X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=chimeraccodecommand.cpp;h=d890db4087813cc3c4c4e453b55013fa555e7689;hp=2586e2801d5071944b6acfa36cac330a9d26694e;hb=cf9987b67aa49777a4c91c2d21f96e58bf17aa82;hpb=1d898dc6edaf9e9f287fab53bf1f21fb29757a17 diff --git a/chimeraccodecommand.cpp b/chimeraccodecommand.cpp index 2586e28..d890db4 100644 --- a/chimeraccodecommand.cpp +++ b/chimeraccodecommand.cpp @@ -9,18 +9,20 @@ #include "chimeraccodecommand.h" #include "ccode.h" +#include "referencedb.h" //********************************************************************************************************************** vector ChimeraCcodeCommand::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 pfilter("filter", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pfilter); - CommandParameter pwindow("window", "Number", "", "0", "", "", "",false,false); parameters.push_back(pwindow); - CommandParameter pnumwanted("numwanted", "Number", "", "20", "", "", "",false,false); parameters.push_back(pnumwanted); - CommandParameter pmask("mask", "String", "", "", "", "", "",false,false); parameters.push_back(pmask); - CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter ptemplate("reference", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(ptemplate); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","chimera-mapinfo-accnos",false,true,true); parameters.push_back(pfasta); + CommandParameter pfilter("filter", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pfilter); + CommandParameter pwindow("window", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pwindow); + CommandParameter pnumwanted("numwanted", "Number", "", "20", "", "", "","",false,false); parameters.push_back(pnumwanted); + CommandParameter pmask("mask", "String", "", "", "", "", "","",false,false); parameters.push_back(pmask); + 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); + CommandParameter psave("save", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psave); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -36,7 +38,7 @@ string ChimeraCcodeCommand::getHelpString(){ try { string helpString = ""; helpString += "The chimera.ccode command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n"; - helpString += "This command was created using the algorythms described in the 'Evaluating putative chimeric sequences from PCR-amplified products' paper by Juan M. Gonzalez, Johannes Zimmerman and Cesareo Saiz-Jimenez.\n"; + helpString += "This command was created using the algorithms described in the 'Evaluating putative chimeric sequences from PCR-amplified products' paper by Juan M. Gonzalez, Johannes Zimmerman and Cesareo Saiz-Jimenez.\n"; helpString += "The chimera.ccode command parameters are fasta, reference, filter, mask, processors, window and numwanted.\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 += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n"; @@ -49,6 +51,7 @@ string ChimeraCcodeCommand::getHelpString(){ helpString += "The mask parameter allows you to specify a file containing one sequence you wish to use as a mask for the your sequences. \n"; helpString += "The window parameter allows you to specify the window size for searching for chimeras. \n"; helpString += "The numwanted parameter allows you to specify how many sequences you would each query sequence compared with.\n"; + 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 chimera.ccode command should be in the following format: \n"; helpString += "chimera.ccode(fasta=yourFastaFile, reference=yourTemplate) \n"; helpString += "Example: chimera.ccode(fasta=AD.align, reference=core_set_aligned.imputed.fasta) \n"; @@ -61,6 +64,23 @@ string ChimeraCcodeCommand::getHelpString(){ } } //********************************************************************************************************************** +string ChimeraCcodeCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "chimera") { pattern = "[filename],[tag],ccode.chimeras-[filename],ccode.chimeras"; } + else if (type == "accnos") { pattern = "[filename],[tag],ccode.accnos-[filename],ccode.accnos"; } + else if (type == "mapinfo") { pattern = "[filename],mapinfo"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ChimeraCcodeCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** ChimeraCcodeCommand::ChimeraCcodeCommand(){ try { abort = true; calledHelp = true; @@ -69,6 +89,7 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(){ outputTypes["chimera"] = tempOutNames; outputTypes["mapinfo"] = tempOutNames; outputTypes["accnos"] = tempOutNames; + } catch(exception& e) { m->errorOut(e, "ChimeraCcodeCommand", "ChimeraCcodeCommand"); @@ -79,9 +100,11 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(){ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { try { abort = false; calledHelp = false; + ReferenceDB* rdb = ReferenceDB::getInstance(); //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { vector myArray = setParameters(); @@ -101,6 +124,7 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { outputTypes["chimera"] = tempOutNames; outputTypes["mapinfo"] = 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); @@ -127,48 +151,66 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { //go through files and make sure they are good, if not, then disregard them for (int i = 0; i < fastaFileNames.size(); i++) { - 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; + 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 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; - } - } + if (!ignore) { - in.close(); + 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 (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--; + //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]); + } } } @@ -178,10 +220,6 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { //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 = ""; } - - templatefile = validParameter.validFile(parameters, "reference", true); - if (templatefile == "not open") { abort = true; } - else if (templatefile == "not found") { templatefile = ""; m->mothurOut("reference is a required parameter for the chimera.ccode command."); m->mothurOutEndLine(); abort = true; } maskfile = validParameter.validFile(parameters, "mask", false); if (maskfile == "not found") { maskfile = ""; } @@ -204,13 +242,35 @@ ChimeraCcodeCommand::ChimeraCcodeCommand(string option) { temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } m->setProcessors(temp); - convert(temp, processors); + 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, "numwanted", false); if (temp == "not found") { temp = "20"; } - convert(temp, numwanted); + m->mothurConvert(temp, numwanted); + + temp = validParameter.validFile(parameters, "save", false); if (temp == "not found"){ temp = "f"; } + save = m->isTrue(temp); + rdb->save = save; + if (save) { //clear out old references + rdb->clearMemory(); + } + + //this has to go after save so that if the user sets save=t and provides no reference we abort + templatefile = validParameter.validFile(parameters, "reference", true); + if (templatefile == "not found") { + //check for saved reference sequences + if (rdb->referenceSeqs.size() != 0) { + templatefile = "saved"; + }else { + m->mothurOut("[ERROR]: You don't have any saved reference sequences and the reference parameter is a required."); + m->mothurOutEndLine(); + abort = true; + } + }else if (templatefile == "not open") { abort = true; } + else { if (save) { rdb->setSavedReference(templatefile); } } + } } @@ -242,23 +302,20 @@ int ChimeraCcodeCommand::execute(){ if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]); }//if user entered a file with a path then preserve it string outputFileName, accnosFileName; - if (maskfile != "") { - outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + maskfile + ".ccode.chimeras"; - accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + maskfile + ".ccode.accnos"; - }else { - outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "ccode.chimeras"; - accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "ccode.accnos"; - } - - string mapInfo = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "mapinfo"; - - if (m->control_pressed) { delete chimera; for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); return 0; } + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])); + string mapInfo = getOutputFileName("mapinfo", variables); + if (maskfile != "") { variables["[tag]"] = maskfile; } + outputFileName = getOutputFileName("chimera", variables); + accnosFileName = getOutputFileName("accnos", variables); + + if (m->control_pressed) { delete chimera; for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); return 0; } #ifdef USE_MPI int pid, numSeqsPerProcessor; int tag = 2001; - vector MPIPos; + vector MPIPos; MPI_Status status; MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are @@ -284,7 +341,7 @@ int ChimeraCcodeCommand::execute(){ MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPI); MPI_File_open(MPI_COMM_WORLD, outAccnosFilename, outMode, MPI_INFO_NULL, &outMPIAccnos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } + if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); delete chimera; return 0; } if (pid == 0) { //you are the root process string outTemp = "For full window mapping info refer to " + mapInfo + "\n"; @@ -314,7 +371,7 @@ int ChimeraCcodeCommand::execute(){ //align your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, MPIPos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); remove(outputFileName.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } + if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); m->mothurRemove(outputFileName); m->mothurRemove(accnosFileName); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); delete chimera; return 0; } }else{ //you are a child process MPI_Recv(&numSeqs, 1, MPI_INT, 0, tag, MPI_COMM_WORLD, &status); @@ -330,7 +387,7 @@ int ChimeraCcodeCommand::execute(){ //align your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, MPIPos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } + if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); delete chimera; return 0; } } //close files @@ -349,19 +406,21 @@ int ChimeraCcodeCommand::execute(){ outHeader.close(); - vector positions = m->divideFile(fastaFileNames[s], processors); - - for (int i = 0; i < (positions.size()-1); i++) { - lines.push_back(new linePair(positions[i], positions[(i+1)])); - } + //break up file - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + vector positions = m->divideFile(fastaFileNames[s], processors); + + for (int i = 0; i < (positions.size()-1); i++) { + lines.push_back(new linePair(positions[i], positions[(i+1)])); + } + if(processors == 1){ numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName); - if (m->control_pressed) { remove(outputFileName.c_str()); remove(tempHeader.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } + if (m->control_pressed) { m->mothurRemove(outputFileName); m->mothurRemove(tempHeader); m->mothurRemove(accnosFileName); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } }else{ processIDS.resize(0); @@ -374,19 +433,19 @@ int ChimeraCcodeCommand::execute(){ //append output files for(int i=1;iappendFiles((outputFileName + toString(processIDS[i]) + ".temp"), outputFileName); - remove((outputFileName + toString(processIDS[i]) + ".temp").c_str()); + m->mothurRemove((outputFileName + toString(processIDS[i]) + ".temp")); } //append output files for(int i=1;iappendFiles((accnosFileName + toString(processIDS[i]) + ".temp"), accnosFileName); - remove((accnosFileName + toString(processIDS[i]) + ".temp").c_str()); + m->mothurRemove((accnosFileName + toString(processIDS[i]) + ".temp")); } if (m->control_pressed) { - remove(outputFileName.c_str()); - remove(accnosFileName.c_str()); - for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); + m->mothurRemove(outputFileName); + m->mothurRemove(accnosFileName); + for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); for (int i = 0; i < lines.size(); i++) { delete lines[i]; } lines.clear(); delete chimera; return 0; @@ -395,15 +454,16 @@ int ChimeraCcodeCommand::execute(){ } #else + lines.push_back(new linePair(0, 1000)); numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName); - if (m->control_pressed) { remove(outputFileName.c_str()); remove(tempHeader.c_str()); remove(accnosFileName.c_str()); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } + if (m->control_pressed) { m->mothurRemove(outputFileName); m->mothurRemove(tempHeader); m->mothurRemove(accnosFileName); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } for (int i = 0; i < lines.size(); i++) { delete lines[i]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } #endif m->appendFiles(outputFileName, tempHeader); - remove(outputFileName.c_str()); + m->mothurRemove(outputFileName); rename(tempHeader.c_str(), outputFileName.c_str()); #endif @@ -480,18 +540,18 @@ int ChimeraCcodeCommand::driver(linePair* filePos, string outputFName, string fi } delete candidateSeq; - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) - unsigned long int pos = inFASTA.tellg(); + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + unsigned long long pos = inFASTA.tellg(); if ((pos == -1) || (pos >= filePos->end)) { break; } #else if (inFASTA.eof()) { break; } #endif //report progress - if((count) % 100 == 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine(); } + if((count) % 100 == 0){ m->mothurOutJustToScreen("Processing sequence: " + toString(count) + "\n"); } } //report progress - if((count) % 100 != 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine(); } + if((count) % 100 != 0){ m->mothurOutJustToScreen("Processing sequence: " + toString(count) + "\n"); } out.close(); out2.close(); @@ -506,7 +566,7 @@ int ChimeraCcodeCommand::driver(linePair* filePos, string outputFName, string fi } //********************************************************************************************************************** #ifdef USE_MPI -int ChimeraCcodeCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& outMPI, MPI_File& outAccMPI, vector& MPIPos){ +int ChimeraCcodeCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& outMPI, MPI_File& outAccMPI, vector& MPIPos){ try { MPI_Status status; @@ -567,7 +627,7 @@ int ChimeraCcodeCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File int ChimeraCcodeCommand::createProcesses(string outputFileName, string filename, string accnos) { try { -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) int process = 0; int num = 0; @@ -607,7 +667,7 @@ int ChimeraCcodeCommand::createProcesses(string outputFileName, string filename, string tempFile = outputFileName + toString(processIDS[i]) + ".num.temp"; m->openInputFile(tempFile, in); if (!in.eof()) { int tempNum = 0; in >> tempNum; num += tempNum; } - in.close(); remove(tempFile.c_str()); + in.close(); m->mothurRemove(tempFile); } return num;