int ChimeraPerseusCommand::execute(){
try{
if (abort == true) { if (calledHelp) { return 0; } return 2; }
//process each file
for (int s = 0; s < fastaFileNames.size(); s++) {
m->mothurOut("Checking sequences from " + fastaFileNames[s] + " ..." ); m->mothurOutEndLine();
int start = time(NULL);
if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]); }//if user entered a file with a path then preserve it
string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "perseus.chimera";
string accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "perseus.accnos";
//string newFasta = m->getRootName(fastaFileNames[s]) + "temp";
//you provided a groupfile
string groupFile = "";
if (groupFileNames.size() != 0) { groupFile = groupFileNames[s]; }
string nameFile = "";
if (nameFileNames.size() != 0) { //you provided a namefile and we don't need to create one
nameFile = nameFileNames[s];
}else { nameFile = getNamesFile(fastaFileNames[s]); }
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
int numSeqs = 0;
int numChimeras = 0;
if (groupFile != "") {
//Parse sequences by group
SequenceParser parser(groupFile, fastaFileNames[s], nameFile);
vector<string> groups = parser.getNamesOfGroups();
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
//clears files
ofstream out, out1, out2;
m->openOutputFile(outputFileName, out); out.close();
m->openOutputFile(accnosFileName, out1); out1.close();
if(processors == 1) { numSeqs = driverGroups(parser, outputFileName, accnosFileName, 0, groups.size(), groups); }
else { numSeqs = createProcessesGroups(parser, outputFileName, accnosFileName, groups, groupFile, fastaFileNames[s], nameFile); }
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
numChimeras = deconvoluteResults(parser, outputFileName, accnosFileName);
m->mothurOut("The number of sequences checked may be larger than the number of unique sequences because some sequences are found in several samples."); m->mothurOutEndLine();
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
}else{
if (processors != 1) { m->mothurOut("Without a groupfile, mothur can only use 1 processor, continuing."); m->mothurOutEndLine(); processors = 1; }
//read sequences and store sorted by frequency
vector<seqData> sequences = readFiles(fastaFileNames[s], nameFile);
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
numSeqs = driver(outputFileName, sequences, accnosFileName, numChimeras);
}
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences. " + toString(numChimeras) + " chimeras were found."); m->mothurOutEndLine();
outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName);
outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName);
}
//set accnos file as new current accnosfile
string current = "";
itTypes = outputTypes.find("accnos");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(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, "ChimeraPerseusCommand", "execute");
exit(1);
}
}
int PreClusterCommand::execute(){
try {
if (abort == true) { if (calledHelp) { return 0; } return 2; }
int start = time(NULL);
if(align == "gotoh") { alignment = new GotohOverlap(gapOpen, gapExtend, match, misMatch, 1000); }
else if(align == "needleman") { alignment = new NeedlemanOverlap(gapOpen, match, misMatch, 1000); }
else if(align == "blast") { alignment = new BlastAlignment(gapOpen, gapExtend, match, misMatch); }
else if(align == "noalign") { alignment = new NoAlign(); }
else {
m->mothurOut(align + " is not a valid alignment option. I will run the command using needleman.");
m->mothurOutEndLine();
alignment = new NeedlemanOverlap(gapOpen, match, misMatch, 1000);
}
string fileroot = outputDir + m->getRootName(m->getSimpleName(fastafile));
map<string, string> variables;
variables["[filename]"] = fileroot;
string newNamesFile = getOutputFileName("name",variables);
string newCountFile = getOutputFileName("count",variables);
string newMapFile = getOutputFileName("map",variables); //add group name if by group
variables["[extension]"] = m->getExtension(fastafile);
string newFastaFile = getOutputFileName("fasta", variables);
outputNames.push_back(newFastaFile); outputTypes["fasta"].push_back(newFastaFile);
if (countfile == "") { outputNames.push_back(newNamesFile); outputTypes["name"].push_back(newNamesFile); }
else { outputNames.push_back(newCountFile); outputTypes["count"].push_back(newCountFile); }
if (bygroup) {
//clear out old files
ofstream outFasta; m->openOutputFile(newFastaFile, outFasta); outFasta.close();
ofstream outNames; m->openOutputFile(newNamesFile, outNames); outNames.close();
newMapFile = fileroot + "precluster.";
//parse fasta and name file by group
vector<string> groups;
if (countfile != "") {
cparser = new SequenceCountParser(countfile, fastafile);
groups = cparser->getNamesOfGroups();
}else {
if (namefile != "") { parser = new SequenceParser(groupfile, fastafile, namefile); }
else { parser = new SequenceParser(groupfile, fastafile); }
groups = parser->getNamesOfGroups();
}
if(processors == 1) { driverGroups(newFastaFile, newNamesFile, newMapFile, 0, groups.size(), groups); }
else { createProcessesGroups(newFastaFile, newNamesFile, newMapFile, groups); }
if (countfile != "") {
mergeGroupCounts(newCountFile, newNamesFile, newFastaFile);
delete cparser;
}else {
delete parser;
//run unique.seqs for deconvolute results
string inputString = "fasta=" + newFastaFile;
if (namefile != "") { inputString += ", name=" + newNamesFile; }
m->mothurOutEndLine();
m->mothurOut("/******************************************/"); m->mothurOutEndLine();
m->mothurOut("Running command: unique.seqs(" + inputString + ")"); m->mothurOutEndLine();
m->mothurCalling = true;
Command* uniqueCommand = new DeconvoluteCommand(inputString);
uniqueCommand->execute();
map<string, vector<string> > filenames = uniqueCommand->getOutputFiles();
delete uniqueCommand;
m->mothurCalling = false;
m->mothurOut("/******************************************/"); m->mothurOutEndLine();
m->renameFile(filenames["fasta"][0], newFastaFile);
m->renameFile(filenames["name"][0], newNamesFile);
}
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete alignment; return 0; }
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to run pre.cluster."); m->mothurOutEndLine();
}else {
if (processors != 1) { m->mothurOut("When using running without group information mothur can only use 1 processor, continuing."); m->mothurOutEndLine(); processors = 1; }
if (namefile != "") { readNameFile(); }
//reads fasta file and return number of seqs
int numSeqs = readFASTA(); //fills alignSeqs and makes all seqs active
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete alignment; return 0; }
if (numSeqs == 0) { m->mothurOut("Error reading fasta file...please correct."); m->mothurOutEndLine(); delete alignment; return 0; }
if (diffs > length) { m->mothurOut("Error: diffs is greater than your sequence length."); m->mothurOutEndLine(); delete alignment; return 0; }
int count = process(newMapFile);
outputNames.push_back(newMapFile); outputTypes["map"].push_back(newMapFile);
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete alignment; return 0; }
m->mothurOut("Total number of sequences before precluster was " + toString(alignSeqs.size()) + "."); m->mothurOutEndLine();
m->mothurOut("pre.cluster removed " + toString(count) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine();
if (countfile != "") { newNamesFile = newCountFile; }
printData(newFastaFile, newNamesFile, "");
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to cluster " + toString(numSeqs) + " sequences."); m->mothurOutEndLine();
}
if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete alignment; return 0; }
delete alignment;
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();
//set fasta file as new current fastafile
string current = "";
itTypes = outputTypes.find("fasta");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
}
itTypes = outputTypes.find("name");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); }
}
itTypes = outputTypes.find("count");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "PreClusterCommand", "execute");
exit(1);
}
}
