tree[0].heirarchyID = "0";
maxLevel = 0;
calcTotals = true;
+ addSeqToTree("unknown", "unknown;");
}
catch(exception& e) {
m->errorOut(e, "PhyloTree", "PhyloTree");
for (int i = 0; i < numGenus; i++) {
iss >> gnode >> gsize; m->gobble(iss);
- uniqueTaxonomies[gnode] = gnode;
+ uniqueTaxonomies.insert(gnode);
totals.push_back(gsize);
}
for (int i = 0; i < numGenus; i++) {
in >> gnode >> gsize; m->gobble(in);
- uniqueTaxonomies[gnode] = gnode;
+ uniqueTaxonomies.insert(gnode);
totals.push_back(gsize);
}
maxLevel = 0;
calcTotals = true;
string name, tax;
-
#ifdef USE_MPI
int pid, num, processors;
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case
#else
- ifstream in;
- m->openInputFile(tfile, in);
-
- //read in users taxonomy file and add sequences to tree
- while(!in.eof()){
- in >> name >> tax; m->gobble(in);
-
- addSeqToTree(name, tax);
- }
- in.close();
+ map<string, string> temp;
+ m->readTax(tfile, temp);
+
+ for (map<string, string>::iterator itTemp = temp.begin(); itTemp != temp.end();) {
+ addSeqToTree(itTemp->first, itTemp->second);
+ temp.erase(itTemp++);
+ }
#endif
assignHeirarchyIDs(0);
-
+
+
+ string unknownTax = "unknown;";
+ //added last taxon until you get desired level
+ for (int i = 1; i < maxLevel; i++) {
+ unknownTax += "unclassfied;";
+ }
+
+ addSeqToTree("unknown", unknownTax);
+
//create file for summary if needed
setUp(tfile);
}
int PhyloTree::addSeqToTree(string seqName, string seqTaxonomy){
try {
-
numSeqs++;
map<string, int>::iterator childPointer;
//somehow the parent is getting one too many accnos
//use print to reassign the taxa id
taxon = getNextTaxon(seqTaxonomy, seqName);
+
+ if (m->debug) { m->mothurOut(seqName +'\t' + taxon +'\n'); }
- if (taxon == "") { m->mothurOut(seqName + " has an error in the taxonomy. This may be due to a ;;"); m->mothurOutEndLine(); if (currentNode != 0) { uniqueTaxonomies[currentNode] = currentNode; } break; }
+ if (taxon == "") { m->mothurOut(seqName + " has an error in the taxonomy. This may be due to a ;;"); m->mothurOutEndLine(); if (currentNode != 0) { uniqueTaxonomies.insert(currentNode); } break; }
childPointer = tree[currentNode].children.find(taxon);
name2Taxonomy[seqName] = currentNode;
}
- if (seqTaxonomy == "") { uniqueTaxonomies[currentNode] = currentNode; }
+ if (seqTaxonomy == "") { uniqueTaxonomies.insert(currentNode); }
}
return 0;
try {
genusIndex.clear();
//generate genusIndexes
- map<int, int>::iterator it2;
- for (it2=uniqueTaxonomies.begin(); it2!=uniqueTaxonomies.end(); it2++) { genusIndex.push_back(it2->first); }
-
+ set<int>::iterator it2;
+ map<int, int> temp;
+ for (it2=uniqueTaxonomies.begin(); it2!=uniqueTaxonomies.end(); it2++) { genusIndex.push_back(*it2); temp[*it2] = genusIndex.size()-1; }
+
+ for (map<string, int>::iterator itName = name2Taxonomy.begin(); itName != name2Taxonomy.end(); itName++) {
+ map<int, int>::iterator itTemp = temp.find(itName->second);
+ if (itTemp != temp.end()) { name2GenusNodeIndex[itName->first] = itTemp->second; }
+ else { m->mothurOut("[ERROR]: trouble making name2GenusNodeIndex, aborting.\n"); m->control_pressed = true; }
+ }
+
return genusIndex;
}
catch(exception& e) {
int counter = 1;
for(it=tree[index].children.begin();it!=tree[index].children.end();it++){
+
+ if (m->debug) { m->mothurOut(toString(index) +'\t' + tree[it->second].name +'\n'); }
+
tree[it->second].heirarchyID = tree[index].heirarchyID + '.' + toString(counter);
counter++;
tree[it->second].level = tree[index].level + 1;
map<string, int>::iterator childPointer;
vector<TaxNode> copy = tree;
-
+
//fill out tree
fillOutTree(0, copy);
}
}
+ if (m->debug) { m->mothurOut("maxLevel = " + toString(maxLevel) +'\n'); }
+
int copyNodes = copy.size();
//go through the seqs and if a sequence finest taxon is not the same level as the most finely defined taxon then classify it as unclassified where necessary
int level = copy[itLeaf->second].level;
int currentNode = itLeaf->second;
+
+ if (m->debug) { m->mothurOut(copy[currentNode].name +'\n'); }
//this sequence is unclassified at some levels
while(level < maxLevel){
level++;
+ if (m->debug) { m->mothurOut("level = " + toString(level) +'\n'); }
string taxon = "unclassified";
void PhyloTree::print(ofstream& out, vector<TaxNode>& copy){
try {
-
+
//output mothur version
out << "#" << m->getVersion() << endl;
out << copy.size() << endl;
out << maxLevel << endl;
-
+
for (int i = 0; i < copy.size(); i++) {
-
+
out << copy[i].level << '\t'<< copy[i].name << '\t' << copy[i].children.size() << '\t';
map<string,int>::iterator it;
//print genus nodes
outTree << endl << uniqueTaxonomies.size() << endl;
- map<int, int>::iterator it2;
- for (it2=uniqueTaxonomies.begin(); it2!=uniqueTaxonomies.end(); it2++) { outTree << it2->first << '\t' << tree[it2->first].accessions.size() << endl; }
+ set<int>::iterator it2;
+ for (it2=uniqueTaxonomies.begin(); it2!=uniqueTaxonomies.end(); it2++) { outTree << *it2 << '\t' << tree[*it2].accessions.size() << endl; }
outTree << endl;
outTree.close();
}
}
/**************************************************************************************************/
-int PhyloTree::getIndex(string seqName){
+int PhyloTree::getGenusIndex(string seqName){
try {
- map<string, int>::iterator itFind = name2Taxonomy.find(seqName);
+ map<string, int>::iterator itFind = name2GenusNodeIndex.find(seqName);
- if (itFind != name2Taxonomy.end()) { return name2Taxonomy[seqName]; }
- else { m->mothurOut("Cannot find " + seqName + ". Mismatch with taxonomy and template files. Cannot continue."); m->mothurOutEndLine(); exit(1);}
+ if (itFind != name2GenusNodeIndex.end()) { return itFind->second; }
+ else { m->mothurOut("Cannot find " + seqName + ". Could be a mismatch with taxonomy and template files. Cannot continue."); m->mothurOutEndLine(); exit(1);}
}
catch(exception& e) {
m->errorOut(e, "PhyloTree", "get");
try {
bool okay = true;
+ templateFileNames.push_back("unknown");
map<string, int>::iterator itFind;
map<string, int> taxonomyFileNames = name2Taxonomy;
+ if (m->debug) { m->mothurOut("[DEBUG]: in error check. Numseqs in template = " + toString(templateFileNames.size()) + ". Numseqs in taxonomy = " + toString(taxonomyFileNames.size()) + ".\n"); }
+
for (int i = 0; i < templateFileNames.size(); i++) {
itFind = taxonomyFileNames.find(templateFileNames[i]);
if (itFind != taxonomyFileNames.end()) { //found it so erase it
taxonomyFileNames.erase(itFind);
}else {
- m->mothurOut(templateFileNames[i] + " is in your template file and is not in your taxonomy file. Please correct."); m->mothurOutEndLine();
+ m->mothurOut("'" +templateFileNames[i] + "' is in your template file and is not in your taxonomy file. Please correct."); m->mothurOutEndLine();
okay = false;
}