicationTools::displayResult("Message handler", mhPath);
string prPath = ApplicationTools::getAFilePath("optimization.profiler", bppdist.getParams(), false, false);
OutputStream* profiler =
(prPath == "none") ? 0 :
(prPath == "std") ? ApplicationTools::message :
new StlOutputStream(new ofstream(prPath.c_str(), ios::out));
if(profiler) profiler->setPrecision(20);
ApplicationTools::displayResult("Profiler", prPath);
// Should I ignore some parameters?
ParameterList allParameters = model->getParameters();
allParameters.addParameters(rDist->getParameters());
ParameterList parametersToIgnore;
string paramListDesc = ApplicationTools::getStringParameter("optimization.ignore_parameter", bppdist.getParams(), "", "", true, false);
bool ignoreBrLen = false;
StringTokenizer st(paramListDesc, ",");
while (st.hasMoreToken())
{
try
{
string param = st.nextToken();
if (param == "BrLen")
ignoreBrLen = true;
else
{
if (allParameters.hasParameter(param))
{
Parameter* p = &allParameters.getParameter(param);
parametersToIgnore.addParameter(*p);
}
else ApplicationTools::displayWarning("Parameter '" + param + "' not found.");
}
}
catch (ParameterNotFoundException& pnfe)
{
ApplicationTools::displayError("Parameter '" + pnfe.getParameter() + "' not found, and so can't be ignored!");
}
}
unsigned int nbEvalMax = ApplicationTools::getParameter<unsigned int>("optimization.max_number_f_eval", bppdist.getParams(), 1000000);
ApplicationTools::displayResult("Max # ML evaluations", TextTools::toString(nbEvalMax));
double tolerance = ApplicationTools::getDoubleParameter("optimization.tolerance", bppdist.getParams(), .000001);
ApplicationTools::displayResult("Tolerance", TextTools::toString(tolerance));
//Here it is:
ofstream warn("warnings", ios::out);
ApplicationTools::warning = new StlOutputStreamWrapper(&warn);
tree = OptimizationTools::buildDistanceTree(distEstimation, *distMethod, parametersToIgnore, !ignoreBrLen, type, tolerance, nbEvalMax, profiler, messenger, optVerbose);
warn.close();
delete ApplicationTools::warning;
ApplicationTools::warning = ApplicationTools::message;
string matrixPath = ApplicationTools::getAFilePath("output.matrix.file", bppdist.getParams(), false, false, "", false);
if (matrixPath != "none")
{
ApplicationTools::displayResult("Output matrix file", matrixPath);
string matrixFormat = ApplicationTools::getAFilePath("output.matrix.format", bppdist.getParams(), false, false, "", false);
string format = "";
bool extended = false;
std::map<std::string, std::string> unparsedArguments_;
KeyvalTools::parseProcedure(matrixFormat, format, unparsedArguments_);
if (unparsedArguments_.find("type") != unparsedArguments_.end())
{
if (unparsedArguments_["type"] == "extended")
{
extended = true;
}
else if (unparsedArguments_["type"] == "classic")
extended = false;
else
ApplicationTools::displayWarning("Argument '" +
unparsedArguments_["type"] + "' for parameter 'Phylip#type' is unknown. " +
"Default used instead: not extended.");
}
else
ApplicationTools::displayWarning("Argument 'Phylip#type' not found. Default used instead: not extended.");
ODistanceMatrix* odm = IODistanceMatrixFactory().createWriter(IODistanceMatrixFactory::PHYLIP_FORMAT, extended);
odm->write(*distEstimation.getMatrix(), matrixPath, true);
delete odm;
}
PhylogeneticsApplicationTools::writeTree(*tree, bppdist.getParams());
//Output some parameters:
if (type == OptimizationTools::DISTANCEMETHOD_ITERATIONS)
{
// Write parameters to screen:
ParameterList parameters = model->getParameters();
for (unsigned int i = 0; i < parameters.size(); i++)
{
ApplicationTools::displayResult(parameters[i].getName(), TextTools::toString(parameters[i].getValue()));
}
parameters = rDist->getParameters();
for (unsigned int i = 0; i < parameters.size(); i++)
{
ApplicationTools::displayResult(parameters[i].getName(), TextTools::toString(parameters[i].getValue()));
}
// Write parameters to file:
string parametersFile = ApplicationTools::getAFilePath("output.estimates", bppdist.getParams(), false, false);
if (parametersFile != "none")
{
ofstream out(parametersFile.c_str(), ios::out);
parameters = model->getParameters();
for (unsigned int i = 0; i < parameters.size(); i++)
{
out << parameters[i].getName() << " = " << parameters[i].getValue() << endl;
}
parameters = rDist->getParameters();
for (unsigned int i = 0; i < parameters.size(); i++)
{
out << parameters[i].getName() << " = " << parameters[i].getValue() << endl;
}
out.close();
}
}
//Bootstrap:
unsigned int nbBS = ApplicationTools::getParameter<unsigned int>("bootstrap.number", bppdist.getParams(), 0);
if(nbBS > 0)
{
ApplicationTools::displayResult("Number of bootstrap samples", TextTools::toString(nbBS));
bool approx = ApplicationTools::getBooleanParameter("bootstrap.approximate", bppdist.getParams(), true);
ApplicationTools::displayResult("Use approximate bootstrap", TextTools::toString(approx ? "yes" : "no"));
if(approx)
{
type = OptimizationTools::DISTANCEMETHOD_INIT;
parametersToIgnore = allParameters;
ignoreBrLen = true;
}
bool bootstrapVerbose = ApplicationTools::getBooleanParameter("bootstrap.verbose", bppdist.getParams(), false, "", true, false);
string bsTreesPath = ApplicationTools::getAFilePath("bootstrap.output.file", bppdist.getParams(), false, false);
ofstream *out = NULL;
if(bsTreesPath != "none")
{
ApplicationTools::displayResult("Bootstrap trees stored in file", bsTreesPath);
out = new ofstream(bsTreesPath.c_str(), ios::out);
}
Newick newick;
vector<Tree *> bsTrees(nbBS);
ApplicationTools::displayTask("Bootstrapping", true);
for(unsigned int i = 0; i < nbBS; i++)
{
ApplicationTools::displayGauge(i, nbBS-1, '=');
VectorSiteContainer * sample = SiteContainerTools::bootstrapSites(*sites);
if(approx) model->setFreqFromData(*sample);
distEstimation.setData(sample);
bsTrees[i] = OptimizationTools::buildDistanceTree(
distEstimation,
*distMethod,
parametersToIgnore,
ignoreBrLen,
type,
tolerance,
nbEvalMax,
NULL,
NULL,
(bootstrapVerbose ? 1 : 0)
);
if(out && i == 0) newick.write(*bsTrees[i], bsTreesPath, true);
if(out && i > 0) newick.write(*bsTrees[i], bsTreesPath, false);
delete sample;
}
if(out) out->close();
if(out) delete out;
ApplicationTools::displayTaskDone();
ApplicationTools::displayTask("Compute bootstrap values");
TreeTools::computeBootstrapValues(*tree, bsTrees);
ApplicationTools::displayTaskDone();
for(unsigned int i = 0; i < nbBS; i++) delete bsTrees[i];
//Write resulting tree:
PhylogeneticsApplicationTools::writeTree(*tree, bppdist.getParams());
}
delete alphabet;
delete sites;
delete distMethod;
delete tree;
bppdist.done();}
catch(exception & e)
{
cout << e.what() << endl;
return 1;
}
return 0;
}
