#include "chimeraperseuscommand.h"
#include "deconvolutecommand.h"
#include "sequence.hpp"
+#include "counttable.h"
+#include "sequencecountparser.h"
//**********************************************************************************************************************
vector<string> ChimeraPerseusCommand::setParameters(){
try {
CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
- CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pname);
- CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup);
+ CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none",false,false); parameters.push_back(pname);
+ CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none",false,false); parameters.push_back(pcount);
+ CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none",false,false); parameters.push_back(pgroup);
CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
string ChimeraPerseusCommand::getHelpString(){
try {
string helpString = "";
- helpString += "The chimera.perseus command reads a fastafile and namefile and outputs potentially chimeric sequences.\n";
+ helpString += "The chimera.perseus command reads a fastafile and namefile or countfile and outputs potentially chimeric sequences.\n";
helpString += "The chimera.perseus command parameters are fasta, name, group, cutoff, processors, alpha and beta.\n";
helpString += "The fasta parameter allows you to enter the fasta file containing your potentially chimeric sequences, and is required, unless you have a valid current fasta file. \n";
- helpString += "The name parameter allows you to provide a name file associated with your fasta file. It is required. \n";
+ helpString += "The name parameter allows you to provide a name file associated with your fasta file.\n";
+ helpString += "The count parameter allows you to provide a count file associated with your fasta file. A count or name file is required. \n";
helpString += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amazon.fasta \n";
helpString += "The group parameter allows you to provide a group file. When checking sequences, only sequences from the same group as the query sequence will be used as the reference. \n";
helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n";
}
}
//**********************************************************************************************************************
+string ChimeraPerseusCommand::getOutputFileNameTag(string type, string inputName=""){
+ try {
+ string outputFileName = "";
+ map<string, vector<string> >::iterator it;
+
+ //is this a type this command creates
+ it = outputTypes.find(type);
+ if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); }
+ else {
+ if (type == "chimera") { outputFileName = "perseus.chimeras"; }
+ else if (type == "accnos") { outputFileName = "perseus.accnos"; }
+ else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; }
+ }
+ return outputFileName;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ChimeraPerseusCommand", "getOutputFileNameTag");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
ChimeraPerseusCommand::ChimeraPerseusCommand(){
try {
abort = true; calledHelp = true;
ChimeraPerseusCommand::ChimeraPerseusCommand(string option) {
try {
abort = false; calledHelp = false;
+ hasCount = false;
+ hasName = false;
//allow user to run help
if(option == "help") { help(); abort = true; calledHelp = true; }
OptionParser parser(option);
map<string,string> parameters = parser.getParameters();
- ValidParameters validParameter("chimera.uchime");
+ ValidParameters validParameter("chimera.perseus");
map<string,string>::iterator it;
//check to make sure all parameters are valid for command
//check for required parameters
- bool hasName = true;
namefile = validParameter.validFile(parameters, "name", false);
- if (namefile == "not found") {
- //if there is a current fasta file, use it
- string filename = m->getNameFile();
- if (filename != "") { nameFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the name parameter."); m->mothurOutEndLine(); }
- else { m->mothurOut("You have no current namefile and the name parameter is required."); m->mothurOutEndLine(); abort = true; }
- hasName = false;
- }else {
+ if (namefile == "not found") { namefile = ""; }
+ else {
m->splitAtDash(namefile, nameFileNames);
//go through files and make sure they are good, if not, then disregard them
}
}
}
+ }
+
+ if (nameFileNames.size() != 0) { hasName = true; }
+
+ //check for required parameters
+ vector<string> countfileNames;
+ countfile = validParameter.validFile(parameters, "count", false);
+ if (countfile == "not found") {
+ countfile = "";
+ }else {
+ m->splitAtDash(countfile, countfileNames);
- //make sure there is at least one valid file left
- if (nameFileNames.size() == 0) { m->mothurOut("[ERROR]: no valid name files."); m->mothurOutEndLine(); abort = true; }
+ //go through files and make sure they are good, if not, then disregard them
+ for (int i = 0; i < countfileNames.size(); i++) {
+
+ bool ignore = false;
+ if (countfileNames[i] == "current") {
+ countfileNames[i] = m->getCountTableFile();
+ if (nameFileNames[i] != "") { m->mothurOut("Using " + countfileNames[i] + " as input file for the count parameter where you had given current."); m->mothurOutEndLine(); }
+ else {
+ m->mothurOut("You have no current count file, ignoring current."); m->mothurOutEndLine(); ignore=true;
+ //erase from file list
+ countfileNames.erase(countfileNames.begin()+i);
+ i--;
+ }
+ }
+
+ if (!ignore) {
+
+ if (inputDir != "") {
+ string path = m->hasPath(countfileNames[i]);
+ //if the user has not given a path then, add inputdir. else leave path alone.
+ if (path == "") { countfileNames[i] = inputDir + countfileNames[i]; }
+ }
+
+ int ableToOpen;
+ ifstream in;
+
+ ableToOpen = m->openInputFile(countfileNames[i], in, "noerror");
+
+ //if you can't open it, try default location
+ if (ableToOpen == 1) {
+ if (m->getDefaultPath() != "") { //default path is set
+ string tryPath = m->getDefaultPath() + m->getSimpleName(countfileNames[i]);
+ m->mothurOut("Unable to open " + countfileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ countfileNames[i] = tryPath;
+ }
+ }
+
+ if (ableToOpen == 1) {
+ if (m->getOutputDir() != "") { //default path is set
+ string tryPath = m->getOutputDir() + m->getSimpleName(countfileNames[i]);
+ m->mothurOut("Unable to open " + countfileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
+ ifstream in2;
+ ableToOpen = m->openInputFile(tryPath, in2, "noerror");
+ in2.close();
+ countfileNames[i] = tryPath;
+ }
+ }
+
+ in.close();
+
+ if (ableToOpen == 1) {
+ m->mothurOut("Unable to open " + countfileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
+ //erase from file list
+ countfileNames.erase(countfileNames.begin()+i);
+ i--;
+ }else {
+ m->setCountTableFile(countfileNames[i]);
+ }
+ }
+ }
}
-
- if (hasName && (nameFileNames.size() != fastaFileNames.size())) { m->mothurOut("[ERROR]: The number of namefiles does not match the number of fastafiles, please correct."); m->mothurOutEndLine(); abort=true; }
+
+ if (countfileNames.size() != 0) { hasCount = true; }
+
+ //make sure there is at least one valid file left
+ if (hasName && hasCount) { m->mothurOut("[ERROR]: You must enter ONLY ONE of the following: count or name."); m->mothurOutEndLine(); abort = true; }
+
+ if (!hasName && !hasCount) {
+ //if there is a current name file, use it, else look for current count file
+ string filename = m->getNameFile();
+ if (filename != "") { hasName = true; nameFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the name parameter."); m->mothurOutEndLine(); }
+ else {
+ filename = m->getCountTableFile();
+ if (filename != "") { hasCount = true; countfileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the count parameter."); m->mothurOutEndLine(); }
+ else { m->mothurOut("[ERROR]: You must provide a count or name file."); m->mothurOutEndLine(); abort = true; }
+ }
+ }
+ if (!hasName && hasCount) { nameFileNames = countfileNames; }
+
+ if (nameFileNames.size() != fastaFileNames.size()) { m->mothurOut("[ERROR]: The number of name or count files does not match the number of fastafiles, please correct."); m->mothurOutEndLine(); abort=true; }
bool hasGroup = true;
groupfile = validParameter.validFile(parameters, "group", false);
if (hasGroup && (groupFileNames.size() != fastaFileNames.size())) { m->mothurOut("[ERROR]: The number of groupfiles does not match the number of fastafiles, please correct."); m->mothurOutEndLine(); abort=true; }
+ if (hasGroup && hasCount) { m->mothurOut("[ERROR]: You must enter ONLY ONE of the following: count or group."); m->mothurOutEndLine(); abort = true; }
//if the user changes the output directory command factory will send this info to us in the output parameter
outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
m->setProcessors(temp);
- convert(temp, processors);
+ m->mothurConvert(temp, processors);
temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found"){ temp = "0.50"; }
- convert(temp, cutoff);
+ m->mothurConvert(temp, cutoff);
temp = validParameter.validFile(parameters, "alpha", false); if (temp == "not found"){ temp = "-5.54"; }
- convert(temp, alpha);
+ m->mothurConvert(temp, alpha);
temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found"){ temp = "0.33"; }
- convert(temp, beta);
+ m->mothurConvert(temp, beta);
}
}
catch(exception& e) {
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 outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + getOutputFileNameTag("chimera");
+ string accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + getOutputFileNameTag("accnos");
+
//string newFasta = m->getRootName(fastaFileNames[s]) + "temp";
//you provided a groupfile
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 (hasCount) {
+ CountTable* ct = new CountTable();
+ ct->readTable(nameFile);
+
+ if (ct->hasGroupInfo()) {
+ cparser = new SequenceCountParser(fastaFileNames[s], *ct);
+
+ vector<string> groups = cparser->getNamesOfGroups();
+
+ if (m->control_pressed) { delete ct; delete cparser; 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(outputFileName, accnosFileName, 0, groups.size(), groups); }
+ else { numSeqs = createProcessesGroups(outputFileName, accnosFileName, groups, groupFile, fastaFileNames[s], nameFile); }
+
+ if (m->control_pressed) { delete ct; delete cparser; for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
+ map<string, string> uniqueNames = cparser->getAllSeqsMap();
+ numChimeras = deconvoluteResults(uniqueNames, outputFileName, accnosFileName);
+ delete cparser;
+
+ 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) { delete ct; for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
+
+ }else {
+ if (processors != 1) { m->mothurOut("Your count file does not contain group information, mothur can only use 1 processor, continuing."); m->mothurOutEndLine(); processors = 1; }
+
+ //read sequences and store sorted by frequency
+ vector<seqData> sequences = readFiles(fastaFileNames[s], ct);
+
+ if (m->control_pressed) { delete ct; for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
+
+ numSeqs = driver(outputFileName, sequences, accnosFileName, numChimeras);
+ }
+ delete ct;
+ }else {
+ if (groupFile != "") {
+ //Parse sequences by group
+ parser = new SequenceParser(groupFile, fastaFileNames[s], nameFile);
+ vector<string> groups = parser->getNamesOfGroups();
+
+ if (m->control_pressed) { delete parser; 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(outputFileName, accnosFileName, 0, groups.size(), groups); }
+ else { numSeqs = createProcessesGroups(outputFileName, accnosFileName, groups, groupFile, fastaFileNames[s], nameFile); }
+
+ if (m->control_pressed) { delete parser; for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
+ map<string, string> uniqueNames = parser->getAllSeqsMap();
+ numChimeras = deconvoluteResults(uniqueNames, outputFileName, accnosFileName);
+ delete parser;
+
+ 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();
string inputString = "fasta=" + inputFile;
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();
nameFile = filenames["name"][0];
}
}
//**********************************************************************************************************************
-int ChimeraPerseusCommand::driverGroups(SequenceParser& parser, string outputFName, string accnos, int start, int end, vector<string> groups){
+int ChimeraPerseusCommand::driverGroups(string outputFName, string accnos, int start, int end, vector<string> groups){
try {
int totalSeqs = 0;
int start = time(NULL); if (m->control_pressed) { return 0; }
- vector<seqData> sequences = loadSequences(parser, groups[i]);
+ vector<seqData> sequences = loadSequences(groups[i]);
if (m->control_pressed) { return 0; }
}
}
//**********************************************************************************************************************
-vector<seqData> ChimeraPerseusCommand::loadSequences(SequenceParser& parser, string group){
+vector<seqData> ChimeraPerseusCommand::loadSequences(string group){
try {
-
- vector<Sequence> thisGroupsSeqs = parser.getSeqs(group);
- map<string, string> nameMap = parser.getNameMap(group);
- map<string, string>::iterator it;
-
- vector<seqData> sequences;
- bool error = false;
-
- for (int i = 0; i < thisGroupsSeqs.size(); i++) {
-
- if (m->control_pressed) { return sequences; }
-
- it = nameMap.find(thisGroupsSeqs[i].getName());
- if (it == nameMap.end()) { error = true; m->mothurOut("[ERROR]: " + thisGroupsSeqs[i].getName() + " is in your fasta file and not in your namefile, please correct."); m->mothurOutEndLine(); }
- else {
- int num = m->getNumNames(it->second);
- sequences.push_back(seqData(thisGroupsSeqs[i].getName(), thisGroupsSeqs[i].getUnaligned(), num));
- }
+ bool error = false;
+ alignLength = 0;
+ vector<seqData> sequences;
+ if (hasCount) {
+ vector<Sequence> thisGroupsSeqs = cparser->getSeqs(group);
+ map<string, int> counts = cparser->getCountTable(group);
+ map<string, int>::iterator it;
+
+ for (int i = 0; i < thisGroupsSeqs.size(); i++) {
+
+ if (m->control_pressed) { return sequences; }
+
+ it = counts.find(thisGroupsSeqs[i].getName());
+ if (it == counts.end()) { error = true; m->mothurOut("[ERROR]: " + thisGroupsSeqs[i].getName() + " is in your fasta file and not in your count file, please correct."); m->mothurOutEndLine(); }
+ else {
+ sequences.push_back(seqData(thisGroupsSeqs[i].getName(), thisGroupsSeqs[i].getUnaligned(), it->second));
+ if (thisGroupsSeqs[i].getUnaligned().length() > alignLength) { alignLength = thisGroupsSeqs[i].getUnaligned().length(); }
+ }
+ }
+ }else{
+ vector<Sequence> thisGroupsSeqs = parser->getSeqs(group);
+ map<string, string> nameMap = parser->getNameMap(group);
+ map<string, string>::iterator it;
+
+ for (int i = 0; i < thisGroupsSeqs.size(); i++) {
+
+ if (m->control_pressed) { return sequences; }
+
+ it = nameMap.find(thisGroupsSeqs[i].getName());
+ if (it == nameMap.end()) { error = true; m->mothurOut("[ERROR]: " + thisGroupsSeqs[i].getName() + " is in your fasta file and not in your namefile, please correct."); m->mothurOutEndLine(); }
+ else {
+ int num = m->getNumNames(it->second);
+ sequences.push_back(seqData(thisGroupsSeqs[i].getName(), thisGroupsSeqs[i].getUnaligned(), num));
+ if (thisGroupsSeqs[i].getUnaligned().length() > alignLength) { alignLength = thisGroupsSeqs[i].getUnaligned().length(); }
+ }
+ }
+
}
- if (error) { m->control_pressed = true; }
-
+ if (error) { m->control_pressed = true; }
//sort by frequency
sort(sequences.rbegin(), sequences.rend());
bool error = false;
ifstream in;
m->openInputFile(inputFile, in);
-
+ alignLength = 0;
+
while (!in.eof()) {
if (m->control_pressed) { in.close(); return sequences; }
if (it == nameMap.end()) { error = true; m->mothurOut("[ERROR]: " + temp.getName() + " is in your fasta file and not in your namefile, please correct."); m->mothurOutEndLine(); }
else {
sequences.push_back(seqData(temp.getName(), temp.getUnaligned(), it->second));
+ if (temp.getUnaligned().length() > alignLength) { alignLength = temp.getUnaligned().length(); }
}
}
in.close();
return sequences;
}
+ catch(exception& e) {
+ m->errorOut(e, "ChimeraPerseusCommand", "readFiles");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+vector<seqData> ChimeraPerseusCommand::readFiles(string inputFile, CountTable* ct){
+ try {
+ //read fasta file and create sequenceData structure - checking for file mismatches
+ vector<seqData> sequences;
+ ifstream in;
+ m->openInputFile(inputFile, in);
+ alignLength = 0;
+
+ while (!in.eof()) {
+ Sequence temp(in); m->gobble(in);
+
+ int count = ct->getNumSeqs(temp.getName());
+ if (m->control_pressed) { break; }
+ else {
+ sequences.push_back(seqData(temp.getName(), temp.getUnaligned(), count));
+ if (temp.getUnaligned().length() > alignLength) { alignLength = temp.getUnaligned().length(); }
+ }
+ }
+ in.close();
+
+ //sort by frequency
+ sort(sequences.rbegin(), sequences.rend());
+
+ return sequences;
+ }
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "getNamesFile");
exit(1);
}
int numSeqs = sequences.size();
- int alignLength = sequences[0].sequence.size();
+ //int alignLength = sequences[0].sequence.size();
ofstream chimeraFile;
ofstream accnosFile;
for(int i=0;i<numSeqs;i++){
if (m->control_pressed) { chimeraFile.close(); m->mothurRemove(chimeraFileName); accnosFile.close(); m->mothurRemove(accnosFileName); return 0; }
-
+
vector<bool> restricted = chimeras;
vector<vector<int> > leftDiffs(numSeqs);
string dummyA, dummyB;
- if(comparisons >= 2){
+ if (sequences[i].sequence.size() < 3) {
+ chimeraFile << i << '\t' << sequences[i].seqName << "\t0\t0\tNull\t0\t0\t0\tNull\tNull\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\tgood" << endl;
+ }else if(comparisons >= 2){
minMismatchToChimera = myPerseus.getChimera(sequences, leftDiffs, rightDiffs, leftParentBi, rightParentBi, breakPointBi, singleLeft, bestLeft, singleRight, bestRight, restricted);
if (m->control_pressed) { chimeraFile.close(); m->mothurRemove(chimeraFileName); accnosFile.close(); m->mothurRemove(accnosFileName); return 0; }
}
}
/**************************************************************************************************/
-int ChimeraPerseusCommand::createProcessesGroups(SequenceParser& parser, string outputFName, string accnos, vector<string> groups, string group, string fasta, string name) {
+int ChimeraPerseusCommand::createProcessesGroups(string outputFName, string accnos, vector<string> groups, string group, string fasta, string name) {
try {
vector<int> processIDS;
lines.push_back(linePair(startIndex, endIndex));
}
-#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
//loop through and create all the processes you want
while (process != processors) {
processIDS.push_back(pid); //create map from line number to pid so you can append files in correct order later
process++;
}else if (pid == 0){
- num = driverGroups(parser, outputFName + toString(getpid()) + ".temp", accnos + toString(getpid()) + ".temp", lines[process].start, lines[process].end, groups);
+ num = driverGroups(outputFName + toString(getpid()) + ".temp", accnos + toString(getpid()) + ".temp", lines[process].start, lines[process].end, groups);
//pass numSeqs to parent
ofstream out;
}
//do my part
- num = driverGroups(parser, outputFName, accnos, lines[0].start, lines[0].end, groups);
+ num = driverGroups(outputFName, accnos, lines[0].start, lines[0].end, groups);
//force parent to wait until all the processes are done
for (int i=0;i<processIDS.size();i++) {
// Allocate memory for thread data.
string extension = toString(i) + ".temp";
- perseusData* tempPerseus = new perseusData(alpha, beta, cutoff, outputFName+extension, fasta, name, group, accnos+extension, groups, m, lines[i].start, lines[i].end, i);
+ perseusData* tempPerseus = new perseusData(hasName, hasCount, alpha, beta, cutoff, outputFName+extension, fasta, name, group, accnos+extension, groups, m, lines[i].start, lines[i].end, i);
pDataArray.push_back(tempPerseus);
processIDS.push_back(i);
//using the main process as a worker saves time and memory
- num = driverGroups(parser, outputFName, accnos, lines[0].start, lines[0].end, groups);
+ num = driverGroups(outputFName, accnos, lines[0].start, lines[0].end, groups);
//Wait until all threads have terminated.
WaitForMultipleObjects(processors-1, hThreadArray, TRUE, INFINITE);
}
}
//**********************************************************************************************************************
-int ChimeraPerseusCommand::deconvoluteResults(SequenceParser& parser, string outputFileName, string accnosFileName){
+int ChimeraPerseusCommand::deconvoluteResults(map<string, string>& uniqueNames, string outputFileName, string accnosFileName){
try {
- map<string, string> uniqueNames = parser.getAllSeqsMap();
map<string, string>::iterator itUnique;
int total = 0;