X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=chimerabellerophoncommand.cpp;h=bb119e41c8e5b40dd681793c43c10f4c6f7e6c61;hp=69eb89533b4988e598c000b8bf5b8a111e07e5e1;hb=1a20e24ee786195ab0e1cccd4f5aede7a88f3f4e;hpb=2bbb7273d4bf5209f098c764551c6e072d60df36 diff --git a/chimerabellerophoncommand.cpp b/chimerabellerophoncommand.cpp index 69eb895..bb119e4 100644 --- a/chimerabellerophoncommand.cpp +++ b/chimerabellerophoncommand.cpp @@ -10,24 +10,99 @@ #include "chimerabellerophoncommand.h" #include "bellerophon.h" +//********************************************************************************************************************** +vector ChimeraBellerophonCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "none","none","none","chimera-accnos",false,true,true); parameters.push_back(pfasta); + CommandParameter pfilter("filter", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pfilter); + CommandParameter pcorrection("correction", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pcorrection); + CommandParameter pwindow("window", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pwindow); + CommandParameter pincrement("increment", "Number", "", "25", "", "", "","",false,false); parameters.push_back(pincrement); + CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ChimeraBellerophonCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string ChimeraBellerophonCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The chimera.bellerophon command reads a fastafile and creates list of potentially chimeric sequences.\n"; + helpString += "The chimera.bellerophon command parameters are fasta, filter, correction, processors, window, increment. The fasta parameter is required, unless you have a valid current file.\n"; + helpString += "The fasta parameter is required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n"; + helpString += "The filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter, default=false. \n"; + helpString += "The correction parameter allows you to put more emphasis on the distance between highly similar sequences and less emphasis on the differences between remote homologs, default=true.\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 window parameter allows you to specify the window size for searching for chimeras, default is 1/4 sequence length. \n"; + helpString += "The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default is 25.\n"; + helpString += "chimera.bellerophon(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors) \n"; + helpString += "Example: chimera.bellerophon(fasta=AD.align, filter=True, correction=true, window=200) \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, "ChimeraBellerophonCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +string ChimeraBellerophonCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "chimera") { pattern = "[filename],bellerophon.chimeras"; } + else if (type == "accnos") { pattern = "[filename],bellerophon.accnos"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ChimeraBellerophonCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +ChimeraBellerophonCommand::ChimeraBellerophonCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["chimera"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "ChimeraBellerophonCommand", "ChimeraBellerophonCommand"); + exit(1); + } +} //*************************************************************************************************************** - ChimeraBellerophonCommand::ChimeraBellerophonCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + 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","filter","correction","processors","window","increment","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); - ValidParameters validParameter; + ValidParameters validParameter("chimera.bellerophon"); map::iterator it; //check to make sure all parameters are valid for command @@ -35,47 +110,112 @@ ChimeraBellerophonCommand::ChimeraBellerophonCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["chimera"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; } - else { - string path; - it = parameters.find("fasta"); - //user has given a template file - if(it != parameters.end()){ - path = hasPath(it->second); - //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { parameters["fasta"] = inputDir + it->second; } + + fastafile = validParameter.validFile(parameters, "fasta", false); + if (fastafile == "not found") { + //if there is a current fasta file, use it + string filename = m->getFastaFile(); + if (filename != "") { fastaFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the fasta parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { + m->splitAtDash(fastafile, fastaFileNames); + + //go through files and make sure they are good, if not, then disregard them + for (int i = 0; i < fastaFileNames.size(); i++) { + + bool ignore = false; + if (fastaFileNames[i] == "current") { + fastaFileNames[i] = m->getFastaFile(); + if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + fastaFileNames.erase(fastaFileNames.begin()+i); + i--; + } + } + + if (!ignore) { + + if (inputDir != "") { + string path = m->hasPath(fastaFileNames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; } + } + + int ableToOpen; + ifstream in; + + ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror"); + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]); + m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastaFileNames[i] = tryPath; + } + } + + //if you can't open it, try default location + if (ableToOpen == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]); + m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + fastaFileNames[i] = tryPath; + } + } + + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + fastaFileNames.erase(fastaFileNames.begin()+i); + i--; + }else { + m->setFastaFile(fastaFileNames[i]); + } + } } + + //make sure there is at least one valid file left + if (fastaFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; } } - - - //check for required parameters - fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the chimera.bellerophon command."); m->mothurOutEndLine(); abort = true; } //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 = ""; - outputDir += hasPath(fastafile); //if user entered a file with a path then preserve it - } + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; } string temp; temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; } - filter = isTrue(temp); + filter = m->isTrue(temp); temp = validParameter.validFile(parameters, "correction", false); if (temp == "not found") { temp = "T"; } - correction = isTrue(temp); + correction = m->isTrue(temp); - temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; } - convert(temp, processors); + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); + m->mothurConvert(temp, processors); temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; } - convert(temp, window); + m->mothurConvert(temp, window); temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "25"; } - convert(temp, increment); + m->mothurConvert(temp, increment); } } catch(exception& e) { @@ -83,104 +223,85 @@ ChimeraBellerophonCommand::ChimeraBellerophonCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void ChimeraBellerophonCommand::help(){ - try { - m->mothurOut("The chimera.bellerophon command reads a fastafile and creates list of potentially chimeric sequences.\n"); - m->mothurOut("The chimera.bellerophon command parameters are fasta, filter, correction, processors, window, increment. The fasta parameter is required.\n"); - m->mothurOut("The filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter, default=false. \n"); - m->mothurOut("The correction parameter allows you to put more emphasis on the distance between highly similar sequences and less emphasis on the differences between remote homologs.\n"); - m->mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n"); - #ifdef USE_MPI - m->mothurOut("When using MPI, the processors parameter is set to the number of MPI processes running. \n"); - #endif - m->mothurOut("The window parameter allows you to specify the window size for searching for chimeras, default is 1/4 sequence length. \n"); - m->mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default is 25.\n"); - m->mothurOut("chimera.bellerophon(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors) \n"); - m->mothurOut("Example: chimera.seqs(fasta=AD.align, filter=True, correction=true, window=200) \n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "ChimeraBellerophonCommand", "help"); - exit(1); - } -} - -//*************************************************************************************************************** - -ChimeraBellerophonCommand::~ChimeraBellerophonCommand(){ /* do nothing */ } - //*************************************************************************************************************** - int ChimeraBellerophonCommand::execute(){ try{ - if (abort == true) { return 0; } - - int start = time(NULL); - - chimera = new Bellerophon(fastafile, filter, correction, window, increment, processors, outputDir); - - string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "bellerophon.chimeras"; - string accnosFileName = outputDir + getRootName(getSimpleName(fastafile)) + "bellerophon.accnos"; - bool hasAccnos = true; - - chimera->getChimeras(); + if (abort == true) { if (calledHelp) { return 0; } return 2; } - if (m->control_pressed) { delete chimera; return 0; } - - #ifdef USE_MPI - MPI_File outMPI; - MPI_File outMPIAccnos; - - int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY; - - char* outFilename = new char[accnosFileName.length()]; - memcpy(outFilename, accnosFileName.c_str(), accnosFileName.length()); - - char* FileName = new char[outputFileName.length()]; - memcpy(FileName, outputFileName.c_str(), outputFileName.length()); - - - MPI_File_open(MPI_COMM_WORLD, FileName, outMode, MPI_INFO_NULL, &outMPI); //comm, filename, mode, info, filepointer - MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPIAccnos); - - delete FileName; - delete outFilename; + for (int i = 0; i < fastaFileNames.size(); i++) { + + m->mothurOut("Checking sequences from " + fastaFileNames[i] + " ..." ); m->mothurOutEndLine(); + + int start = time(NULL); + + chimera = new Bellerophon(fastaFileNames[i], filter, correction, window, increment, processors, outputDir); + + if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[i]); }//if user entered a file with a path then preserve it + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])); + string outputFileName = getOutputFileName("chimera", variables); + string accnosFileName = getOutputFileName("accnos", variables); + + chimera->getChimeras(); + + if (m->control_pressed) { delete chimera; for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); return 0; } + + #ifdef USE_MPI + MPI_File outMPI; + MPI_File outMPIAccnos; + + int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY; + + char outFilename[1024]; + strcpy(outFilename, accnosFileName.c_str()); - numSeqs = chimera->print(outMPI, outMPIAccnos); - - MPI_File_close(&outMPI); - MPI_File_close(&outMPIAccnos); + char FileName[1024]; + strcpy(FileName, outputFileName.c_str()); - #else + MPI_File_open(MPI_COMM_WORLD, FileName, outMode, MPI_INFO_NULL, &outMPI); //comm, filename, mode, info, filepointer + MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPIAccnos); - ofstream out; - openOutputFile(outputFileName, out); - - ofstream out2; - openOutputFile(accnosFileName, out2); - - numSeqs = chimera->print(out, out2); - out.close(); - out2.close(); - - #endif + numSeqs = chimera->print(outMPI, outMPIAccnos, ""); + + MPI_File_close(&outMPI); + MPI_File_close(&outMPIAccnos); + + #else - if (m->control_pressed) { remove(accnosFileName.c_str()); remove(outputFileName.c_str()); delete chimera; return 0; } + ofstream out; + m->openOutputFile(outputFileName, out); + + ofstream out2; + m->openOutputFile(accnosFileName, out2); + + numSeqs = chimera->print(out, out2, ""); + out.close(); + out2.close(); + + #endif + + if (m->control_pressed) { m->mothurRemove(accnosFileName); m->mothurRemove(outputFileName); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); delete chimera; return 0; } + + m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine(); + + outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName); + outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName); + + delete chimera; + } - //delete accnos file if its blank - if (isBlank(accnosFileName)) { remove(accnosFileName.c_str()); hasAccnos = false; } + //set accnos file as new current accnosfile + string current = ""; + itTypes = outputTypes.find("accnos"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); } + } m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); - m->mothurOut(outputFileName); m->mothurOutEndLine(); - if (hasAccnos) { m->mothurOut(accnosFileName); m->mothurOutEndLine(); } + for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } m->mothurOutEndLine(); - m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine(); - - delete chimera; return 0;