Bayesian::Bayesian(string tfile, string tempFile, string method, int ksize, int cutoff, int i, int tid, bool f, bool sh) :
Classify(), kmerSize(ksize), confidenceThreshold(cutoff), iters(i) {
try {
ReferenceDB* rdb = ReferenceDB::getInstance();
threadID = tid;
flip = f;
shortcuts = sh;
string baseName = tempFile;
if (baseName == "saved") { baseName = rdb->getSavedReference(); }
string baseTName = tfile;
if (baseTName == "saved") { baseTName = rdb->getSavedTaxonomy(); }
/************calculate the probablity that each word will be in a specific taxonomy*************/
string tfileroot = m->getFullPathName(baseTName.substr(0,baseTName.find_last_of(".")+1));
string tempfileroot = m->getRootName(m->getSimpleName(baseName));
string phyloTreeName = tfileroot + "tree.train";
string phyloTreeSumName = tfileroot + "tree.sum";
string probFileName = tfileroot + tempfileroot + char('0'+ kmerSize) + "mer.prob";
string probFileName2 = tfileroot + tempfileroot + char('0'+ kmerSize) + "mer.numNonZero";
ofstream out;
ofstream out2;
ifstream phyloTreeTest(phyloTreeName.c_str());
ifstream probFileTest2(probFileName2.c_str());
ifstream probFileTest(probFileName.c_str());
ifstream probFileTest3(phyloTreeSumName.c_str());
int start = time(NULL);
//if they are there make sure they were created after this release date
bool FilesGood = false;
if(probFileTest && probFileTest2 && phyloTreeTest && probFileTest3){
FilesGood = checkReleaseDate(probFileTest, probFileTest2, phyloTreeTest, probFileTest3);
}
//if you want to save, but you dont need to calculate then just read
if (rdb->save && probFileTest && probFileTest2 && phyloTreeTest && probFileTest3 && FilesGood && (tempFile != "saved")) {
ifstream saveIn;
m->openInputFile(tempFile, saveIn);
while (!saveIn.eof()) {
Sequence temp(saveIn);
m->gobble(saveIn);
rdb->referenceSeqs.push_back(temp);
}
saveIn.close();
}
if(probFileTest && probFileTest2 && phyloTreeTest && probFileTest3 && FilesGood){
if (tempFile == "saved") { m->mothurOutEndLine(); m->mothurOut("Using sequences from " + rdb->getSavedReference() + " that are saved in memory."); m->mothurOutEndLine(); }
m->mothurOut("Reading template taxonomy... "); cout.flush();
phyloTree = new PhyloTree(phyloTreeTest, phyloTreeName);
m->mothurOut("DONE."); m->mothurOutEndLine();
genusNodes = phyloTree->getGenusNodes();
genusTotals = phyloTree->getGenusTotals();
if (tfile == "saved") {
m->mothurOutEndLine(); m->mothurOut("Using probabilties from " + rdb->getSavedTaxonomy() + " that are saved in memory... "); cout.flush();;
wordGenusProb = rdb->wordGenusProb;
WordPairDiffArr = rdb->WordPairDiffArr;
}else {
m->mothurOut("Reading template probabilities... "); cout.flush();
readProbFile(probFileTest, probFileTest2, probFileName, probFileName2);
}
//save probabilities
if (rdb->save) { rdb->wordGenusProb = wordGenusProb; rdb->WordPairDiffArr = WordPairDiffArr; }
}else{
//create search database and names vector
generateDatabaseAndNames(tfile, tempFile, method, ksize, 0.0, 0.0, 0.0, 0.0);
//prevents errors caused by creating shortcut files if you had an error in the sanity check.
if (m->control_pressed) { m->mothurRemove(phyloTreeName); m->mothurRemove(probFileName); m->mothurRemove(probFileName2); }
else{
genusNodes = phyloTree->getGenusNodes();
genusTotals = phyloTree->getGenusTotals();
m->mothurOut("Calculating template taxonomy tree... "); cout.flush();
phyloTree->printTreeNodes(phyloTreeName);
m->mothurOut("DONE."); m->mothurOutEndLine();
m->mothurOut("Calculating template probabilities... "); cout.flush();
numKmers = database->getMaxKmer() + 1;
//initialze probabilities
wordGenusProb.resize(numKmers);
WordPairDiffArr.resize(numKmers);
for (int j = 0; j < wordGenusProb.size(); j++) { wordGenusProb[j].resize(genusNodes.size()); }
ofstream out;
ofstream out2;
#ifdef USE_MPI
int pid;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
if (pid == 0) {
#endif
if (shortcuts) {
m->openOutputFile(probFileName, out);
//output mothur version
out << "#" << m->getVersion() << endl;
out << numKmers << endl;
m->openOutputFile(probFileName2, out2);
//output mothur version
out2 << "#" << m->getVersion() << endl;
}
#ifdef USE_MPI
}
#endif
//for each word
for (int i = 0; i < numKmers; i++) {
//m->mothurOut("[DEBUG]: kmer = " + toString(i) + "\n");
if (m->control_pressed) { break; }
#ifdef USE_MPI
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
if (pid == 0) {
#endif
if (shortcuts) { out << i << '\t'; }
#ifdef USE_MPI
}
#endif
vector<int> seqsWithWordi = database->getSequencesWithKmer(i);
//for each sequence with that word
vector<int> count; count.resize(genusNodes.size(), 0);
for (int j = 0; j < seqsWithWordi.size(); j++) {
int temp = phyloTree->getGenusIndex(names[seqsWithWordi[j]]);
count[temp]++; //increment count of seq in this genus who have this word
}
//probabilityInTemplate = (# of seqs with that word in template + 0.50) / (total number of seqs in template + 1);
float probabilityInTemplate = (seqsWithWordi.size() + 0.50) / (float) (names.size() + 1);
diffPair tempProb(log(probabilityInTemplate), 0.0);
WordPairDiffArr[i] = tempProb;
int numNotZero = 0;
for (int k = 0; k < genusNodes.size(); k++) {
//probabilityInThisTaxonomy = (# of seqs with that word in this taxonomy + probabilityInTemplate) / (total number of seqs in this taxonomy + 1);
wordGenusProb[i][k] = log((count[k] + probabilityInTemplate) / (float) (genusTotals[k] + 1));
if (count[k] != 0) {
#ifdef USE_MPI
int pid;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
if (pid == 0) {
#endif
if (shortcuts) { out << k << '\t' << wordGenusProb[i][k] << '\t' ; }
#ifdef USE_MPI
}
#endif
numNotZero++;
}
}
#ifdef USE_MPI
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
if (pid == 0) {
#endif
if (shortcuts) {
out << endl;
out2 << probabilityInTemplate << '\t' << numNotZero << '\t' << log(probabilityInTemplate) << endl;
}
#ifdef USE_MPI
}
#endif
}
#ifdef USE_MPI
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
if (pid == 0) {
#endif
if (shortcuts) {
out.close();
out2.close();
}
#ifdef USE_MPI
}
#endif
//read in new phylotree with less info. - its faster
ifstream phyloTreeTest(phyloTreeName.c_str());
delete phyloTree;
phyloTree = new PhyloTree(phyloTreeTest, phyloTreeName);
//save probabilities
if (rdb->save) { rdb->wordGenusProb = wordGenusProb; rdb->WordPairDiffArr = WordPairDiffArr; }
}
}
if (m->debug) { m->mothurOut("[DEBUG]: about to generateWordPairDiffArr\n"); }
generateWordPairDiffArr();
if (m->debug) { m->mothurOut("[DEBUG]: done generateWordPairDiffArr\n"); }
//save probabilities
if (rdb->save) { rdb->wordGenusProb = wordGenusProb; rdb->WordPairDiffArr = WordPairDiffArr; }
m->mothurOut("DONE."); m->mothurOutEndLine();
m->mothurOut("It took " + toString(time(NULL) - start) + " seconds get probabilities. "); m->mothurOutEndLine();
}
catch(exception& e) {
m->errorOut(e, "Bayesian", "Bayesian");
exit(1);
}
}
PhyloSummary::PhyloSummary(string refTfile, GroupMap* g){
try {
m = MothurOut::getInstance();
maxLevel = 0;
ignore = false;
numSeqs = 0;
groupmap = g;
ct = NULL;
//check for necessary files
if (refTfile == "saved") { ReferenceDB* rdb = ReferenceDB::getInstance(); refTfile = rdb->getSavedTaxonomy(); }
string taxFileNameTest = m->getFullPathName((refTfile.substr(0,refTfile.find_last_of(".")+1) + "tree.sum"));
ifstream FileTest(taxFileNameTest.c_str());
if (!FileTest) {
m->mothurOut("Error: can't find " + taxFileNameTest + "."); m->mothurOutEndLine(); exit(1);
}else{
readTreeStruct(FileTest);
}
tree[0].rank = "0";
assignRank(0);
}
catch(exception& e) {
m->errorOut(e, "PhyloSummary", "PhyloSummary");
exit(1);
}
}