+ readTrees(); if (m->control_pressed) { delete tmap; for (int i = 0; i < T.size(); i++) { delete T[i]; } return 0; }
+
+ sumFile = outputDir + m->getSimpleName(treefile) + ".wsummary";
+ m->openOutputFile(sumFile, outSum);
+ outputNames.push_back(sumFile); outputTypes["wsummary"].push_back(sumFile);
+
+ SharedUtil util;
+ string s; //to make work with setgroups
+ Groups = m->getGroups();
+ vector<string> nameGroups = tmap->getNamesOfGroups();
+ util.setGroups(Groups, nameGroups, s, numGroups, "weighted"); //sets the groups the user wants to analyze
+ m->setGroups(Groups);
+
+ if (m->control_pressed) { delete tmap; for (int i = 0; i < T.size(); i++) { delete T[i]; } return 0; }
+
+ Weighted weighted(tmap, includeRoot);
+
+ int start = time(NULL);
+
+ //set or check size
+ if (subsample) {
+ //user has not set size, set size = smallest samples size
+ if (subsampleSize == -1) {
+ vector<string> temp; temp.push_back(Groups[0]);
+ subsampleSize = (tmap->getNamesSeqs(temp)).size(); //num in first group
+ for (int i = 1; i < Groups.size(); i++) {
+ temp.clear(); temp.push_back(Groups[i]);
+ int thisSize = (tmap->getNamesSeqs(temp)).size();
+ if (thisSize < subsampleSize) { subsampleSize = thisSize; }
+ }
+ m->mothurOut("\nSetting subsample size to " + toString(subsampleSize) + ".\n\n");
+ }else { //eliminate any too small groups
+ vector<string> newGroups = Groups;
+ Groups.clear();
+ for (int i = 0; i < newGroups.size(); i++) {
+ vector<string> thisGroup; thisGroup.push_back(newGroups[i]);
+ vector<string> thisGroupsSeqs = tmap->getNamesSeqs(thisGroup);
+ int thisSize = thisGroupsSeqs.size();
+
+ if (thisSize >= subsampleSize) { Groups.push_back(newGroups[i]); }
+ else { m->mothurOut("You have selected a size that is larger than "+newGroups[i]+" number of sequences, removing "+newGroups[i]+".\n"); }
+ }
+ m->setGroups(Groups);
+ }
+ }
+
+ //here in case some groups are removed by subsample
+ util.getCombos(groupComb, Groups, numComp);
+
+ if (numComp < processors) { processors = numComp; }
+
+ if (consensus && (numComp < 2)) { m->mothurOut("consensus can only be used with numComparisions greater than 1, setting consensus=f.\n"); consensus=false; }
+
+ //get weighted scores for users trees
+ for (int i = 0; i < T.size(); i++) {
+
+ if (m->control_pressed) { delete tmap; for (int i = 0; i < T.size(); i++) { delete T[i]; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ counter = 0;
+ rScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC...
+ uScores.resize(numComp); //data[0] = weightedscore AB, data[1] = weightedscore AC...
+
+ vector<double> userData; userData.resize(numComp,0); //weighted score info for user tree. data[0] = weightedscore AB, data[1] = weightedscore AC...
+ vector<double> randomData; randomData.resize(numComp,0); //weighted score info for random trees. data[0] = weightedscore AB, data[1] = weightedscore AC...
+
+ if (random) {
+ output = new ColumnFile(outputDir + m->getSimpleName(treefile) + toString(i+1) + ".weighted", itersString);
+ outputNames.push_back(outputDir + m->getSimpleName(treefile) + toString(i+1) + ".weighted");
+ outputTypes["weighted"].push_back(outputDir + m->getSimpleName(treefile) + toString(i+1) + ".weighted");
+ }
+
+ userData = weighted.getValues(T[i], processors, outputDir); //userData[0] = weightedscore
+ if (m->control_pressed) { delete tmap; for (int i = 0; i < T.size(); i++) { delete T[i]; } if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ //save users score
+ for (int s=0; s<numComp; s++) {
+ //add users score to vector of user scores
+ uScores[s].push_back(userData[s]);
+ //save users tree score for summary file
+ utreeScores.push_back(userData[s]);
+ }
+
+ if (random) { runRandomCalcs(T[i], userData); }
+
+ //clear data
+ rScores.clear();
+ uScores.clear();
+ validScores.clear();
+
+ //subsample loop
+ vector< vector<double> > calcDistsTotals; //each iter, each groupCombos dists. this will be used to make .dist files
+ for (int thisIter = 0; thisIter < subsampleIters; thisIter++) { //subsampleIters=0, if subsample=f.
+
+ if (m->control_pressed) { break; }
+
+ //copy to preserve old one - would do this in subsample but tree needs it and memory cleanup becomes messy.
+ TreeMap* newTmap = new TreeMap();
+ newTmap->getCopy(tmap);
+
+ SubSample sample;
+ Tree* subSampleTree = sample.getSample(T[i], newTmap, nameMap, subsampleSize);
+
+ //call new weighted function
+ vector<double> iterData; iterData.resize(numComp,0);
+ Weighted thisWeighted(newTmap, includeRoot);
+ iterData = thisWeighted.getValues(subSampleTree, processors, outputDir); //userData[0] = weightedscore
+
+ //save data to make ave dist, std dist
+ calcDistsTotals.push_back(iterData);
+
+ delete newTmap;
+ delete subSampleTree;
+ }
+
+ if (m->control_pressed) { delete tmap; for (int i = 0; i < T.size(); i++) { delete T[i]; } if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ if (subsample) { getAverageSTDMatrices(calcDistsTotals, i); }
+ if (consensus) { getConsensusTrees(calcDistsTotals, i); }
+ }
+
+
+ if (m->control_pressed) { delete tmap; for (int i = 0; i < T.size(); i++) { delete T[i]; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ if (phylip) { createPhylipFile(); }
+
+ printWSummaryFile();
+
+ //clear out users groups
+ m->clearGroups();
+ delete tmap;
+ for (int i = 0; i < T.size(); i++) { delete T[i]; }
+
+ if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; }
+
+ m->mothurOut("It took " + toString(time(NULL) - start) + " secs to run unifrac.weighted."); m->mothurOutEndLine();
+
+ //set phylip file as new current phylipfile
+ string current = "";
+ itTypes = outputTypes.find("phylip");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setPhylipFile(current); }
+ }
+
+ //set column file as new current columnfile
+ itTypes = outputTypes.find("column");
+ if (itTypes != outputTypes.end()) {
+ if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setColumnFile(current); }
+ }
+
+ m->mothurOutEndLine();
+ m->mothurOut("Output File Names: "); m->mothurOutEndLine();
+ for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
+ m->mothurOutEndLine();
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracWeightedCommand", "execute");
+ exit(1);
+ }
+}
+/**************************************************************************************************/
+int UnifracWeightedCommand::getAverageSTDMatrices(vector< vector<double> >& dists, int treeNum) {
+ try {
+ //we need to find the average distance and standard deviation for each groups distance
+
+ //finds sum
+ vector<double> averages; averages.resize(numComp, 0);
+ for (int thisIter = 0; thisIter < subsampleIters; thisIter++) {
+ for (int i = 0; i < dists[thisIter].size(); i++) {
+ averages[i] += dists[thisIter][i];
+ }
+ }
+
+ //finds average.
+ for (int i = 0; i < averages.size(); i++) { averages[i] /= (float) subsampleIters; }
+
+ //find standard deviation
+ vector<double> stdDev; stdDev.resize(numComp, 0);
+
+ for (int thisIter = 0; thisIter < iters; thisIter++) { //compute the difference of each dist from the mean, and square the result of each
+ for (int j = 0; j < dists[thisIter].size(); j++) {
+ stdDev[j] += ((dists[thisIter][j] - averages[j]) * (dists[thisIter][j] - averages[j]));
+ }
+ }
+ for (int i = 0; i < stdDev.size(); i++) {
+ stdDev[i] /= (float) subsampleIters;
+ stdDev[i] = sqrt(stdDev[i]);
+ }
+
+ //make matrix with scores in it
+ vector< vector<double> > avedists; avedists.resize(m->getNumGroups());
+ for (int i = 0; i < m->getNumGroups(); i++) {
+ avedists[i].resize(m->getNumGroups(), 0.0);
+ }
+
+ //make matrix with scores in it
+ vector< vector<double> > stddists; stddists.resize(m->getNumGroups());
+ for (int i = 0; i < m->getNumGroups(); i++) {
+ stddists[i].resize(m->getNumGroups(), 0.0);
+ }
+
+ //flip it so you can print it
+ int count = 0;
+ for (int r=0; r<m->getNumGroups(); r++) {
+ for (int l = 0; l < r; l++) {
+ avedists[r][l] = averages[count];
+ avedists[l][r] = averages[count];
+ stddists[r][l] = stdDev[count];
+ stddists[l][r] = stdDev[count];
+ count++;
+ }
+ }
+
+ string aveFileName = outputDir + m->getSimpleName(treefile) + toString(treeNum+1) + ".weighted.ave.dist";
+ outputNames.push_back(aveFileName); outputTypes["phylip"].push_back(aveFileName);
+
+ ofstream out;
+ m->openOutputFile(aveFileName, out);
+
+ string stdFileName = outputDir + m->getSimpleName(treefile) + toString(treeNum+1) + ".weighted.std.dist";
+ outputNames.push_back(stdFileName); outputTypes["phylip"].push_back(stdFileName);
+
+ ofstream outStd;
+ m->openOutputFile(stdFileName, outStd);
+
+ if ((outputForm == "lt") || (outputForm == "square")) {
+ //output numSeqs
+ out << m->getNumGroups() << endl;
+ outStd << m->getNumGroups() << endl;
+ }
+
+ //output to file
+ for (int r=0; r<m->getNumGroups(); r++) {
+ //output name
+ string name = (m->getGroups())[r];
+ if (name.length() < 10) { //pad with spaces to make compatible
+ while (name.length() < 10) { name += " "; }
+ }
+
+ if (outputForm == "lt") {
+ out << name << '\t';
+ outStd << name << '\t';
+
+ //output distances
+ for (int l = 0; l < r; l++) { out << avedists[r][l] << '\t'; outStd << stddists[r][l] << '\t';}
+ out << endl; outStd << endl;
+ }else if (outputForm == "square") {
+ out << name << '\t';
+ outStd << name << '\t';
+
+ //output distances
+ for (int l = 0; l < m->getNumGroups(); l++) { out << avedists[r][l] << '\t'; outStd << stddists[r][l] << '\t'; }
+ out << endl; outStd << endl;
+ }else{
+ //output distances
+ for (int l = 0; l < r; l++) {
+ string otherName = (m->getGroups())[l];
+ if (otherName.length() < 10) { //pad with spaces to make compatible
+ while (otherName.length() < 10) { otherName += " "; }
+ }
+
+ out << name << '\t' << otherName << avedists[r][l] << endl;
+ outStd << name << '\t' << otherName << stddists[r][l] << endl;
+ }
+ }
+ }
+ out.close();
+ outStd.close();
+
+ return 0;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracWeightedCommand", "getAverageSTDMatrices");
+ exit(1);
+ }
+}
+
+/**************************************************************************************************/
+int UnifracWeightedCommand::getConsensusTrees(vector< vector<double> >& dists, int treeNum) {
+ try {
+
+ //used in tree constructor
+ m->runParse = false;
+
+ //create treemap class from groupmap for tree class to use
+ TreeMap* newTmap = new TreeMap();
+ newTmap->makeSim(m->getGroups());
+
+ //clear old tree names if any
+ m->Treenames.clear();
+
+ //fills globaldatas tree names
+ m->Treenames = m->getGroups();
+
+ vector<Tree*> newTrees = buildTrees(dists, treeNum, newTmap); //also creates .all.tre file containing the trees created
+
+ if (m->control_pressed) { delete newTmap; return 0; }
+
+ Consensus con;
+ Tree* conTree = con.getTree(newTrees, newTmap);
+
+ //create a new filename
+ string conFile = outputDir + m->getRootName(m->getSimpleName(treefile)) + toString(treeNum+1) + ".weighted.cons.tre";
+ outputNames.push_back(conFile); outputTypes["tree"].push_back(conFile);
+ ofstream outTree;
+ m->openOutputFile(conFile, outTree);
+
+ if (conTree != NULL) { conTree->print(outTree, "boot"); delete conTree; }
+ outTree.close();
+ delete newTmap;
+
+ return 0;
+
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracWeightedCommand", "getConsensusTrees");
+ exit(1);
+ }
+}
+/**************************************************************************************************/
+
+vector<Tree*> UnifracWeightedCommand::buildTrees(vector< vector<double> >& dists, int treeNum, TreeMap* mytmap) {
+ try {
+
+ vector<Tree*> trees;
+
+ //create a new filename
+ string outputFile = outputDir + m->getRootName(m->getSimpleName(treefile)) + toString(treeNum+1) + ".weighted.all.tre";
+ outputNames.push_back(outputFile); outputTypes["tree"].push_back(outputFile);
+
+ ofstream outAll;
+ m->openOutputFile(outputFile, outAll);
+
+
+ for (int i = 0; i < dists.size(); i++) { //dists[0] are the dists for the first subsampled tree.
+
+ if (m->control_pressed) { break; }
+
+ //make matrix with scores in it
+ vector< vector<double> > sims; sims.resize(m->getNumGroups());
+ for (int j = 0; j < m->getNumGroups(); j++) {
+ sims[j].resize(m->getNumGroups(), 0.0);
+ }
+
+ int count = 0;
+ for (int r=0; r<m->getNumGroups(); r++) {
+ for (int l = 0; l < r; l++) {
+ double sim = -(dists[i][count]-1.0);
+ sims[r][l] = sim;
+ sims[l][r] = sim;
+ count++;
+ }
+ }
+
+ //create tree
+ Tree* tempTree = new Tree(mytmap, sims);
+ tempTree->assembleTree();
+
+ trees.push_back(tempTree);
+
+ //print tree
+ tempTree->print(outAll);
+ }
+
+ outAll.close();
+
+ if (m->control_pressed) { for (int i = 0; i < trees.size(); i++) { delete trees[i]; trees[i] = NULL; } m->mothurRemove(outputFile); }
+
+ return trees;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "UnifracWeightedCommand", "buildTrees");
+ exit(1);
+ }
+}
+/**************************************************************************************************/
+
+int UnifracWeightedCommand::readTrees() {
+ try {
+
+ if (groupfile != "") {