X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=chimeracheckcommand.cpp;h=64ed9faa73e7cb72e5e307cc10e86f1a9bcfc195;hp=d82a84a1b86ab5643e0416d8d73091ce16b29e23;hb=615301e57c25e241356a9c2380648d117709458d;hpb=e150b0b0664caec517485ee6d69dcdade6dcae77 diff --git a/chimeracheckcommand.cpp b/chimeracheckcommand.cpp index d82a84a..64ed9fa 100644 --- a/chimeracheckcommand.cpp +++ b/chimeracheckcommand.cpp @@ -8,20 +8,22 @@ */ #include "chimeracheckcommand.h" +#include "referencedb.h" //********************************************************************************************************************** vector ChimeraCheckCommand::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 psvg("svg", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(psvg); - CommandParameter pincrement("increment", "Number", "", "10", "", "", "",false,false); parameters.push_back(pincrement); - CommandParameter pksize("ksize", "Number", "", "7", "", "", "",false,false); parameters.push_back(pksize); - 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",false,true,true); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none","",false,false,true); parameters.push_back(pname); + CommandParameter psvg("svg", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psvg); + CommandParameter pincrement("increment", "Number", "", "10", "", "", "","",false,false); parameters.push_back(pincrement); + CommandParameter pksize("ksize", "Number", "", "7", "", "", "","",false,false); parameters.push_back(pksize); + 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); } return myArray; @@ -36,7 +38,7 @@ string ChimeraCheckCommand::getHelpString(){ try { string helpString = ""; helpString += "The chimera.check command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n"; - helpString += "This command was created using the algorythms described in CHIMERA_CHECK version 2.7 written by Niels Larsen. \n"; + helpString += "This command was created using the algorithms described in CHIMERA_CHECK version 2.7 written by Niels Larsen. \n"; helpString += "The chimera.check command parameters are fasta, reference, processors, ksize, increment, svg and name.\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"; @@ -50,6 +52,7 @@ string ChimeraCheckCommand::getHelpString(){ helpString += "The svg parameter allows you to specify whether or not you would like a svg file outputted for each query sequence, default is False.\n"; helpString += "The name parameter allows you to enter a file containing names of sequences you would like .svg files for.\n"; helpString += "You may enter multiple name files by separating their names with dashes. ie. fasta=abrecovery.svg.names-amzon.svg.names \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.check command should be in the following format: \n"; helpString += "chimera.check(fasta=yourFastaFile, reference=yourTemplateFile, processors=yourProcessors, ksize=yourKmerSize) \n"; helpString += "Example: chimera.check(fasta=AD.fasta, reference=core_set_aligned,imputed.fasta, processors=4, ksize=8) \n"; @@ -62,6 +65,21 @@ string ChimeraCheckCommand::getHelpString(){ } } //********************************************************************************************************************** +string ChimeraCheckCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "chimera") { pattern = "[filename],chimeracheck.chimeras"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ChimeraCheckCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** ChimeraCheckCommand::ChimeraCheckCommand(){ try { abort = true; calledHelp = true; @@ -77,7 +95,8 @@ ChimeraCheckCommand::ChimeraCheckCommand(){ //*************************************************************************************************************** ChimeraCheckCommand::ChimeraCheckCommand(string option) { try { - abort = false; calledHelp = false; + abort = false; calledHelp = false; + ReferenceDB* rdb = ReferenceDB::getInstance(); //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } @@ -183,6 +202,8 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { //erase from file list fastaFileNames.erase(fastaFileNames.begin()+i); i--; + }else { + m->setFastaFile(fastaFileNames[i]); } } } @@ -193,10 +214,6 @@ ChimeraCheckCommand::ChimeraCheckCommand(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.check command."); m->mothurOutEndLine(); abort = true; } namefile = validParameter.validFile(parameters, "name", false); if (namefile == "not found") { namefile = ""; } @@ -262,6 +279,8 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { //erase from file list nameFileNames.erase(nameFileNames.begin()+i); i--; + }else { + m->setNameFile(nameFileNames[i]); } } } @@ -277,17 +296,39 @@ ChimeraCheckCommand::ChimeraCheckCommand(string option) { string 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, "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); } } + temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found") { temp = "7"; } - convert(temp, ksize); + m->mothurConvert(temp, ksize); temp = validParameter.validFile(parameters, "svg", false); if (temp == "not found") { temp = "F"; } svg = m->isTrue(temp); if (nameFileNames.size() != 0) { svg = true; } temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "10"; } - convert(temp, increment); + m->mothurConvert(temp, increment); } } catch(exception& e) { @@ -316,14 +357,16 @@ int ChimeraCheckCommand::execute(){ if (m->control_pressed) { delete chimera; return 0; } if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[i]); }//if user entered a file with a path then preserve it - string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])) + "chimeracheck.chimeras"; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])); + string outputFileName = getOutputFileName("chimera", variables); outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName); #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 @@ -344,7 +387,7 @@ int ChimeraCheckCommand::execute(){ MPI_File_open(MPI_COMM_WORLD, inFileName, inMode, MPI_INFO_NULL, &inMPI); //comm, filename, mode, info, filepointer MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPI); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); 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); 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 MPIPos = m->setFilePosFasta(fastaFileNames[i], numSeqs); //fills MPIPos, returns numSeqs @@ -364,7 +407,7 @@ int ChimeraCheckCommand::execute(){ //align your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, MPIPos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); 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); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); delete chimera; return 0; } //wait on chidren for(int j = 1; j < processors; j++) { @@ -384,7 +427,7 @@ int ChimeraCheckCommand::execute(){ //align your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, MPIPos); - if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); 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); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); delete chimera; return 0; } //tell parent you are done. char buf[5]; @@ -398,18 +441,20 @@ int ChimeraCheckCommand::execute(){ MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case #else - vector positions = m->divideFile(fastaFileNames[i], processors); - - for (int s = 0; s < (positions.size()-1); s++) { - lines.push_back(new linePair(positions[s], positions[(s+1)])); - } + //break up file - #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) + vector positions = m->divideFile(fastaFileNames[i], processors); + + for (int s = 0; s < (positions.size()-1); s++) { + lines.push_back(new linePair(positions[s], positions[(s+1)])); + } + if(processors == 1){ numSeqs = driver(lines[0], outputFileName, fastaFileNames[i]); - if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } for (int j = 0; j < lines.size(); j++) { delete lines[j]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } + if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } for (int j = 0; j < lines.size(); j++) { delete lines[j]; } outputTypes.clear(); lines.clear(); delete chimera; return 0; } }else{ processIDS.resize(0); @@ -421,11 +466,11 @@ int ChimeraCheckCommand::execute(){ //append output files for(int j=1;jappendFiles((outputFileName + toString(processIDS[j]) + ".temp"), outputFileName); - remove((outputFileName + toString(processIDS[j]) + ".temp").c_str()); + m->mothurRemove((outputFileName + toString(processIDS[j]) + ".temp")); } if (m->control_pressed) { - for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); + for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); for (int j = 0; j < lines.size(); j++) { delete lines[j]; } lines.clear(); delete chimera; return 0; @@ -433,9 +478,10 @@ int ChimeraCheckCommand::execute(){ } #else + lines.push_back(new linePair(0, 1000)); numSeqs = driver(lines[0], outputFileName, fastaFileNames[i]); - if (m->control_pressed) { for (int j = 0; j < lines.size(); j++) { delete lines[j]; } lines.clear(); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } outputTypes.clear(); delete chimera; return 0; } + if (m->control_pressed) { for (int j = 0; j < lines.size(); j++) { delete lines[j]; } lines.clear(); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } outputTypes.clear(); delete chimera; return 0; } #endif #endif delete chimera; @@ -493,18 +539,18 @@ int ChimeraCheckCommand::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(); inFASTA.close(); @@ -518,7 +564,7 @@ int ChimeraCheckCommand::driver(linePair* filePos, string outputFName, string fi } //********************************************************************************************************************** #ifdef USE_MPI -int ChimeraCheckCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& outMPI, vector& MPIPos){ +int ChimeraCheckCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& outMPI, vector& MPIPos){ try { MPI_File outAccMPI; MPI_Status status; @@ -552,10 +598,10 @@ int ChimeraCheckCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File delete candidateSeq; //report progress - if((i+1) % 100 == 0){ cout << "Processing sequence: " << (i+1) << endl; m->mothurOutJustToLog("Processing sequence: " + toString(i+1) + "\n"); } + if((i+1) % 100 == 0){ cout << "Processing sequence: " << (i+1) << endl; } } //report progress - if(num % 100 != 0){ cout << "Processing sequence: " << num << endl; m->mothurOutJustToLog("Processing sequence: " + toString(num) + "\n"); } + if(num % 100 != 0){ cout << "Processing sequence: " << num << endl; } return 0; } @@ -570,7 +616,7 @@ int ChimeraCheckCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File int ChimeraCheckCommand::createProcesses(string outputFileName, string filename) { try { -#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) +#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) int process = 0; int num = 0; @@ -610,7 +656,7 @@ int ChimeraCheckCommand::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;