+
+//**********************************************************************************************************************
+vector<string> ClassifySeqsCommand::setParameters(){
+ try {
+ CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(ptaxonomy);
+ CommandParameter ptemplate("reference", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(ptemplate);
+ 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 psearch("search", "Multiple", "kmer-blast-suffix-distance", "kmer", "", "", "",false,false); parameters.push_back(psearch);
+ CommandParameter pksize("ksize", "Number", "", "8", "", "", "",false,false); parameters.push_back(pksize);
+ CommandParameter pmethod("method", "Multiple", "bayesian-knn", "bayesian", "", "", "",false,false); parameters.push_back(pmethod);
+ CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
+ CommandParameter pmatch("match", "Number", "", "1.0", "", "", "",false,false); parameters.push_back(pmatch);
+ CommandParameter pmismatch("mismatch", "Number", "", "-1.0", "", "", "",false,false); parameters.push_back(pmismatch);
+ CommandParameter pgapopen("gapopen", "Number", "", "-2.0", "", "", "",false,false); parameters.push_back(pgapopen);
+ CommandParameter pgapextend("gapextend", "Number", "", "-1.0", "", "", "",false,false); parameters.push_back(pgapextend);
+ //CommandParameter pflip("flip", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pflip);
+ CommandParameter pcutoff("cutoff", "Number", "", "0", "", "", "",false,true); parameters.push_back(pcutoff);
+ CommandParameter pprobs("probs", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pprobs);
+ CommandParameter piters("iters", "Number", "", "100", "", "", "",false,true); parameters.push_back(piters);
+ CommandParameter psave("save", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(psave);
+ CommandParameter pnumwanted("numwanted", "Number", "", "10", "", "", "",false,true); parameters.push_back(pnumwanted);
+ 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); }
+ return myArray;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClassifySeqsCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string ClassifySeqsCommand::getHelpString(){
+ try {
+ string helpString = "";
+ helpString += "The classify.seqs command reads a fasta file containing sequences and creates a .taxonomy file and a .tax.summary file.\n";
+ helpString += "The classify.seqs command parameters are reference, fasta, name, search, ksize, method, taxonomy, processors, match, mismatch, gapopen, gapextend, numwanted and probs.\n";
+ helpString += "The reference, fasta and taxonomy parameters are required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n";
+ helpString += "The search parameter allows you to specify the method to find most similar template. Your options are: suffix, kmer, blast and distance. The default is kmer.\n";
+ helpString += "The name parameter allows you add a names file with your fasta file, if you enter multiple fasta files, you must enter matching names files for them.\n";
+ helpString += "The group parameter allows you add a group file so you can have the summary totals broken up by group.\n";
+ helpString += "The method parameter allows you to specify classification method to use. Your options are: bayesian and knn. The default is bayesian.\n";
+ helpString += "The ksize parameter allows you to specify the kmer size for finding most similar template to candidate. The default is 8.\n";
+ helpString += "The processors parameter allows you to specify the number of processors to use. The default is 1.\n";
+#ifdef USE_MPI
+ helpString += "When using MPI, the processors parameter is set to the number of MPI processes running. \n";
+#endif
+ helpString += "If the save parameter is set to true the reference sequences will be saved in memory, to clear them later you can use the clear.memory command. Default=f.";
+ helpString += "The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n";
+ helpString += "The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0.\n";
+ helpString += "The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n";
+ helpString += "The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -1.0.\n";
+ helpString += "The numwanted parameter allows you to specify the number of sequence matches you want with the knn method. The default is 10.\n";
+ helpString += "The cutoff parameter allows you to specify a bootstrap confidence threshold for your taxonomy. The default is 0.\n";
+ helpString += "The probs parameter shuts off the bootstrapping results for the bayesian method. The default is true, meaning you want the bootstrapping to be shown.\n";
+ helpString += "The iters parameter allows you to specify how many iterations to do when calculating the bootstrap confidence score for your taxonomy with the bayesian method. The default is 100.\n";
+ //helpString += "The flip parameter allows you shut off mothur's The default is T.\n";
+ helpString += "The classify.seqs command should be in the following format: \n";
+ helpString += "classify.seqs(reference=yourTemplateFile, fasta=yourFastaFile, method=yourClassificationMethod, search=yourSearchmethod, ksize=yourKmerSize, taxonomy=yourTaxonomyFile, processors=yourProcessors) \n";
+ helpString += "Example classify.seqs(fasta=amazon.fasta, reference=core.filtered, method=knn, search=gotoh, ksize=8, processors=2)\n";
+ helpString += "The .taxonomy file consists of 2 columns: 1 = your sequence name, 2 = the taxonomy for your sequence. \n";
+ helpString += "The .tax.summary is a summary of the different taxonomies represented in your fasta file. \n";
+ helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n";
+ return helpString;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClassifySeqsCommand", "getHelpString");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+ClassifySeqsCommand::ClassifySeqsCommand(){
+ try {
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["taxonomy"] = tempOutNames;
+ outputTypes["accnos"] = tempOutNames;
+ outputTypes["taxsummary"] = tempOutNames;
+ outputTypes["matchdist"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ClassifySeqsCommand", "ClassifySeqsCommand");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+ClassifySeqsCommand::ClassifySeqsCommand(string option) {