+//**********************************************************************************************************************
+vector<string> ChimeraSlayerCommand::setParameters(){
+ try {
+ 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 pwindow("window", "Number", "", "50", "", "", "",false,false); parameters.push_back(pwindow);
+ CommandParameter pksize("ksize", "Number", "", "7", "", "", "",false,false); parameters.push_back(pksize);
+ CommandParameter pmatch("match", "Number", "", "5.0", "", "", "",false,false); parameters.push_back(pmatch);
+ CommandParameter pmismatch("mismatch", "Number", "", "-4.0", "", "", "",false,false); parameters.push_back(pmismatch);
+ CommandParameter pminsim("minsim", "Number", "", "90", "", "", "",false,false); parameters.push_back(pminsim);
+ CommandParameter pmincov("mincov", "Number", "", "70", "", "", "",false,false); parameters.push_back(pmincov);
+ CommandParameter pminsnp("minsnp", "Number", "", "10", "", "", "",false,false); parameters.push_back(pminsnp);
+ CommandParameter pminbs("minbs", "Number", "", "90", "", "", "",false,false); parameters.push_back(pminbs);
+ CommandParameter psearch("search", "Multiple", "kmer-blast", "blast", "", "", "",false,false); parameters.push_back(psearch);
+ CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
+ CommandParameter prealign("realign", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(prealign);
+ CommandParameter ptrim("trim", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(ptrim);
+ CommandParameter psplit("split", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(psplit);
+ CommandParameter pnumwanted("numwanted", "Number", "", "15", "", "", "",false,false); parameters.push_back(pnumwanted);
+ CommandParameter piters("iters", "Number", "", "1000", "", "", "",false,false); parameters.push_back(piters);
+ CommandParameter pdivergence("divergence", "Number", "", "1.007", "", "", "",false,false); parameters.push_back(pdivergence);
+ CommandParameter pparents("parents", "Number", "", "3", "", "", "",false,false); parameters.push_back(pparents);
+ CommandParameter pincrement("increment", "Number", "", "5", "", "", "",false,false); parameters.push_back(pincrement);
+ 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, "ChimeraSlayerCommand", "setParameters");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+string ChimeraSlayerCommand::getHelpString(){
+ try {
+ string helpString = "";
+ helpString += "The chimera.slayer command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n";
+ helpString += "This command was modeled after the chimeraSlayer written by the Broad Institute.\n";
+ helpString += "The chimera.slayer command parameters are fasta, name, template, processors, trim, ksize, window, match, mismatch, divergence. minsim, mincov, minbs, minsnp, parents, search, iters, increment, numwanted, and realign.\n";
+ helpString += "The fasta parameter allows you to enter the fasta file containing your potentially chimeric sequences, and is required, unless you have a valid current fasta file. \n";
+ helpString += "The name parameter allows you to provide a name file, if you are using template=self. \n";
+ helpString += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amazon.fasta \n";
+ helpString += "The reference parameter allows you to enter a reference file containing known non-chimeric sequences, and is required. You may also set template=self, in this case the abundant sequences will be used as potential parents. \n";
+ helpString += "The processors parameter allows you to specify how many processors you would like 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 += "The trim parameter allows you to output a new fasta file containing your sequences with the chimeric ones trimmed to include only their longest piece, default=F. \n";
+ helpString += "The split parameter allows you to check both pieces of non-chimeric sequence for chimeras, thus looking for trimeras and quadmeras. default=F. \n";
+ helpString += "The window parameter allows you to specify the window size for searching for chimeras, default=50. \n";
+ helpString += "The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default=5.\n";
+ helpString += "The numwanted parameter allows you to specify how many sequences you would each query sequence compared with, default=15.\n";
+ helpString += "The ksize parameter allows you to input kmersize, default is 7, used if search is kmer. \n";
+ helpString += "The match parameter allows you to reward matched bases in blast search, default is 5. \n";
+ helpString += "The parents parameter allows you to select the number of potential parents to investigate from the numwanted best matches after rating them, default is 3. \n";
+ helpString += "The mismatch parameter allows you to penalize mismatched bases in blast search, default is -4. \n";
+ helpString += "The divergence parameter allows you to set a cutoff for chimera determination, default is 1.007. \n";
+ helpString += "The iters parameter allows you to specify the number of bootstrap iters to do with the chimeraslayer method, default=1000.\n";
+ helpString += "The minsim parameter allows you to specify a minimum similarity with the parent fragments, default=90. \n";
+ helpString += "The mincov parameter allows you to specify minimum coverage by closest matches found in template. Default is 70, meaning 70%. \n";
+ helpString += "The minbs parameter allows you to specify minimum bootstrap support for calling a sequence chimeric. Default is 90, meaning 90%. \n";
+ helpString += "The minsnp parameter allows you to specify percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default: 10) \n";
+ helpString += "The search parameter allows you to specify search method for finding the closest parent. Choices are blast, and kmer, default blast. \n";
+ helpString += "The realign parameter allows you to realign the query to the potential parents. Choices are true or false, default true. \n";
+ helpString += "The chimera.slayer command should be in the following format: \n";
+ helpString += "chimera.slayer(fasta=yourFastaFile, reference=yourTemplate, search=yourSearch) \n";
+ helpString += "Example: chimera.slayer(fasta=AD.align, reference=core_set_aligned.imputed.fasta, search=kmer) \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, "ChimeraSlayerCommand", "getHelpString");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
+ChimeraSlayerCommand::ChimeraSlayerCommand(){
+ try {
+ abort = true; calledHelp = true;
+ setParameters();
+ vector<string> tempOutNames;
+ outputTypes["chimera"] = tempOutNames;
+ outputTypes["accnos"] = tempOutNames;
+ outputTypes["fasta"] = tempOutNames;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "ChimeraSlayerCommand", "ChimeraSlayerCommand");
+ exit(1);
+ }
+}