]> git.donarmstrong.com Git - mothur.git/blobdiff - removelineagecommand.cpp
added classify.shared command and random forest files. added count file to pcr.seqs...
[mothur.git] / removelineagecommand.cpp
index 021b56cd02f36aaa88edac90a8773ed1090bc5a0..2b930b5e2450cc15b7871923fb02dbcc1c5824ee 100644 (file)
 #include "removelineagecommand.h"
 #include "sequence.hpp"
 #include "listvector.hpp"
+#include "counttable.h"
 
 //**********************************************************************************************************************
 vector<string> RemoveLineageCommand::setParameters(){  
        try {
                CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta);
-               CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname);
-               CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup);
+        CommandParameter pname("name", "InputTypes", "", "", "NameCount", "FNGLT", "none",false,false); parameters.push_back(pname);
+        CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "FNGLT", "none",false,false); parameters.push_back(pcount);
+               CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "FNGLT", "none",false,false); parameters.push_back(pgroup);
                CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist);
                CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,true); parameters.push_back(ptaxonomy);
                CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport);
@@ -38,9 +40,9 @@ vector<string> RemoveLineageCommand::setParameters(){
 string RemoveLineageCommand::getHelpString(){  
        try {
                string helpString = "";
-               helpString += "The remove.lineage command reads a taxonomy file and any of the following file types: fasta, name, group, list or alignreport file.\n";
+               helpString += "The remove.lineage command reads a taxonomy file and any of the following file types: fasta, name, group, count, list or alignreport file.\n";
                helpString += "It outputs a file containing only the sequences from the taxonomy file that are not from the taxon you requested to be removed.\n";
-               helpString += "The remove.lineage command parameters are taxon, fasta, name, group, list, taxonomy, alignreport and dups.  You must provide taxonomy unless you have a valid current taxonomy file.\n";
+               helpString += "The remove.lineage command parameters are taxon, fasta, name, group, list, taxonomy, count, alignreport and dups.  You must provide taxonomy unless you have a valid current taxonomy file.\n";
                helpString += "The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n";
                helpString += "The taxon parameter allows you to select the taxons you would like to remove, and is required.\n";
                helpString += "You may enter your taxons with confidence scores, doing so will remove only those sequences that belong to the taxonomy and whose cofidence scores fall below the scores you give.\n";
@@ -49,7 +51,7 @@ string RemoveLineageCommand::getHelpString(){
                helpString += "Example remove.lineage(taxonomy=amazon.silva.taxonomy, taxon=Bacteria;Firmicutes;Bacilli;Lactobacillales;).\n";
                helpString += "Note: If you are running mothur in script mode you must wrap the taxon in ' characters so mothur will ignore the ; in the taxon.\n";
                helpString += "Example remove.lineage(taxonomy=amazon.silva.taxonomy, taxon='Bacteria;Firmicutes;Bacilli;Lactobacillales;').\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) {
@@ -57,8 +59,32 @@ string RemoveLineageCommand::getHelpString(){
                exit(1);
        }
 }
-
-
+//**********************************************************************************************************************
+string RemoveLineageCommand::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 == "fasta")            {   outputFileName =  "pick" + m->getExtension(inputName);   }
+            else if (type == "taxonomy")    {   outputFileName =  "pick" + m->getExtension(inputName);   }
+            else if (type == "name")        {   outputFileName =  "pick" + m->getExtension(inputName);   }
+            else if (type == "group")       {   outputFileName =  "pick" + m->getExtension(inputName);   }
+            else if (type == "list")        {   outputFileName =  "pick" + m->getExtension(inputName);   }
+            else if (type == "count")       {   outputFileName =  "pick.count_table";   }
+            else if (type == "alignreport")      {   outputFileName =  "pick.align.report";   }
+            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, "RemoveLineageCommand", "getOutputFileNameTag");
+               exit(1);
+       }
+}
 //**********************************************************************************************************************
 RemoveLineageCommand::RemoveLineageCommand(){  
        try {
@@ -71,6 +97,7 @@ RemoveLineageCommand::RemoveLineageCommand(){
                outputTypes["group"] = tempOutNames;
                outputTypes["alignreport"] = tempOutNames;
                outputTypes["list"] = tempOutNames;
+        outputTypes["count"] = tempOutNames;
        }
        catch(exception& e) {
                m->errorOut(e, "RemoveLineageCommand", "RemoveLineageCommand");
@@ -84,11 +111,10 @@ RemoveLineageCommand::RemoveLineageCommand(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 {
-                       //valid paramters for this command
-                       string Array[] =  {"fasta","name", "group", "alignreport", "taxon", "dups", "list","taxonomy","outputdir","inputdir"};
-                       vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
+                       vector<string> myArray = setParameters();       
                        
                        OptionParser parser(option);
                        map<string,string> parameters = parser.getParameters();
@@ -109,6 +135,7 @@ RemoveLineageCommand::RemoveLineageCommand(string option)  {
                        outputTypes["group"] = tempOutNames;
                        outputTypes["alignreport"] = tempOutNames;
                        outputTypes["list"] = tempOutNames;
+            outputTypes["count"] = tempOutNames;
                        
                        //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 = "";         }
@@ -165,21 +192,32 @@ RemoveLineageCommand::RemoveLineageCommand(string option)  {
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["taxonomy"] = inputDir + it->second;         }
                                }
+                
+                it = parameters.find("count");
+                               //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["count"] = inputDir + it->second;            }
+                               }
                        }
 
                        
                        //check for required parameters                 
                        fastafile = validParameter.validFile(parameters, "fasta", true);
-                       if (fastafile == "not open") { abort = true; }
+                       if (fastafile == "not open") { fastafile = ""; abort = true; }
                        else if (fastafile == "not found") {  fastafile = "";  }        
+                       else { m->setFastaFile(fastafile); }
                        
                        namefile = validParameter.validFile(parameters, "name", true);
-                       if (namefile == "not open") { abort = true; }
+                       if (namefile == "not open") { namefile = ""; abort = true; }
                        else if (namefile == "not found") {  namefile = "";  }  
+                       else { m->setNameFile(namefile); }
                        
                        groupfile = validParameter.validFile(parameters, "group", true);
                        if (groupfile == "not open") { abort = true; }
                        else if (groupfile == "not found") {  groupfile = "";  }        
+                       else { m->setGroupFile(groupfile); }
                        
                        alignfile = validParameter.validFile(parameters, "alignreport", true);
                        if (alignfile == "not open") { abort = true; }
@@ -188,15 +226,29 @@ RemoveLineageCommand::RemoveLineageCommand(string option)  {
                        listfile = validParameter.validFile(parameters, "list", true);
                        if (listfile == "not open") { abort = true; }
                        else if (listfile == "not found") {  listfile = "";  }
+                       else { m->setListFile(listfile); }
                        
                        taxfile = validParameter.validFile(parameters, "taxonomy", true);
-                       if (taxfile == "not open") { abort = true; }
+                       if (taxfile == "not open") { taxfile = ""; abort = true; }
                        else if (taxfile == "not found") {              
                                taxfile = m->getTaxonomyFile(); 
                                if (taxfile != "") { m->mothurOut("Using " + taxfile + " as input file for the taxonomy parameter."); m->mothurOutEndLine(); }
                                else {  m->mothurOut("You have no current taxonomy file and the taxonomy parameter is required."); m->mothurOutEndLine(); abort = true; }
-                       }
-                       
+                       }else { m->setTaxonomyFile(taxfile); }
+                       
+            countfile = validParameter.validFile(parameters, "count", true);
+            if (countfile == "not open") { countfile = ""; abort = true; }
+            else if (countfile == "not found") { countfile = "";  }    
+            else { m->setCountTableFile(countfile); }
+            
+            if ((namefile != "") && (countfile != "")) {
+                m->mothurOut("[ERROR]: you may only use one of the following: name or count."); m->mothurOutEndLine(); abort = true;
+            }
+            
+            if ((groupfile != "") && (countfile != "")) {
+                m->mothurOut("[ERROR]: you may only use one of the following: group or count."); m->mothurOutEndLine(); abort=true;
+            }
+            
                        string usedDups = "true";
                        string temp = validParameter.validFile(parameters, "dups", false);      
                        if (temp == "not found") { 
@@ -212,12 +264,19 @@ RemoveLineageCommand::RemoveLineageCommand(string option)  {
                                if (taxons[0] == '\'') {  taxons = taxons.substr(1); }
                                if (taxons[(taxons.length()-1)] == '\'') {  taxons = taxons.substr(0, (taxons.length()-1)); }
                        }
+                       m->splitAtChar(taxons, listOfTaxons, '-');
                        
-                       
-                       if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == ""))  { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; }
+                       if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "") && (countfile == ""))  { m->mothurOut("You must provide one of the following: fasta, name, group, count, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; }
                
                        if ((usedDups != "") && (namefile == "")) {  m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine();  abort = true; }                       
-
+                       
+                       if (countfile == "") {
+                if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
+                    vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
+                    parser.getNameFile(files);
+                }
+            }
+                       
                }
 
        }
@@ -234,6 +293,12 @@ int RemoveLineageCommand::execute(){
                if (abort == true) { if (calledHelp) { return 0; }  return 2;   }
                
                if (m->control_pressed) { return 0; }
+        
+        if (countfile != "") {
+            if ((fastafile != "") || (listfile != "") || (taxfile != "")) { 
+                m->mothurOut("\n[NOTE]: The count file should contain only unique names, so mothur assumes your fasta, list and taxonomy files also contain only uniques.\n\n");
+            }
+        }
                
                //read through the correct file and output lines you want to keep
                if (taxfile != "")                      {               readTax();              }  //fills the set of names to remove
@@ -242,9 +307,10 @@ int RemoveLineageCommand::execute(){
                if (groupfile != "")            {               readGroup();    }
                if (alignfile != "")            {               readAlign();    }
                if (listfile != "")                     {               readList();             }
+        if (countfile != "")           {               readCount();    }
                
                
-               if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) {        remove(outputNames[i].c_str());  } return 0; }
+               if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) {        m->mothurRemove(outputNames[i]);  } return 0; }
                
                if (outputNames.size() != 0) {
                        m->mothurOutEndLine();
@@ -278,6 +344,11 @@ int RemoveLineageCommand::execute(){
                        if (itTypes != outputTypes.end()) {
                                if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); }
                        }
+            
+            itTypes = outputTypes.find("count");
+                       if (itTypes != outputTypes.end()) {
+                               if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
+                       }
                }
                
                return 0;               
@@ -294,8 +365,7 @@ int RemoveLineageCommand::readFasta(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(fastafile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
-               
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + getOutputFileNameTag("fasta", fastafile);         
                ofstream out;
                m->openOutputFile(outputFileName, out);
                
@@ -306,7 +376,7 @@ int RemoveLineageCommand::readFasta(){
                bool wroteSomething = false;
                
                while(!in.eof()){
-                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
                        
                        Sequence currSeq(in);
                        name = currSeq.getName();
@@ -340,8 +410,7 @@ int RemoveLineageCommand::readList(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(listfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" +  m->getExtension(listfile);
-               
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + getOutputFileNameTag("list", listfile);            
                ofstream out;
                m->openOutputFile(outputFileName, out);
                
@@ -360,7 +429,7 @@ int RemoveLineageCommand::readList(){
                        
                        //for each bin
                        for (int i = 0; i < list.getNumBins(); i++) {
-                               if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                               if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
                        
                                //parse out names that are in accnos file
                                string binnames = list.get(i);
@@ -411,8 +480,7 @@ int RemoveLineageCommand::readName(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(namefile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
-
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + getOutputFileNameTag("name", namefile);
                ofstream out;
                m->openOutputFile(outputFileName, out);
 
@@ -423,7 +491,7 @@ int RemoveLineageCommand::readName(){
                bool wroteSomething = false;
                
                while(!in.eof()){
-                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
 
                        in >> firstCol;                         
                        in >> secondCol;                        
@@ -483,14 +551,65 @@ int RemoveLineageCommand::readName(){
                exit(1);
        }
 }
-
+//**********************************************************************************************************************
+int RemoveLineageCommand::readCount(){
+       try {
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(countfile);  }
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(countfile)) + getOutputFileNameTag("count", countfile);
+               
+               ofstream out;
+               m->openOutputFile(outputFileName, out);
+               
+               ifstream in;
+               m->openInputFile(countfile, in);
+               
+               bool wroteSomething = false;
+               
+        string headers = m->getline(in); m->gobble(in);
+        out << headers << endl;
+        
+        string name, rest; int thisTotal;
+        while (!in.eof()) {
+            
+            if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
+            
+            in >> name; m->gobble(in); 
+            in >> thisTotal; m->gobble(in);
+            rest = m->getline(in); m->gobble(in);
+            if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + rest + "\n"); }
+            
+            if (names.count(name) == 0) {
+                out << name << '\t' << thisTotal << '\t' << rest << endl;
+                wroteSomething = true;
+            }
+        }
+        in.close();
+               out.close();
+        
+        //check for groups that have been eliminated
+        CountTable ct;
+        if (ct.testGroups(outputFileName)) {
+            ct.readTable(outputFileName);
+            ct.printTable(outputFileName);
+        }
+               
+               if (wroteSomething == false) {  m->mothurOut("Your group file contains only sequences from " + taxons + "."); m->mothurOutEndLine();  }
+               outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
+        
+               return 0;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "RemoveLineageCommand", "readCount");
+               exit(1);
+       }
+}
 //**********************************************************************************************************************
 int RemoveLineageCommand::readGroup(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(groupfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
-               
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + getOutputFileNameTag("group", groupfile);         
                ofstream out;
                m->openOutputFile(outputFileName, out);
 
@@ -501,7 +620,7 @@ int RemoveLineageCommand::readGroup(){
                bool wroteSomething = false;
                
                while(!in.eof()){
-                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
                        
                        in >> name;                             //read from first column
                        in >> group;                    //read from second column
@@ -532,7 +651,7 @@ int RemoveLineageCommand::readTax(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(taxfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + getOutputFileNameTag("taxonomy", taxfile);
                ofstream out;
                m->openOutputFile(outputFileName, out);
                
@@ -542,120 +661,134 @@ int RemoveLineageCommand::readTax(){
                
                bool wroteSomething = false;
                
-               bool taxonsHasConfidence = false;
-               vector< map<string, float> > searchTaxons;
-               string noConfidenceTaxons = taxons;
-               int hasConPos = taxons.find_first_of('(');
-               if (hasConPos != string::npos) {  
-                       taxonsHasConfidence = true; 
-                       searchTaxons = getTaxons(taxons); 
-                       noConfidenceTaxons = removeConfidences(taxons);
+               vector<bool> taxonsHasConfidence; taxonsHasConfidence.resize(listOfTaxons.size(), false);
+               vector< vector< map<string, float> > > searchTaxons; searchTaxons.resize(listOfTaxons.size());
+               vector<string> noConfidenceTaxons; noConfidenceTaxons.resize(listOfTaxons.size(), "");
+               
+               for (int i = 0; i < listOfTaxons.size(); i++) {
+                       noConfidenceTaxons[i] = listOfTaxons[i];
+                       int hasConPos = listOfTaxons[i].find_first_of('(');
+                       if (hasConPos != string::npos) {  
+                               taxonsHasConfidence[i] = true; 
+                               searchTaxons[i] = getTaxons(listOfTaxons[i]); 
+                               noConfidenceTaxons[i] = listOfTaxons[i];
+                               m->removeConfidences(noConfidenceTaxons[i]);
+                       }
                }
                
                
                while(!in.eof()){
 
-                       if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName);  return 0; }
 
                        in >> name;                             //read from first column
                        in >> tax;                      //read from second column
                        
-                       string newtax = tax;
+                       bool remove = false;
                        
-                       //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them
-                       if (!taxonsHasConfidence) {
-                               
-                               int hasConfidences = tax.find_first_of('(');
-                               if (hasConfidences != string::npos) { 
-                                       newtax = removeConfidences(tax);
-                               }
-                               
-                               int pos = newtax.find(taxons);
-                               
-                               if (pos == string::npos) { 
-                                       wroteSomething = true;
-                                       out << name << '\t' << tax << endl;
-                               }else{ //this sequence contains the taxon the user wants to remove
-                                       names.insert(name);
-                               }
+            string noQuotesTax = m->removeQuotes(tax);
+            
+                       for (int j = 0; j < listOfTaxons.size(); j++) {
+                               string newtax = noQuotesTax;
                                
-                       }else{//if taxons has them and you don't them remove taxons
-                               int hasConfidences = tax.find_first_of('(');
-                               if (hasConfidences == string::npos) { 
-                               
-                                       int pos = newtax.find(noConfidenceTaxons);
+                               //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them
+                               if (!taxonsHasConfidence[j]) {
+                                       
+                                       int hasConfidences = noQuotesTax.find_first_of('(');
+                                       if (hasConfidences != string::npos) { 
+                                               newtax = noQuotesTax;
+                                               m->removeConfidences(newtax);
+                                       }
+                                       
+                                       int pos = newtax.find(noConfidenceTaxons[j]);
                                        
                                        if (pos == string::npos) { 
-                                               wroteSomething = true;
-                                               out << name << '\t' << tax << endl;
+                                               //wroteSomething = true;
+                                               //out << name << '\t' << tax << endl;
                                        }else{ //this sequence contains the taxon the user wants to remove
                                                names.insert(name);
+                                               remove=true; break;
                                        }
-                               }else { //both have confidences so we want to make sure the users confidences are greater then or equal to the taxons
-                                       //first remove confidences from both and see if the taxonomy exists
-                               
-                                       string noNewTax = tax;
-                                       int hasConfidences = tax.find_first_of('(');
-                                       if (hasConfidences != string::npos) { 
-                                               noNewTax = removeConfidences(tax);
-                                       }
-                                       
-                                       int pos = noNewTax.find(noConfidenceTaxons);
                                        
-                                       if (pos != string::npos) { //if yes, then are the confidences okay
+                               }else{//if taxons has them and you don't them remove taxons
+                                       int hasConfidences = noQuotesTax.find_first_of('(');
+                                       if (hasConfidences == string::npos) { 
+                                               
+                                               int pos = newtax.find(noConfidenceTaxons[j]);
                                                
-                                               bool remove = false;
-                                               vector< map<string, float> > usersTaxon = getTaxons(newtax);
+                                               if (pos == string::npos) { 
+                                                       //wroteSomething = true;
+                                                       //out << name << '\t' << tax << endl;
+                                               }else{ //this sequence contains the taxon the user wants to remove
+                                                       names.insert(name);
+                                                       remove=true; break;
+                                               }
+                                       }else { //both have confidences so we want to make sure the users confidences are greater then or equal to the taxons
+                                               //first remove confidences from both and see if the taxonomy exists
+                                               
+                                               string noNewTax = noQuotesTax;
+                                               int hasConfidences = noQuotesTax.find_first_of('(');
+                                               if (hasConfidences != string::npos) { 
+                                                       noNewTax = noQuotesTax;
+                                                       m->removeConfidences(noNewTax);
+                                               }
                                                
-                                               //the usersTaxon is most likely longer than the searchTaxons, and searchTaxon[0] may relate to userTaxon[4]
-                                               //we want to "line them up", so we will find the the index where the searchstring starts
-                                               int index = 0;
-                                               for (int i = 0; i < usersTaxon.size(); i++) {
+                                               int pos = noNewTax.find(noConfidenceTaxons[j]);
+                                               
+                                               if (pos != string::npos) { //if yes, then are the confidences okay
                                                        
-                                                       if (usersTaxon[i].begin()->first == searchTaxons[0].begin()->first) { 
-                                                               index = i;  
-                                                               int spot = 0;
-                                                               bool goodspot = true;
-                                                               //is this really the start, or are we dealing with a taxon of the same name?
-                                                               while ((spot < searchTaxons.size()) && ((i+spot) < usersTaxon.size())) {
-                                                                       if (usersTaxon[i+spot].begin()->first != searchTaxons[spot].begin()->first) { goodspot = false; break; }
-                                                                       else { spot++; }
-                                                               }
+                                                       vector< map<string, float> > usersTaxon = getTaxons(newtax);
+                                                       
+                                                       //the usersTaxon is most likely longer than the searchTaxons, and searchTaxon[0] may relate to userTaxon[4]
+                                                       //we want to "line them up", so we will find the the index where the searchstring starts
+                                                       int index = 0;
+                                                       for (int i = 0; i < usersTaxon.size(); i++) {
                                                                
-                                                               if (goodspot) { break; }
+                                                               if (usersTaxon[i].begin()->first == searchTaxons[j][0].begin()->first) { 
+                                                                       index = i;  
+                                                                       int spot = 0;
+                                                                       bool goodspot = true;
+                                                                       //is this really the start, or are we dealing with a taxon of the same name?
+                                                                       while ((spot < searchTaxons[j].size()) && ((i+spot) < usersTaxon.size())) {
+                                                                               if (usersTaxon[i+spot].begin()->first != searchTaxons[j][spot].begin()->first) { goodspot = false; break; }
+                                                                               else { spot++; }
+                                                                       }
+                                                                       
+                                                                       if (goodspot) { break; }
+                                                               }
                                                        }
-                                               }
-                                               
-                                               for (int i = 0; i < searchTaxons.size(); i++) {
                                                        
-                                                       if ((i+index) < usersTaxon.size()) { //just in case, should never be false
-                                                               if (usersTaxon[i+index].begin()->second < searchTaxons[i].begin()->second) { //is the users cutoff less than the search taxons
+                                                       for (int i = 0; i < searchTaxons[j].size(); i++) {
+                                                               
+                                                               if ((i+index) < usersTaxon.size()) { //just in case, should never be false
+                                                                       if (usersTaxon[i+index].begin()->second < searchTaxons[j][i].begin()->second) { //is the users cutoff less than the search taxons
+                                                                               remove = true;
+                                                                               break;
+                                                                       }
+                                                               }else {
                                                                        remove = true;
                                                                        break;
                                                                }
+                                                       }
+                                                       
+                                                       //passed the test so remove you
+                                                       if (remove) {
+                                                               names.insert(name);
+                                                               remove=true; break;
                                                        }else {
-                                                               remove = true;
-                                                               break;
+                                                               //wroteSomething = true;
+                                                               //out << name << '\t' << tax << endl;
                                                        }
-                                               }
-                                               
-                                               //passed the test so remove you
-                                               if (remove) {
-                                                       names.insert(name);
                                                }else {
-                                                       wroteSomething = true;
-                                                       out << name << '\t' << tax << endl;
+                                                       //wroteSomething = true;
+                                                       //out << name << '\t' << tax << endl;
                                                }
-                                       }else {
-                                               wroteSomething = true;
-                                               out << name << '\t' << tax << endl;
                                        }
                                }
+                               
                        }
                        
-                       
-                       
-                       
+                       if (!remove) {  wroteSomething = true; out << name << '\t' << tax << endl; }
                        m->gobble(in);
                }
                in.close();
@@ -714,36 +847,13 @@ vector< map<string, float> > RemoveLineageCommand::getTaxons(string tax) {
                exit(1);
        }
 }
-/**************************************************************************************************/
-string RemoveLineageCommand::removeConfidences(string tax) {
-       try {
-               
-               string taxon = "";
-               int taxLength = tax.length();
-               for(int i=0;i<taxLength;i++){
-                       if(tax[i] == ';'){
-                               taxon = taxon.substr(0, taxon.find_first_of('(')); //rip off confidence
-                               taxon += ";";
-                       }
-                       else{
-                               taxon += tax[i];
-                       }
-               }
-                               
-               return taxon;
-       }
-       catch(exception& e) {
-               m->errorOut(e, "RemoveLineageCommand", "removeConfidences");
-               exit(1);
-       }
-}
 //**********************************************************************************************************************
 //alignreport file has a column header line then all other lines contain 16 columns.  we just want the first column since that contains the name
 int RemoveLineageCommand::readAlign(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(alignfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + "pick.align.report";
+               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(alignfile)) + getOutputFileNameTag("alignreport");
                
                ofstream out;
                m->openOutputFile(outputFileName, out);
@@ -762,7 +872,7 @@ int RemoveLineageCommand::readAlign(){
                out << endl;
                
                while(!in.eof()){
-                       if (m->control_pressed) { in.close();  out.close();  remove(outputFileName.c_str());  return 0; }
+                       if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
                        
                        in >> name;                             //read from first column