try {
/************calculate the probablity that each word will be in a specific taxonomy*************/
- string phyloTreeName = tfile.substr(0,tfile.find_last_of(".")+1) + "tree.train";
- string probFileName = tfile.substr(0,tfile.find_last_of(".")+1) + tempFile.substr(0,tempFile.find_last_of(".")+1) + char('0'+ kmerSize) + "mer.prob";
- string probFileName2 = tfile.substr(0,tfile.find_last_of(".")+1) + tempFile.substr(0,tempFile.find_last_of(".")+1) + char('0'+ kmerSize) + "mer.numNonZero";
+ string tfileroot = tfile.substr(0,tfile.find_last_of(".")+1);
+ string tempfileroot = m->getRootName(m->getSimpleName(tempFile));
+ 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(probFileTest && probFileTest2 && phyloTreeTest){
+ //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(probFileTest && probFileTest2 && phyloTreeTest && probFileTest3 && FilesGood){
m->mothurOut("Reading template taxonomy... "); cout.flush();
phyloTree = new PhyloTree(phyloTreeTest, phyloTreeName);
//create search database and names vector
generateDatabaseAndNames(tfile, tempFile, method, ksize, 0.0, 0.0, 0.0, 0.0);
- 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);
-
- for (int j = 0; j < wordGenusProb.size(); j++) { wordGenusProb[j].resize(genusNodes.size()); }
-
-
- #ifdef USE_MPI
- int pid;
- MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
-
- if (pid == 0) {
- #endif
-
- ofstream out;
- openOutputFile(probFileName, out);
-
- out << numKmers << endl;
-
- ofstream out2;
- openOutputFile(probFileName2, out2);
-
- #ifdef USE_MPI
- }
- #endif
-
-
- //for each word
- for (int i = 0; i < numKmers; i++) {
- if (m->control_pressed) { break; }
+ //prevents errors caused by creating shortcut files if you had an error in the sanity check.
+ if (m->control_pressed) { remove(phyloTreeName.c_str()); remove(probFileName.c_str()); remove(probFileName2.c_str()); }
+ 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);
+ cout << numKmers << '\t' << genusNodes.size() << endl;
+ for (int j = 0; j < wordGenusProb.size(); j++) { wordGenusProb[j].resize(genusNodes.size()); }
+ cout << numKmers << '\t' << genusNodes.size() << endl;
+ 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
- out << i << '\t';
- #ifdef USE_MPI
- }
- #endif
+ m->openOutputFile(probFileName, out);
- vector<int> seqsWithWordi = database->getSequencesWithKmer(i);
+ //output mothur version
+ out << "#" << m->getVersion() << endl;
- map<int, int> count;
- for (int k = 0; k < genusNodes.size(); k++) { count[genusNodes[k]] = 0; }
-
- //for each sequence with that word
- for (int j = 0; j < seqsWithWordi.size(); j++) {
- int temp = phyloTree->getIndex(names[seqsWithWordi[j]]);
- count[temp]++; //increment count of seq in this genus who have this word
- }
+ out << numKmers << endl;
- //probabilityInTemplate = (# of seqs with that word in template + 0.05) / (total number of seqs in template + 1);
- float probabilityInTemplate = (seqsWithWordi.size() + 0.50) / (float) (names.size() + 1);
+ m->openOutputFile(probFileName2, out2);
+
+ //output mothur version
+ out2 << "#" << m->getVersion() << endl;
+
+ #ifdef USE_MPI
+ }
+ #endif
+
- 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[genusNodes[k]] + probabilityInTemplate) / (float) (genusTotals[k] + 1));
- if (count[genusNodes[k]] != 0) {
- #ifdef USE_MPI
- MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
- if (pid == 0) {
- #endif
+ //for each word
+ for (int i = 0; i < numKmers; i++) {
+ if (m->control_pressed) { break; }
+
+ #ifdef USE_MPI
+ MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
+
+ if (pid == 0) {
+ #endif
- out << k << '\t' << wordGenusProb[i][k] << '\t';
+ out << i << '\t';
+
+ #ifdef USE_MPI
+ }
+ #endif
+
+ vector<int> seqsWithWordi = database->getSequencesWithKmer(i);
+
+ map<int, int> count;
+ for (int k = 0; k < genusNodes.size(); k++) { count[genusNodes[k]] = 0; }
+
+ //for each sequence with that word
+ for (int j = 0; j < seqsWithWordi.size(); j++) {
+ int temp = phyloTree->getIndex(names[seqsWithWordi[j]]);
+ count[temp]++; //increment count of seq in this genus who have this word
+ }
+
+ //probabilityInTemplate = (# of seqs with that word in template + 0.05) / (total number of seqs in template + 1);
+ float probabilityInTemplate = (seqsWithWordi.size() + 0.50) / (float) (names.size() + 1);
+
+ 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[genusNodes[k]] + probabilityInTemplate) / (float) (genusTotals[k] + 1));
+ if (count[genusNodes[k]] != 0) {
+ #ifdef USE_MPI
+ int pid;
+ MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
- #ifdef USE_MPI
- }
- #endif
+ if (pid == 0) {
+ #endif
+
+ out << k << '\t' << wordGenusProb[i][k] << '\t';
+
+ #ifdef USE_MPI
+ }
+ #endif
- numNotZero++;
+ numNotZero++;
+ }
}
+
+ #ifdef USE_MPI
+ MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
+
+ if (pid == 0) {
+ #endif
+
+ out << endl;
+ out2 << probabilityInTemplate << '\t' << numNotZero << endl;
+
+ #ifdef USE_MPI
+ }
+ #endif
}
#ifdef USE_MPI
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
+
if (pid == 0) {
#endif
- out << endl;
- out2 << probabilityInTemplate << '\t' << numNotZero << endl;
+ 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);
}
-
- #ifdef USE_MPI
- MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
- if (pid == 0) {
- #endif
-
- 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);
}
m->mothurOut("DONE."); m->mothurOutEndLine();
int index = getMostProbableTaxonomy(queryKmers);
if (m->control_pressed) { return tax; }
-
+//cout << seq->getName() << '\t' << index << endl;
//bootstrap - to set confidenceScore
int numToSelect = queryKmers.size() / 8;
tax = bootstrapResults(queryKmers, index, numToSelect);
//get taxonomy
int newTax = getMostProbableTaxonomy(temp);
- TaxNode taxonomy = phyloTree->get(newTax);
-
+ TaxNode taxonomyTemp = phyloTree->get(newTax);
+
//add to confidence results
- while (taxonomy.level != 0) { //while you are not at the root
+ while (taxonomyTemp.level != 0) { //while you are not at the root
itBoot2 = confidenceScores.find(newTax); //is this a classification we already have a count on
confidenceScores[newTax]++;
}
- newTax = taxonomy.parent;
- taxonomy = phyloTree->get(taxonomy.parent);
+ newTax = taxonomyTemp.parent;
+ taxonomyTemp = phyloTree->get(newTax);
}
}
#ifdef USE_MPI
int pid, num, num2, processors;
- vector<long> positions;
- vector<long> positions2;
+ vector<unsigned long int> positions;
+ vector<unsigned long int> positions2;
MPI_Status status;
MPI_File inMPI;
MPI_File_open(MPI_COMM_WORLD, inFileName2, MPI_MODE_RDONLY, MPI_INFO_NULL, &inMPI2); //comm, filename, mode, info, filepointer
if (pid == 0) {
- positions = setFilePosEachLine(inNumName, num);
- positions2 = setFilePosEachLine(inName, num2);
+ positions = m->setFilePosEachLine(inNumName, num);
+ positions2 = m->setFilePosEachLine(inName, num2);
for(int i = 1; i < processors; i++) {
MPI_Send(&num, 1, MPI_INT, i, tag, MPI_COMM_WORLD);
positions2.resize(num2+1);
MPI_Recv(&positions2[0], (num2+1), MPI_LONG, 0, tag, MPI_COMM_WORLD, &status);
}
-
- //read numKmers
+
+ //read version
int length = positions2[1] - positions2[0];
+ char* buf5 = new char[length];
+
+ MPI_File_read_at(inMPI2, positions2[0], buf5, length, MPI_CHAR, &status);
+ delete buf5;
+
+ //read numKmers
+ length = positions2[2] - positions2[1];
char* buf = new char[length];
- MPI_File_read_at(inMPI2, positions2[0], buf, length, MPI_CHAR, &status);
+ MPI_File_read_at(inMPI2, positions2[1], buf, length, MPI_CHAR, &status);
string tempBuf = buf;
if (tempBuf.length() > length) { tempBuf = tempBuf.substr(0, length); }
int kmer, name;
vector<int> numbers; numbers.resize(numKmers);
float prob;
- vector<float> zeroCountProb; zeroCountProb.resize(numKmers);
+ vector<float> zeroCountProb; zeroCountProb.resize(numKmers);
+
+ //read version
+ length = positions[1] - positions[0];
+ char* buf6 = new char[length];
+ MPI_File_read_at(inMPI2, positions[0], buf6, length, MPI_CHAR, &status);
+ delete buf6;
+
//read file
- for(int i=0;i<num;i++){
+ for(int i=1;i<num;i++){
//read next sequence
length = positions[i+1] - positions[i];
char* buf4 = new char[length];
MPI_File_close(&inMPI);
- for(int i=1;i<num2;i++){
+ for(int i=2;i<num2;i++){
//read next sequence
length = positions2[i+1] - positions2[i];
char* buf4 = new char[length];
MPI_File_close(&inMPI2);
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case
#else
-
- in >> numKmers; gobble(in);
+ //read version
+ string line = m->getline(in); m->gobble(in);
+
+ in >> numKmers; m->gobble(in);
//initialze probabilities
wordGenusProb.resize(numKmers);
vector<int> num; num.resize(numKmers);
float prob;
vector<float> zeroCountProb; zeroCountProb.resize(numKmers);
-
+
+ //read version
+ string line2 = m->getline(inNum); m->gobble(inNum);
+
while (inNum) {
inNum >> zeroCountProb[count] >> num[count];
count++;
- gobble(inNum);
+ m->gobble(inNum);
}
inNum.close();
wordGenusProb[kmer][name] = prob;
}
- gobble(in);
+ m->gobble(in);
}
in.close();
}
}
/**************************************************************************************************/
+bool Bayesian::checkReleaseDate(ifstream& file1, ifstream& file2, ifstream& file3, ifstream& file4) {
+ try {
+
+ bool good = true;
+
+ vector<string> lines;
+ lines.push_back(m->getline(file1));
+ lines.push_back(m->getline(file2));
+ lines.push_back(m->getline(file3));
+ lines.push_back(m->getline(file4));
+
+ //before we added this check
+ if ((lines[0][0] != '#') || (lines[1][0] != '#') || (lines[2][0] != '#') || (lines[3][0] != '#')) { good = false; }
+ else {
+ //rip off #
+ for (int i = 0; i < lines.size(); i++) { lines[i] = lines[i].substr(1); }
+
+ //get mothurs current version
+ string version = m->getVersion();
+
+ vector<string> versionVector;
+ m->splitAtChar(version, versionVector, '.');
+
+ //check each files version
+ for (int i = 0; i < lines.size(); i++) {
+ vector<string> linesVector;
+ m->splitAtChar(lines[i], linesVector, '.');
+
+ if (versionVector.size() != linesVector.size()) { good = false; break; }
+ else {
+ for (int j = 0; j < versionVector.size(); j++) {
+ int num1, num2;
+ convert(versionVector[j], num1);
+ convert(linesVector[j], num2);
+
+ //if mothurs version is newer than this files version, then we want to remake it
+ if (num1 > num2) { good = false; break; }
+ }
+ }
+
+ if (!good) { break; }
+ }
+ }
+
+ if (!good) { file1.close(); file2.close(); file3.close(); file4.close(); }
+ else { file1.seekg(0); file2.seekg(0); file3.seekg(0); file4.seekg(0); }
+
+ return good;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "Bayesian", "checkReleaseDate");
+ exit(1);
+ }
+}
+/**************************************************************************************************/
projects / mothur.git / blobdiff