]> git.donarmstrong.com Git - mothur.git/blobdiff - screenseqscommand.cpp
added otu.association command. added calcSpearman, calcKendall and calcPearson functi...
[mothur.git] / screenseqscommand.cpp
index 7a6ea3a5f5cc8f0906c8e49c39d05d1d689f7e51..41067396c6f5333faeaf3346afd9b865ad351531 100644 (file)
@@ -16,7 +16,9 @@ vector<string> ScreenSeqsCommand::setParameters(){
                CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
                CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
                CommandParameter pgroup("group", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pgroup);
+               CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pqfile);
                CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(palignreport);
+               CommandParameter ptax("taxonomy", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(ptax);
                CommandParameter pstart("start", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pstart);
                CommandParameter pend("end", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pend);
                CommandParameter pmaxambig("maxambig", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pmaxambig);
@@ -43,8 +45,9 @@ string ScreenSeqsCommand::getHelpString(){
        try {
                string helpString = "";
                helpString += "The screen.seqs command reads a fastafile and creates .....\n";
-               helpString += "The screen.seqs command parameters are fasta, start, end, maxambig, maxhomop, minlength, maxlength, name, group, optimize, criteria and processors.\n";
+               helpString += "The screen.seqs command parameters are fasta, start, end, maxambig, maxhomop, minlength, maxlength, name, group, qfile, alignreport, taxonomy, optimize, criteria and processors.\n";
                helpString += "The fasta parameter is required.\n";
+               helpString += "The alignreport and taxonomy parameters allow you to remove bad seqs from taxonomy and alignreport files.\n";
                helpString += "The start parameter .... The default is -1.\n";
                helpString += "The end parameter .... The default is -1.\n";
                helpString += "The maxambig parameter allows you to set the maximum number of ambigious bases allowed. The default is -1.\n";
@@ -59,7 +62,7 @@ string ScreenSeqsCommand::getHelpString(){
                helpString += "screen.seqs(fasta=yourFastaFile, name=youNameFile, group=yourGroupFIle, start=yourStart, end=yourEnd, maxambig=yourMaxambig,  \n";
                helpString += "maxhomop=yourMaxhomop, minlength=youMinlength, maxlength=yourMaxlength)  \n";    
                helpString += "Example screen.seqs(fasta=abrecovery.fasta, name=abrecovery.names, group=abrecovery.groups, start=..., end=..., maxambig=..., maxhomop=..., minlength=..., maxlength=...).\n";
-               helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n";
+               helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n";
                return helpString;
        }
        catch(exception& e) {
@@ -78,6 +81,8 @@ ScreenSeqsCommand::ScreenSeqsCommand(){
                outputTypes["group"] = tempOutNames;
                outputTypes["alignreport"] = tempOutNames;
                outputTypes["accnos"] = tempOutNames;
+               outputTypes["qfile"] = tempOutNames;
+               outputTypes["taxonomy"] = tempOutNames;
        }
        catch(exception& e) {
                m->errorOut(e, "ScreenSeqsCommand", "ScreenSeqsCommand");
@@ -92,6 +97,7 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option)  {
                
                //allow user to run help
                if(option == "help") { help(); abort = true; calledHelp = true; }
+               else if(option == "citation") { citation(); abort = true; calledHelp = true;}
                
                else {
                        vector<string> myArray = setParameters();
@@ -114,6 +120,8 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option)  {
                        outputTypes["group"] = tempOutNames;
                        outputTypes["alignreport"] = tempOutNames;
                        outputTypes["accnos"] = tempOutNames;
+                       outputTypes["qfile"] = tempOutNames;
+                       outputTypes["taxonomy"] = tempOutNames;
                        
                        //if the user changes the input directory command factory will send this info to us in the output parameter 
                        string inputDir = validParameter.validFile(parameters, "inputdir", false);              
@@ -151,6 +159,22 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option)  {
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["alignreport"] = inputDir + it->second;              }
                                }
+                               
+                               it = parameters.find("qfile");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = m->hasPath(it->second);
+                                       //if the user has not given a path then, add inputdir. else leave path alone.
+                                       if (path == "") {       parameters["qfile"] = inputDir + it->second;            }
+                               }
+                               
+                               it = parameters.find("taxonomy");
+                               //user has given a template file
+                               if(it != parameters.end()){ 
+                                       path = m->hasPath(it->second);
+                                       //if the user has not given a path then, add inputdir. else leave path alone.
+                                       if (path == "") {       parameters["taxonomy"] = inputDir + it->second;         }
+                               }
                        }
 
                        //check for required parameters
@@ -160,19 +184,31 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option)  {
                                if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
                                else {  m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
                        }
-                       else if (fastafile == "not open") { abort = true; }     
+                       else if (fastafile == "not open") { abort = true; }
+                       else { m->setFastaFile(fastafile); }
        
                        groupfile = validParameter.validFile(parameters, "group", true);
                        if (groupfile == "not open") { abort = true; }  
                        else if (groupfile == "not found") { groupfile = ""; }
+                       else { m->setGroupFile(groupfile); }
+                       
+                       qualfile = validParameter.validFile(parameters, "qfile", true);
+                       if (qualfile == "not open") { abort = true; }   
+                       else if (qualfile == "not found") { qualfile = ""; }
+                       else { m->setQualFile(qualfile); }
                        
                        namefile = validParameter.validFile(parameters, "name", true);
                        if (namefile == "not open") { namefile = ""; abort = true; }
                        else if (namefile == "not found") { namefile = ""; }    
-
+                       else { m->setNameFile(namefile); }
+                       
                        alignreport = validParameter.validFile(parameters, "alignreport", true);
                        if (alignreport == "not open") { abort = true; }
-                       else if (alignreport == "not found") { alignreport = ""; }      
+                       else if (alignreport == "not found") { alignreport = ""; }
+                       
+                       taxonomy = validParameter.validFile(parameters, "taxonomy", true);
+                       if (taxonomy == "not open") { abort = true; }
+                       else if (taxonomy == "not found") { taxonomy = ""; }    
                        
                        //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"){  
@@ -184,26 +220,26 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option)  {
                        // ...at some point should added some additional type checking...
                        string temp;
                        temp = validParameter.validFile(parameters, "start", false);            if (temp == "not found") { temp = "-1"; }
-                       convert(temp, startPos); 
+                       m->mothurConvert(temp, startPos); 
                
                        temp = validParameter.validFile(parameters, "end", false);                      if (temp == "not found") { temp = "-1"; }
-                       convert(temp, endPos);  
+                       m->mothurConvert(temp, endPos);  
 
                        temp = validParameter.validFile(parameters, "maxambig", false);         if (temp == "not found") { temp = "-1"; }
-                       convert(temp, maxAmbig);  
+                       m->mothurConvert(temp, maxAmbig);  
 
                        temp = validParameter.validFile(parameters, "maxhomop", false);         if (temp == "not found") { temp = "-1"; }
-                       convert(temp, maxHomoP);  
+                       m->mothurConvert(temp, maxHomoP);  
 
                        temp = validParameter.validFile(parameters, "minlength", false);        if (temp == "not found") { temp = "-1"; }
-                       convert(temp, minLength); 
+                       m->mothurConvert(temp, minLength); 
                        
                        temp = validParameter.validFile(parameters, "maxlength", false);        if (temp == "not found") { temp = "-1"; }
-                       convert(temp, maxLength); 
+                       m->mothurConvert(temp, maxLength); 
                        
                        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, "optimize", false); //optimizing trumps the optimized values original value
                        if (temp == "not found"){       temp = "none";          }
@@ -223,7 +259,12 @@ ScreenSeqsCommand::ScreenSeqsCommand(string option)  {
                        if (optimize.size() == 1) { if (optimize[0] == "none") { optimize.clear(); } }
                        
                        temp = validParameter.validFile(parameters, "criteria", false); if (temp == "not found"){       temp = "90";                            }
-                       convert(temp, criteria); 
+                       m->mothurConvert(temp, criteria); 
+                       
+                       if (namefile == "") {
+                               vector<string> files; files.push_back(fastafile);
+                               parser.getNameFile(files);
+                       }
                }
 
        }
@@ -240,17 +281,22 @@ int ScreenSeqsCommand::execute(){
                if (abort == true) { if (calledHelp) { return 0; }  return 2;   }
                
                //if the user want to optimize we need to know the 90% mark
-               vector<unsigned long int> positions;
+               vector<unsigned long long> positions;
                if (optimize.size() != 0) {  //get summary is paralellized so we need to divideFile, no need to do this step twice so I moved it here
                        //use the namefile to optimize correctly
                        if (namefile != "") { nameMap = m->readNames(namefile); }
                        getSummary(positions); 
                } 
                else { 
+                       #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
                        positions = m->divideFile(fastafile, processors);
                        for (int i = 0; i < (positions.size()-1); i++) {
                                lines.push_back(new linePair(positions[i], positions[(i+1)]));
-                       }       
+                       }
+                       #else 
+                               positions.push_back(0); positions.push_back(1000);
+                               lines.push_back(new linePair(0, 1000));
+                       #endif
                }
                                
                string goodSeqFile = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "good" + m->getExtension(fastafile);
@@ -259,16 +305,16 @@ int ScreenSeqsCommand::execute(){
                int numFastaSeqs = 0;
                set<string> badSeqNames;
                int start = time(NULL);
-               
+       
 #ifdef USE_MPI 
                        int pid, numSeqsPerProcessor; 
                        int tag = 2001;
-                       vector<unsigned long int> MPIPos;
+                       vector<unsigned long long> MPIPos;
                        
                        MPI_Status status; 
                        MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
                        MPI_Comm_size(MPI_COMM_WORLD, &processors); 
-
+       
                        MPI_File inMPI;
                        MPI_File outMPIGood;
                        MPI_File outMPIBadAccnos;
@@ -373,7 +419,7 @@ int ScreenSeqsCommand::execute(){
                        if(processors == 1){
                                numFastaSeqs = driver(lines[0], goodSeqFile, badAccnosFile, fastafile, badSeqNames);
                                
-                               if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; }
+                               if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; }
                                
                        }else{
                                processIDS.resize(0);
@@ -386,13 +432,13 @@ int ScreenSeqsCommand::execute(){
                                //append alignment and report files
                                for(int i=1;i<processors;i++){
                                        m->appendFiles((goodSeqFile + toString(processIDS[i]) + ".temp"), goodSeqFile);
-                                       remove((goodSeqFile + toString(processIDS[i]) + ".temp").c_str());
+                                       m->mothurRemove((goodSeqFile + toString(processIDS[i]) + ".temp"));
                        
                                        m->appendFiles((badAccnosFile + toString(processIDS[i]) + ".temp"), badAccnosFile);
-                                       remove((badAccnosFile + toString(processIDS[i]) + ".temp").c_str());
+                                       m->mothurRemove((badAccnosFile + toString(processIDS[i]) + ".temp"));
                                }
                                
-                               if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; }
+                               if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; }
                                
                                //read badSeqs in because root process doesnt know what other "bad" seqs the children found
                                ifstream inBad;
@@ -411,7 +457,7 @@ int ScreenSeqsCommand::execute(){
        #else
                        numFastaSeqs = driver(lines[0], goodSeqFile, badAccnosFile, fastafile, badSeqNames);
                        
-                       if (m->control_pressed) { remove(goodSeqFile.c_str()); return 0; }
+                       if (m->control_pressed) { m->mothurRemove(goodSeqFile); return 0; }
                        
        #endif
 
@@ -452,17 +498,19 @@ int ScreenSeqsCommand::execute(){
                                                                                                                                                                        
                if(namefile != "" && groupfile != "")   {       
                        screenNameGroupFile(badSeqNames);       
-                       if (m->control_pressed) {  remove(goodSeqFile.c_str()); return 0; }
+                       if (m->control_pressed) {  m->mothurRemove(goodSeqFile); return 0; }
                }else if(namefile != "")        {       
                        screenNameGroupFile(badSeqNames);
-                       if (m->control_pressed) {  remove(goodSeqFile.c_str());  return 0; }    
+                       if (m->control_pressed) {  m->mothurRemove(goodSeqFile);  return 0; }   
                }else if(groupfile != "")                               {       screenGroupFile(badSeqNames);           }       // this screens just the group
                
-               if (m->control_pressed) { remove(goodSeqFile.c_str());  return 0; }
+               if (m->control_pressed) { m->mothurRemove(goodSeqFile);  return 0; }
 
                if(alignreport != "")                                   {       screenAlignReport(badSeqNames);         }
+               if(qualfile != "")                                              {       screenQual(badSeqNames);                        }
+               if(taxonomy != "")                                              {       screenTaxonomy(badSeqNames);            }
                
-               if (m->control_pressed) { remove(goodSeqFile.c_str());  return 0; }
+               if (m->control_pressed) { m->mothurRemove(goodSeqFile);  return 0; }
                
                #ifdef USE_MPI
                        }
@@ -492,6 +540,16 @@ int ScreenSeqsCommand::execute(){
                if (itTypes != outputTypes.end()) {
                        if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); }
                }
+               
+               itTypes = outputTypes.find("qfile");
+               if (itTypes != outputTypes.end()) {
+                       if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setQualFile(current); }
+               }
+               
+               itTypes = outputTypes.find("taxonomy");
+               if (itTypes != outputTypes.end()) {
+                       if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
+               }
 
                m->mothurOut("It took " + toString(time(NULL) - start) + " secs to screen " + toString(numFastaSeqs) + " sequences.");
                m->mothurOutEndLine();
@@ -520,7 +578,7 @@ int ScreenSeqsCommand::screenNameGroupFile(set<string> badSeqNames){
                ofstream goodNameOut;   m->openOutputFile(goodNameFile, goodNameOut);
                
                while(!inputNames.eof()){
-                       if (m->control_pressed) { goodNameOut.close();  inputNames.close(); remove(goodNameFile.c_str());  return 0; }
+                       if (m->control_pressed) { goodNameOut.close();  inputNames.close(); m->mothurRemove(goodNameFile);  return 0; }
 
                        inputNames >> seqName >> seqList;
                        it = badSeqNames.find(seqName);
@@ -566,7 +624,7 @@ int ScreenSeqsCommand::screenNameGroupFile(set<string> badSeqNames){
                        ofstream goodGroupOut;  m->openOutputFile(goodGroupFile, goodGroupOut);
                        
                        while(!inputGroups.eof()){
-                               if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); remove(goodNameFile.c_str());  remove(goodGroupFile.c_str()); return 0; }
+                               if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); m->mothurRemove(goodNameFile);  m->mothurRemove(goodGroupFile); return 0; }
 
                                inputGroups >> seqName >> group;
                                
@@ -602,7 +660,7 @@ int ScreenSeqsCommand::screenNameGroupFile(set<string> badSeqNames){
        }
 }
 //***************************************************************************************************************
-int ScreenSeqsCommand::getSummary(vector<unsigned long int>& positions){
+int ScreenSeqsCommand::getSummary(vector<unsigned long long>& positions){
        try {
                
                vector<int> startPosition;
@@ -611,12 +669,23 @@ int ScreenSeqsCommand::getSummary(vector<unsigned long int>& positions){
                vector<int> ambigBases;
                vector<int> longHomoPolymer;
                
-               vector<unsigned long int> positions = m->divideFile(fastafile, processors);
-                               
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+               vector<unsigned long long> positions = m->divideFile(fastafile, processors);
+               
                for (int i = 0; i < (positions.size()-1); i++) {
                        lines.push_back(new linePair(positions[i], positions[(i+1)]));
                }       
+#else
+               lines.push_back(new linePair(0, 1000));
+#endif
+               
+#ifdef USE_MPI
+               int pid;
+               MPI_Comm_rank(MPI_COMM_WORLD, &pid); 
                
+               if (pid == 0) { 
+                       driverCreateSummary(startPosition, endPosition, seqLength, ambigBases, longHomoPolymer, fastafile, lines[0]);
+#else
                int numSeqs = 0;
                #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
                        if(processors == 1){
@@ -630,7 +699,7 @@ int ScreenSeqsCommand::getSummary(vector<unsigned long int>& positions){
                        numSeqs = driverCreateSummary(startPosition, endPosition, seqLength, ambigBases, longHomoPolymer, fastafile, lines[0]);
                        if (m->control_pressed) {  return 0; }
                #endif
-
+#endif
                sort(startPosition.begin(), startPosition.end());
                sort(endPosition.begin(), endPosition.end());
                sort(seqLength.begin(), seqLength.end());
@@ -649,6 +718,33 @@ int ScreenSeqsCommand::getSummary(vector<unsigned long int>& positions){
                        else if (optimize[i] == "maxlength") { maxLength = seqLength[criteriaPercentile]; m->mothurOut("Optimizing maxlength to " + toString(maxLength) + "."); m->mothurOutEndLine(); }
                }
 
+#ifdef USE_MPI
+               }
+               
+               MPI_Status status; 
+               MPI_Comm_rank(MPI_COMM_WORLD, &pid); 
+               MPI_Comm_size(MPI_COMM_WORLD, &processors); 
+                       
+               if (pid == 0) { 
+                       //send file positions to all processes
+                       for(int i = 1; i < processors; i++) { 
+                               MPI_Send(&startPos, 1, MPI_INT, i, 2001, MPI_COMM_WORLD);
+                               MPI_Send(&endPos, 1, MPI_INT, i, 2001, MPI_COMM_WORLD);
+                               MPI_Send(&maxAmbig, 1, MPI_INT, i, 2001, MPI_COMM_WORLD);
+                               MPI_Send(&maxHomoP, 1, MPI_INT, i, 2001, MPI_COMM_WORLD);
+                               MPI_Send(&minLength, 1, MPI_INT, i, 2001, MPI_COMM_WORLD);
+                               MPI_Send(&maxLength, 1, MPI_INT, i, 2001, MPI_COMM_WORLD);
+                       }
+               }else {
+                       MPI_Recv(&startPos, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD, &status);
+                       MPI_Recv(&endPos, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD, &status);
+                       MPI_Recv(&maxAmbig, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD, &status);
+                       MPI_Recv(&maxHomoP, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD, &status);
+                       MPI_Recv(&minLength, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD, &status);
+                       MPI_Recv(&maxLength, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD, &status);
+               }
+               MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case
+#endif
                return 0;
        }
        catch(exception& e) {
@@ -695,9 +791,9 @@ int ScreenSeqsCommand::driverCreateSummary(vector<int>& startPosition, vector<in
                                
                                count++;
                        }
-                       
+                       //if((count) % 100 == 0){       m->mothurOut("Optimizing sequence: " + toString(count)); m->mothurOutEndLine();         }
                        #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
-                               unsigned long int pos = in.tellg();
+                               unsigned long long pos = in.tellg();
                                if ((pos == -1) || (pos >= filePos->end)) { break; }
                        #else
                                if (in.eof()) { break; }
@@ -779,7 +875,7 @@ int ScreenSeqsCommand::createProcessesCreateSummary(vector<int>& startPosition,
                        for (int k = 0; k < tempNum; k++)                       {               in >> temp; longHomoPolymer.push_back(temp);    }               m->gobble(in);
                                
                        in.close();
-                       remove(tempFilename.c_str());
+                       m->mothurRemove(tempFilename);
                }
                
                return num;
@@ -805,7 +901,7 @@ int ScreenSeqsCommand::screenGroupFile(set<string> badSeqNames){
                ofstream goodGroupOut;  m->openOutputFile(goodGroupFile, goodGroupOut);
                
                while(!inputGroups.eof()){
-                       if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); remove(goodGroupFile.c_str()); return 0; }
+                       if (m->control_pressed) { goodGroupOut.close(); inputGroups.close(); m->mothurRemove(goodGroupFile); return 0; }
 
                        inputGroups >> seqName >> group;
                        it = badSeqNames.find(seqName);
@@ -819,7 +915,7 @@ int ScreenSeqsCommand::screenGroupFile(set<string> badSeqNames){
                        m->gobble(inputGroups);
                }
                
-               if (m->control_pressed) { goodGroupOut.close();  inputGroups.close(); remove(goodGroupFile.c_str());  return 0; }
+               if (m->control_pressed) { goodGroupOut.close();  inputGroups.close(); m->mothurRemove(goodGroupFile);  return 0; }
 
                //we were unable to remove some of the bad sequences
                if (badSeqNames.size() != 0) {
@@ -832,7 +928,7 @@ int ScreenSeqsCommand::screenGroupFile(set<string> badSeqNames){
                inputGroups.close();
                goodGroupOut.close();
                
-               if (m->control_pressed) { remove(goodGroupFile.c_str());   }
+               if (m->control_pressed) { m->mothurRemove(goodGroupFile);   }
                
                return 0;
        
@@ -863,7 +959,7 @@ int ScreenSeqsCommand::screenAlignReport(set<string> badSeqNames){
                }
 
                while(!inputAlignReport.eof()){
-                       if (m->control_pressed) { goodAlignReportOut.close(); inputAlignReport.close(); remove(goodAlignReportFile.c_str()); return 0; }
+                       if (m->control_pressed) { goodAlignReportOut.close(); inputAlignReport.close(); m->mothurRemove(goodAlignReportFile); return 0; }
 
                        inputAlignReport >> seqName;
                        it = badSeqNames.find(seqName);
@@ -883,7 +979,7 @@ int ScreenSeqsCommand::screenAlignReport(set<string> badSeqNames){
                        m->gobble(inputAlignReport);
                }
                
-               if (m->control_pressed) { goodAlignReportOut.close();  inputAlignReport.close(); remove(goodAlignReportFile.c_str());  return 0; }
+               if (m->control_pressed) { goodAlignReportOut.close();  inputAlignReport.close(); m->mothurRemove(goodAlignReportFile);  return 0; }
 
                //we were unable to remove some of the bad sequences
                if (badSeqNames.size() != 0) {
@@ -896,7 +992,7 @@ int ScreenSeqsCommand::screenAlignReport(set<string> badSeqNames){
                inputAlignReport.close();
                goodAlignReportOut.close();
                                
-               if (m->control_pressed) {  remove(goodAlignReportFile.c_str());  return 0; }
+               if (m->control_pressed) {  m->mothurRemove(goodAlignReportFile);  return 0; }
                
                return 0;
        
@@ -906,6 +1002,129 @@ int ScreenSeqsCommand::screenAlignReport(set<string> badSeqNames){
                exit(1);
        }
        
+}
+//***************************************************************************************************************
+
+int ScreenSeqsCommand::screenTaxonomy(set<string> badSeqNames){
+       try {
+               ifstream input;
+               m->openInputFile(taxonomy, input);
+               string seqName, tax;
+               set<string>::iterator it;
+               
+               string goodTaxFile = outputDir + m->getRootName(m->getSimpleName(taxonomy)) + "good" + m->getExtension(taxonomy);
+               outputNames.push_back(goodTaxFile);  outputTypes["taxonomy"].push_back(goodTaxFile);
+               ofstream goodTaxOut;    m->openOutputFile(goodTaxFile, goodTaxOut);
+                               
+               while(!input.eof()){
+                       if (m->control_pressed) { goodTaxOut.close(); input.close(); m->mothurRemove(goodTaxFile); return 0; }
+                       
+                       input >> seqName >> tax;
+                       it = badSeqNames.find(seqName);
+                       
+                       if(it != badSeqNames.end()){ badSeqNames.erase(it); }
+                       else{
+                               goodTaxOut << seqName << '\t' << tax << endl;
+                       }
+                       m->gobble(input);
+               }
+               
+               if (m->control_pressed) { goodTaxOut.close(); input.close(); m->mothurRemove(goodTaxFile); return 0; }
+               
+               //we were unable to remove some of the bad sequences
+               if (badSeqNames.size() != 0) {
+                       for (it = badSeqNames.begin(); it != badSeqNames.end(); it++) {  
+                               m->mothurOut("Your taxonomy file does not include the sequence " + *it + " please correct."); 
+                               m->mothurOutEndLine();
+                       }
+               }
+               
+               input.close();
+               goodTaxOut.close();
+               
+               if (m->control_pressed) {  m->mothurRemove(goodTaxFile);  return 0; }
+               
+               return 0;
+               
+       }
+       catch(exception& e) {
+               m->errorOut(e, "ScreenSeqsCommand", "screenTaxonomy");
+               exit(1);
+       }
+       
+}
+//***************************************************************************************************************
+
+int ScreenSeqsCommand::screenQual(set<string> badSeqNames){
+       try {
+               ifstream in;
+               m->openInputFile(qualfile, in);
+               set<string>::iterator it;
+               
+               string goodQualFile = outputDir + m->getRootName(m->getSimpleName(qualfile)) + "good" + m->getExtension(qualfile);
+               outputNames.push_back(goodQualFile);  outputTypes["qfile"].push_back(goodQualFile);
+               ofstream goodQual;      m->openOutputFile(goodQualFile, goodQual);
+               
+               while(!in.eof()){       
+                       
+                       if (m->control_pressed) { goodQual.close(); in.close(); m->mothurRemove(goodQualFile); return 0; }
+
+                       string saveName = "";
+                       string name = "";
+                       string scores = "";
+                       
+                       in >> name; 
+                       
+                       if (name.length() != 0) { 
+                               saveName = name.substr(1);
+                               while (!in.eof())       {       
+                                       char c = in.get(); 
+                                       if (c == 10 || c == 13){        break;  }
+                                       else { name += c; }     
+                               } 
+                               m->gobble(in);
+                       }
+                       
+                       while(in){
+                               char letter= in.get();
+                               if(letter == '>'){      in.putback(letter);     break;  }
+                               else{ scores += letter; }
+                       }
+                       
+                       m->gobble(in);
+                       
+                       it = badSeqNames.find(saveName);
+                       
+                       if(it != badSeqNames.end()){
+                               badSeqNames.erase(it);
+                       }else{                          
+                               goodQual << name << endl << scores;
+                       }
+                       
+                       m->gobble(in);
+               }
+               
+               in.close();
+               goodQual.close();
+               
+               //we were unable to remove some of the bad sequences
+               if (badSeqNames.size() != 0) {
+                       for (it = badSeqNames.begin(); it != badSeqNames.end(); it++) {  
+                               m->mothurOut("Your qual file does not include the sequence " + *it + " please correct."); 
+                               m->mothurOutEndLine();
+                       }
+               }
+               
+               if (m->control_pressed) {  m->mothurRemove(goodQualFile);  return 0; }
+               
+               return 0;
+               
+       }
+       catch(exception& e) {
+               m->errorOut(e, "ScreenSeqsCommand", "screenQual");
+               exit(1);
+       }
+       
 }
 //**********************************************************************************************************************
 
@@ -950,7 +1169,7 @@ int ScreenSeqsCommand::driver(linePair* filePos, string goodFName, string badAcc
                        }
                        
                        #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
-                               unsigned long int pos = inFASTA.tellg();
+                               unsigned long long pos = inFASTA.tellg();
                                if ((pos == -1) || (pos >= filePos->end)) { break; }
                        #else
                                if (inFASTA.eof()) { break; }
@@ -976,7 +1195,7 @@ int ScreenSeqsCommand::driver(linePair* filePos, string goodFName, string badAcc
 }
 //**********************************************************************************************************************
 #ifdef USE_MPI
-int ScreenSeqsCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& goodFile, MPI_File& badAccnosFile, vector<unsigned long int>& MPIPos, set<string>& badSeqNames){
+int ScreenSeqsCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& goodFile, MPI_File& badAccnosFile, vector<unsigned long long>& MPIPos, set<string>& badSeqNames){
        try {
                string outputString = "";
                MPI_Status statusGood; 
@@ -1096,7 +1315,7 @@ int ScreenSeqsCommand::createProcesses(string goodFileName, string badAccnos, st
                        string tempFile =  filename + toString(processIDS[i]) + ".num.temp";
                        m->openInputFile(tempFile, in);
                        if (!in.eof()) { int tempNum = 0; in >> tempNum; num += tempNum; }
-                       in.close(); remove(tempFile.c_str());
+                       in.close(); m->mothurRemove(tempFile);
                }
                
                return num;