]> git.donarmstrong.com Git - mothur.git/blobdiff - getgroupscommand.cpp
working on pam
[mothur.git] / getgroupscommand.cpp
index 432894b06fe9d5ffa6982fdaaa49474a44c403e0..bb15a3f5a21e3c7785283cfc5d6eade2c1bda6ed 100644 (file)
 //**********************************************************************************************************************
 vector<string> GetGroupsCommand::setParameters(){      
        try {
-               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(pfasta);
-               CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none",false,false); parameters.push_back(pshared);
-               CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname);
-               CommandParameter pgroup("group", "InputTypes", "", "", "none", "sharedGroup", "FNGLT",false,false); parameters.push_back(pgroup);
-               CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(plist);
-               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT",false,false); parameters.push_back(ptaxonomy);
-               CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(paccnos);
-               CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups);
-               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
-               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+               CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "FNGLT","fasta",false,false, true); parameters.push_back(pfasta);
+               CommandParameter pshared("shared", "InputTypes", "", "", "none", "sharedGroup", "none","shared",false,false, true); parameters.push_back(pshared);
+        CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","name",false,false, true); parameters.push_back(pname);
+        CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","count",false,false, true); parameters.push_back(pcount);
+               CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "sharedGroup", "FNGLT","group",false,false, true); parameters.push_back(pgroup);           
+        CommandParameter pdesign("design", "InputTypes", "", "", "none", "sharedGroup", "FNGLT","design",false,false, true); parameters.push_back(pdesign);
+               CommandParameter plist("list", "InputTypes", "", "", "none", "none", "FNGLT","list",false,false, true); parameters.push_back(plist);
+               CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "FNGLT","taxonomy",false,false, true); parameters.push_back(ptaxonomy);
+               CommandParameter paccnos("accnos", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(paccnos);
+               CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups);
+               CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
+               CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
                
                vector<string> myArray;
                for (int i = 0; i < parameters.size(); i++) {   myArray.push_back(parameters[i].name);          }
@@ -40,9 +42,9 @@ vector<string> GetGroupsCommand::setParameters(){
 string GetGroupsCommand::getHelpString(){      
        try {
                string helpString = "";
-               helpString += "The get.groups command selects sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy or shared file.\n";
+               helpString += "The get.groups command selects sequences from a specfic group or set of groups from the following file types: fasta, name, group, list, taxonomy, design or shared file.\n";
                helpString += "It outputs a file containing the sequences in the those specified groups, or a sharedfile containing only those groups.\n";
-               helpString += "The get.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared and groups. The group parameter is required, unless you have a current group file, or are using a shared file.\n";
+               helpString += "The get.groups command parameters are accnos, fasta, name, group, list, taxonomy, shared, design and groups. The group or count parameter is required, unless you have a current group or count file, or are using a shared file.\n";
                helpString += "You must also provide an accnos containing the list of groups to get or set the groups parameter to the groups you wish to select.\n";
                helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like.  You can separate group names with dashes.\n";
                helpString += "The get.groups command should be in the following format: get.groups(accnos=yourAccnos, fasta=yourFasta, group=yourGroupFile).\n";
@@ -57,6 +59,28 @@ string GetGroupsCommand::getHelpString(){
        }
 }
 //**********************************************************************************************************************
+string GetGroupsCommand::getOutputPattern(string type) {
+    try {
+        string pattern = "";
+        
+        if (type == "fasta")            {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "taxonomy")    {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "name")        {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "group")       {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "count")       {   pattern = "[filename],pick,[extension]";    }
+        else if (type == "list")        {   pattern = "[filename],[tag],pick,[extension]";    }
+        else if (type == "shared")      {   pattern = "[filename],[tag],pick,[extension]";    }
+        else if (type == "design")      {   pattern = "[filename],pick,[extension]";    }
+        else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true;  }
+        
+        return pattern;
+    }
+    catch(exception& e) {
+        m->errorOut(e, "GetGroupsCommand", "getOutputPattern");
+        exit(1);
+    }
+}
+//**********************************************************************************************************************
 GetGroupsCommand::GetGroupsCommand(){  
        try {
                abort = true; calledHelp = true;
@@ -68,6 +92,8 @@ GetGroupsCommand::GetGroupsCommand(){
                outputTypes["group"] = tempOutNames;
                outputTypes["list"] = tempOutNames;
                outputTypes["shared"] = tempOutNames;
+        outputTypes["design"] = tempOutNames;
+        outputTypes["count"] = tempOutNames;
        }
        catch(exception& e) {
                m->errorOut(e, "GetGroupsCommand", "GetGroupsCommand");
@@ -105,6 +131,8 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        outputTypes["group"] = tempOutNames;
                        outputTypes["list"] = tempOutNames;
                        outputTypes["shared"] = tempOutNames;
+            outputTypes["design"] = tempOutNames;
+            outputTypes["count"] = tempOutNames;
                        
                        
                        //if the user changes the output directory command factory will send this info to us in the output parameter 
@@ -170,6 +198,22 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                                        //if the user has not given a path then, add inputdir. else leave path alone.
                                        if (path == "") {       parameters["shared"] = inputDir + it->second;           }
                                }
+                
+                it = parameters.find("design");
+                               //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["design"] = 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;            }
+                               }
                        }
                        
                        
@@ -189,11 +233,6 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        else if (namefile == "not found") {  namefile = "";  }  
                        else { m->setNameFile(namefile); }
                        
-                       groupfile = validParameter.validFile(parameters, "group", true);
-                       if (groupfile == "not open") { groupfile = ""; abort = true; }
-                       else if (groupfile == "not found") {  groupfile = "";                   }
-                       else { m->setGroupFile(groupfile); }    
-                       
                        listfile = validParameter.validFile(parameters, "list", true);
                        if (listfile == "not open") { abort = true; }
                        else if (listfile == "not found") {  listfile = "";  }
@@ -219,9 +258,28 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        groupfile = validParameter.validFile(parameters, "group", true);
                        if (groupfile == "not open") { groupfile = ""; abort = true; }
                        else if (groupfile == "not found") {    groupfile = ""; }
-                       else { m->setGroupFile(groupfile); }    
+                       else { m->setGroupFile(groupfile); }
+            
+            designfile = validParameter.validFile(parameters, "design", true);
+                       if (designfile == "not open") { designfile = ""; abort = true; }
+                       else if (designfile == "not found") {   designfile = "";        }
+                       else { m->setDesignFile(designfile); }
+            
+            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;
+            }
+
                        
-                       if ((sharedfile == "") && (groupfile == "")) { 
+                       if ((sharedfile == "") && (groupfile == "") && (designfile == "") && (countfile == "")) { 
                                //is there are current file available for any of these?
                                if ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")) {
                                        //give priority to group, then shared
@@ -231,7 +289,11 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                                                sharedfile = m->getSharedFile(); 
                                                if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); }
                                                else { 
-                                                       m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+                                                       countfile = m->getCountTableFile(); 
+                            if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); }
+                            else { 
+                                m->mothurOut("You have no current groupfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+                            }
                                                }
                                        }
                                }else {
@@ -242,7 +304,16 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                                                groupfile = m->getGroupFile(); 
                                                if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); }
                                                else { 
-                                                       m->mothurOut("You have no current groupfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+                                                       designfile = m->getDesignFile(); 
+                            if (designfile != "") { m->mothurOut("Using " + designfile + " as input file for the design parameter."); m->mothurOutEndLine(); }
+                            else { 
+                                countfile = m->getCountTableFile(); 
+                                if (countfile != "") { m->mothurOut("Using " + countfile + " as input file for the count parameter."); m->mothurOutEndLine(); }
+                                else { 
+                                    m->mothurOut("You have no current groupfile, designfile, countfile or sharedfile and one is required."); m->mothurOutEndLine(); abort = true;
+                                }
+
+                            }
                                                }
                                        }
                                }
@@ -250,13 +321,15 @@ GetGroupsCommand::GetGroupsCommand(string option)  {
                        
                        if ((accnosfile == "") && (Groups.size() == 0)) { m->mothurOut("You must provide an accnos file or specify groups using the groups parameter."); m->mothurOutEndLine(); abort = true; }
                        
-                       if ((fastafile == "") && (namefile == "") && (groupfile == "")  && (sharedfile == "") && (listfile == "") && (taxfile == ""))  { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared or list."); m->mothurOutEndLine(); abort = true; }
-                       if ((groupfile == "") && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")))  { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group file."); m->mothurOutEndLine(); abort = true; }
-
-                       if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
-                               vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
-                               parser.getNameFile(files);
-                       }
+                       if ((fastafile == "") && (namefile == "") && (countfile == "") && (groupfile == "")  && (designfile == "") && (sharedfile == "") && (listfile == "") && (taxfile == ""))  { m->mothurOut("You must provide at least one of the following: fasta, name, taxonomy, group, shared, design, count or list."); m->mothurOutEndLine(); abort = true; }
+                       if (((groupfile == "") && (countfile == "")) && ((namefile != "") || (fastafile != "") || (listfile != "") || (taxfile != "")))  { m->mothurOut("If using a fasta, name, taxonomy, group or list, then you must provide a group or count file."); m->mothurOutEndLine(); abort = true; }
+            
+            if (countfile == "") {
+                if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){
+                    vector<string> files; files.push_back(fastafile); files.push_back(taxfile);
+                    parser.getNameFile(files);
+                }
+            }
                }
                
        }
@@ -273,7 +346,7 @@ int GetGroupsCommand::execute(){
                if (abort == true) { if (calledHelp) { return 0; }  return 2;   }
                
                //get groups you want to remove
-               if (accnosfile != "") { readAccnos(); }
+               if (accnosfile != "") { m->readAccnos(accnosfile, Groups); m->setGroups(Groups); }
                
                if (groupfile != "") {
                        groupMap = new GroupMap(groupfile);
@@ -284,6 +357,7 @@ int GetGroupsCommand::execute(){
                        SharedUtil* util = new SharedUtil();
                        vector<string> gNamesOfGroups = groupMap->getNamesOfGroups();
                        util->setGroups(Groups, gNamesOfGroups);
+            m->setGroups(Groups);
                        groupMap->setNamesOfGroups(gNamesOfGroups);
                        delete util;
                        
@@ -291,7 +365,23 @@ int GetGroupsCommand::execute(){
                        fillNames();
                        
                        delete groupMap;
-               }
+               }else 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");
+            }
+            CountTable ct;
+            ct.readTable(countfile, true, false);
+            if (!ct.hasGroupInfo()) { m->mothurOut("[ERROR]: your count file does not contain group info, aborting.\n"); return 0; }
+                
+            vector<string> gNamesOfGroups = ct.getNamesOfGroups();
+            SharedUtil util;
+            util.setGroups(Groups, gNamesOfGroups);
+            m->setGroups(Groups);
+            for (int i = 0; i < Groups.size(); i++) {
+                vector<string> thisGroupsSeqs = ct.getNamesOfSeqs(Groups[i]);
+                for (int j = 0; j < thisGroupsSeqs.size(); j++) { names.insert(thisGroupsSeqs[j]); }
+            }
+        }
                
                if (m->control_pressed) { return 0; }
                
@@ -299,9 +389,11 @@ int GetGroupsCommand::execute(){
                if (namefile != "")                     {               readName();             }
                if (fastafile != "")            {               readFasta();    }
                if (groupfile != "")            {               readGroup();    }
+        if (countfile != "")           {               readCount();    }
                if (listfile != "")                     {               readList();             }
                if (taxfile != "")                      {               readTax();              }
                if (sharedfile != "")           {               readShared();   }
+        if (designfile != "")          {               readDesign();   }
                
                if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) {        m->mothurRemove(outputNames[i]); } return 0; }
                
@@ -343,6 +435,16 @@ int GetGroupsCommand::execute(){
                        if (itTypes != outputTypes.end()) {
                                if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setSharedFile(current); }
                        }
+            
+            itTypes = outputTypes.find("design");
+                       if (itTypes != outputTypes.end()) {
+                               if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setDesignFile(current); }
+                       }
+            
+            itTypes = outputTypes.find("count");
+                       if (itTypes != outputTypes.end()) {
+                               if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
+                       }
                }
                
                return 0;               
@@ -359,7 +461,10 @@ int GetGroupsCommand::readFasta(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(fastafile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(fastafile)) + "pick" + m->getExtension(fastafile);
+        map<string, string> variables; 
+        variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(fastafile));
+        variables["[extension]"] = m->getExtension(fastafile);
+               string outputFileName = getOutputFileName("fasta", variables);
                
                ofstream out;
                m->openOutputFile(outputFileName, out);
@@ -422,12 +527,17 @@ int GetGroupsCommand::readShared(){
                
                InputData input(sharedfile, "sharedfile");
                vector<SharedRAbundVector*> lookup = input.getSharedRAbundVectors();
+        map<string, string> variables; 
+        variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile));
+        variables["[extension]"] = m->getExtension(sharedfile);
                
                bool wroteSomething = false;
                
                while(lookup[0] != NULL) {
                        
-                       string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + ".pick" + m->getExtension(sharedfile);
+            variables["[tag]"] = lookup[0]->getLabel();
+            string outputFileName = getOutputFileName("shared", variables);
+                       
                        ofstream out;
                        m->openOutputFile(outputFileName, out);
                        outputTypes["shared"].push_back(outputFileName);  outputNames.push_back(outputFileName);
@@ -472,10 +582,9 @@ int GetGroupsCommand::readList(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(listfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(listfile)) + "pick" +  m->getExtension(listfile);
-               
-               ofstream out;
-               m->openOutputFile(outputFileName, out);
+        map<string, string> variables; 
+        variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(listfile));
+        variables["[extension]"] = m->getExtension(listfile);
                
                ifstream in;
                m->openInputFile(listfile, in);
@@ -486,9 +595,19 @@ int GetGroupsCommand::readList(){
                while(!in.eof()){
                        
                        selectedCount = 0;
-                       
+
                        //read in list vector
                        ListVector list(in);
+            
+            variables["[tag]"] = list.getLabel();
+            string outputFileName = getOutputFileName("list", variables);
+                       
+                       ofstream out;
+                       m->openOutputFile(outputFileName, out);
+                       outputTypes["list"].push_back(outputFileName);  outputNames.push_back(outputFileName);
+            
+            vector<string> binLabels = list.getLabels();
+            vector<string> newBinLabels;
                        
                        //make a new list vector
                        ListVector newList;
@@ -500,13 +619,14 @@ int GetGroupsCommand::readList(){
                                
                                //parse out names that are in accnos file
                                string binnames = list.get(i);
+                vector<string> thisBinNames;
+                m->splitAtComma(binnames, thisBinNames);
                                
                                string newNames = "";
-                               while (binnames.find_first_of(',') != -1) { 
-                                       string name = binnames.substr(0,binnames.find_first_of(','));
-                                       binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
-                                       
-                                       //if that name is in the .accnos file, add it
+                for (int j = 0; j < thisBinNames.size(); j++) {
+                    string name = thisBinNames[j];
+                    
+                    //if that name is in the .accnos file, add it
                                        if (names.count(name) != 0) {  newNames += name + ",";  selectedCount++;  }
                                        else{
                                                //if you are not in the accnos file check if you are a name that needs to be changed
@@ -516,39 +636,30 @@ int GetGroupsCommand::readList(){
                                                        selectedCount++;
                                                }
                                        }
-                               }
-                               
-                               //get last name
-                               if (names.count(binnames) != 0) {  newNames += binnames + ",";  selectedCount++;  }
-                               else{
-                                       //if you are not in the accnos file check if you are a name that needs to be changed
-                                       map<string, string>::iterator it = uniqueToRedundant.find(binnames);
-                                       if (it != uniqueToRedundant.end()) {
-                                               newNames += it->second + ",";
-                                               selectedCount++;
-                                       }
-                               }
-                               
+                }
+                                                               
                                //if there are names in this bin add to new list
                                if (newNames != "") {  
                                        newNames = newNames.substr(0, newNames.length()-1); //rip off extra comma
-                                       newList.push_back(newNames);    
+                                       newList.push_back(newNames);
+                    newBinLabels.push_back(binLabels[i]);
                                }
                        }
                        
                        //print new listvector
                        if (newList.getNumBins() != 0) {
                                wroteSomething = true;
+                newList.setLabels(newBinLabels);
+                newList.printHeaders(out);
                                newList.print(out);
                        }
                        
                        m->gobble(in);
+            out.close();
                }
-               in.close();     
-               out.close();
+               in.close();
                
                if (wroteSomething == false) {  m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine();  }
-               outputTypes["list"].push_back(outputFileName); outputNames.push_back(outputFileName);
                
                m->mothurOut("Selected " + toString(selectedCount) + " sequences from your list file."); m->mothurOutEndLine();
                
@@ -565,7 +676,10 @@ int GetGroupsCommand::readName(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(namefile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(namefile)) + "pick" + m->getExtension(namefile);
+        map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(namefile));
+        variables["[extension]"] = m->getExtension(namefile);
+               string outputFileName = getOutputFileName("name", variables);
                
                ofstream out;
                m->openOutputFile(outputFileName, out);
@@ -646,7 +760,10 @@ int GetGroupsCommand::readGroup(){
        try {
                string thisOutputDir = outputDir;
                if (outputDir == "") {  thisOutputDir += m->hasPath(groupfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(groupfile)) + "pick" + m->getExtension(groupfile);
+        map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(groupfile));
+        variables["[extension]"] = m->getExtension(groupfile);
+               string outputFileName = getOutputFileName("group", variables);
                
                ofstream out;
                m->openOutputFile(outputFileName, out);
@@ -689,37 +806,115 @@ int GetGroupsCommand::readGroup(){
        }
 }
 //**********************************************************************************************************************
-int GetGroupsCommand::readTax(){
+int GetGroupsCommand::readCount(){
        try {
                string thisOutputDir = outputDir;
-               if (outputDir == "") {  thisOutputDir += m->hasPath(taxfile);  }
-               string outputFileName = thisOutputDir + m->getRootName(m->getSimpleName(taxfile)) + "pick" + m->getExtension(taxfile);
+               if (outputDir == "") {  thisOutputDir += m->hasPath(countfile);  }
+        map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(countfile));
+        variables["[extension]"] = m->getExtension(countfile);
+               string outputFileName = getOutputFileName("count", variables);
+               
                ofstream out;
                m->openOutputFile(outputFileName, out);
                
                ifstream in;
-               m->openInputFile(taxfile, in);
-               string name, tax;
+               m->openInputFile(countfile, in);
+               
+               bool wroteSomething = false;
+               int selectedCount = 0;
+               
+        string headers = m->getline(in); m->gobble(in);
+        vector<string> columnHeaders = m->splitWhiteSpace(headers);
+        
+        vector<string> groups;
+        map<int, string> originalGroupIndexes;
+        map<string, int> GroupIndexes;
+        set<int> indexOfGroupsChosen;
+        for (int i = 2; i < columnHeaders.size(); i++) {  groups.push_back(columnHeaders[i]);  originalGroupIndexes[i-2] = columnHeaders[i]; }
+        //sort groups to keep consistent with how we store the groups in groupmap
+        sort(groups.begin(), groups.end());
+        for (int i = 0; i < groups.size(); i++) {  GroupIndexes[groups[i]] = i; }
+        sort(Groups.begin(), Groups.end());
+        out << "Representative_Sequence\ttotal\t";
+        for (int i = 0; i < Groups.size(); i++) { out << Groups[i] << '\t'; indexOfGroupsChosen.insert(GroupIndexes[Groups[i]]); }
+        out << endl;
+        
+        string name; int oldTotal;
+        while (!in.eof()) {
+            
+            if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
+            
+            in >> name; m->gobble(in); in >> oldTotal; m->gobble(in);
+            if (m->debug) { m->mothurOut("[DEBUG]: " + name + '\t' + toString(oldTotal) + "\n"); }
+            
+            if (names.count(name) != 0) {
+                //if group info, then read it
+                vector<int> selectedCounts; int thisTotal = 0; int temp;
+                for (int i = 0; i < groups.size(); i++) {  
+                    int thisIndex = GroupIndexes[originalGroupIndexes[i]]; 
+                    in >> temp;  m->gobble(in);
+                    if (indexOfGroupsChosen.count(thisIndex) != 0) { //we want this group
+                        selectedCounts.push_back(temp); thisTotal += temp;
+                    }
+                }
+
+                out << name << '\t' << thisTotal << '\t';
+                for (int i = 0; i < selectedCounts.size(); i++) {  out << selectedCounts[i] << '\t'; }
+                out << endl;
+                
+                wroteSomething = true;
+                selectedCount+= thisTotal;
+            }else {  m->getline(in); }
+            
+            m->gobble(in);
+        }
+        in.close();
+               out.close();
+               
+               if (wroteSomething == false) {  m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine();  }
+               outputTypes["count"].push_back(outputFileName); outputNames.push_back(outputFileName);
+               
+               m->mothurOut("Selected " + toString(selectedCount) + " sequences from your count file."); m->mothurOutEndLine();
+        
+               return 0;
+       }
+       catch(exception& e) {
+               m->errorOut(e, "GetGroupsCommand", "readCount");
+               exit(1);
+       }
+}
+//**********************************************************************************************************************
+int GetGroupsCommand::readDesign(){
+       try {
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(designfile);  }
+        map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(designfile));
+        variables["[extension]"] = m->getExtension(designfile);
+               string outputFileName = getOutputFileName("design", variables);
+               
+               ofstream out;
+               m->openOutputFile(outputFileName, out);
+               
+               ifstream in;
+               m->openInputFile(designfile, in);
+               string name, group;
                
                bool wroteSomething = false;
+               int selectedCount = 0;
                
                while(!in.eof()){
                        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
+                       in >> group;                    //read from second column
                        
                        //if this name is in the accnos file
-                       if (names.count(name) != 0) {
+                       if (m->inUsersGroups(name, Groups)) {
                                wroteSomething = true;
-                               out << name << '\t' << tax << endl;
-                       }else{
-                               //if you are not in the accnos file check if you are a name that needs to be changed
-                               map<string, string>::iterator it = uniqueToRedundant.find(name);
-                               if (it != uniqueToRedundant.end()) {
-                                       wroteSomething = true;
-                                       out << it->second << '\t' << tax << endl;
-                               }
+                               out << name << '\t' << group << endl;
+                selectedCount++;
                        }
                        
                        m->gobble(in);
@@ -727,39 +922,71 @@ int GetGroupsCommand::readTax(){
                in.close();
                out.close();
                
-               if (wroteSomething == false) {  m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine();  }
-               outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName);
+               if (wroteSomething == false) {  m->mothurOut("Your file does NOT contain groups from the groups you wish to get."); m->mothurOutEndLine();  }
+               outputTypes["design"].push_back(outputFileName); outputNames.push_back(outputFileName);
+               
+               m->mothurOut("Selected " + toString(selectedCount) + " groups from your design file."); m->mothurOutEndLine();
+        
                
                return 0;
        }
        catch(exception& e) {
-               m->errorOut(e, "GetGroupsCommand", "readTax");
+               m->errorOut(e, "GetGroupsCommand", "readDesign");
                exit(1);
        }
 }
+
+
 //**********************************************************************************************************************
-void GetGroupsCommand::readAccnos(){
+int GetGroupsCommand::readTax(){
        try {
-               Groups.clear();
+               string thisOutputDir = outputDir;
+               if (outputDir == "") {  thisOutputDir += m->hasPath(taxfile);  }
+        map<string, string> variables; 
+               variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(taxfile));
+        variables["[extension]"] = m->getExtension(taxfile);
+               string outputFileName = getOutputFileName("taxonomy", variables);
+               
+               ofstream out;
+               m->openOutputFile(outputFileName, out);
                
                ifstream in;
-               m->openInputFile(accnosfile, in);
-               string name;
+               m->openInputFile(taxfile, in);
+               string name, tax;
+               
+               bool wroteSomething = false;
                
                while(!in.eof()){
-                       in >> name;
+                       if (m->control_pressed) { in.close();  out.close();  m->mothurRemove(outputFileName);  return 0; }
                        
-                       Groups.push_back(name);
+                       in >> name;                             //read from first column
+                       in >> tax;                      //read from second column
+                       
+                       //if this name is in the accnos file
+                       if (names.count(name) != 0) {
+                               wroteSomething = true;
+                               out << name << '\t' << tax << endl;
+                       }else{
+                               //if you are not in the accnos file check if you are a name that needs to be changed
+                               map<string, string>::iterator it = uniqueToRedundant.find(name);
+                               if (it != uniqueToRedundant.end()) {
+                                       wroteSomething = true;
+                                       out << it->second << '\t' << tax << endl;
+                               }
+                       }
                        
                        m->gobble(in);
                }
-               in.close();             
+               in.close();
+               out.close();
                
-               m->setGroups(Groups);
+               if (wroteSomething == false) {  m->mothurOut("Your file does NOT contain sequences from the groups you wish to get."); m->mothurOutEndLine();  }
+               outputTypes["taxonomy"].push_back(outputFileName); outputNames.push_back(outputFileName);
                
+               return 0;
        }
        catch(exception& e) {
-               m->errorOut(e, "GetGroupsCommand", "readAccnos");
+               m->errorOut(e, "GetGroupsCommand", "readTax");
                exit(1);
        }
 }