void TFastaFile::readRecords(const string& aFastaFilename, vector<Engine::SequenceManager::Sequence>& aFastaSequences, bool removeTabCharacterInDescription)
{
string info;
string seq;
aFastaSequences.clear();
TFastaFile fastaFile(aFastaFilename);
while(fastaFile.readNextRecord(info, seq, removeTabCharacterInDescription))
{
aFastaSequences.push_back(Engine::SequenceManager::Sequence(info, seq));
}
fastaFile.closeFastaFile();
}
int seqNoise::writeOutput(string fastaFileName, string namesFileName, string uMapFileName, vector<int> finalTau, vector<int> centroids, vector<int> otuData, vector<string> sequences, vector<string> uniqueNames, vector<string> redundantNames, vector<int> seqFreq, vector<double>& distances){
try {
int numOTUs = finalTau.size();
int numSeqs = uniqueNames.size();
ofstream fastaFile(fastaFileName.c_str());
ofstream namesFile(namesFileName.c_str());
ofstream uMapFile(uMapFileName.c_str());
vector<int> maxSequenceAbund(numOTUs, 0);
vector<int> maxSequenceIndex(numOTUs, 0);
for(int i=0;i<numSeqs;i++){
if (m->control_pressed) { return 0; }
if(maxSequenceAbund[otuData[i]] < seqFreq[i]){
maxSequenceAbund[otuData[i]] = seqFreq[i];
maxSequenceIndex[otuData[i]] = i;
}
}
int count = 1;
for(int i=0;i<numOTUs;i++){
if (m->control_pressed) { return 0; }
if(finalTau[i] > 0){
if(maxSequenceIndex[i] != centroids[i] && distances[maxSequenceIndex[i]*numSeqs + centroids[i]] == 0){
// cout << uniqueNames[centroids[i]] << '\t' << uniqueNames[maxSequenceIndex[i]] << '\t' << count << endl;
centroids[i] = maxSequenceIndex[i];
}
int index = centroids[i];
fastaFile << '>' << uniqueNames[index] << endl << sequences[index] << endl;
namesFile << uniqueNames[index] << '\t';
string refSeq = sequences[index];
string redundantSeqs = redundantNames[index];;
vector<freqData> frequencyData;
for(int j=0;j<numSeqs;j++){
if(otuData[j] == i && j != index){
frequencyData.push_back(freqData(j, seqFreq[j]));
}
}
sort(frequencyData.rbegin(), frequencyData.rend());
string refDegap = degapSeq(refSeq);
vector<int> rUnalign = convertSeq(refDegap);
uMapFile << "ideal_seq_" << count << '\t' << finalTau[i] << endl;
uMapFile << uniqueNames[index] << '\t' << seqFreq[index] << "\t0\t" << refDegap << endl;
for(int j=0;j<frequencyData.size();j++){
if (m->control_pressed) { return 0; }
redundantSeqs += ',' + redundantNames[frequencyData[j].index];
uMapFile << uniqueNames[frequencyData[j].index] << '\t' << seqFreq[frequencyData[j].index] << '\t';
string querySeq = sequences[frequencyData[j].index];
string queryDegap = degapSeq(querySeq);
vector<int> qUnalign = convertSeq(queryDegap);
int udiffs = countDiffs(qUnalign, rUnalign);
uMapFile << udiffs << '\t' << queryDegap << endl;
}
uMapFile << endl;
namesFile << redundantSeqs << endl;
count++;
}
}
fastaFile.close();
namesFile.close();
uMapFile.close();
return 0;
}
catch(exception& e) {
m->errorOut(e, "seqNoise", "writeOutput");
exit(1);
}
}