X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chimeraslayercommand.cpp;h=4c37a854fe317a29c90be7dc45e31144fe68a6c5;hb=19fcbbdba99658f5eca244803280f9ee7f9f6607;hp=f6baa0a2074d75e01c73eeb50cae1f77f291ee20;hpb=1e4552ceb0f67f70a147d1cdca7244b62ac115ab;p=mothur.git diff --git a/chimeraslayercommand.cpp b/chimeraslayercommand.cpp index f6baa0a..4c37a85 100644 --- a/chimeraslayercommand.cpp +++ b/chimeraslayercommand.cpp @@ -10,6 +10,7 @@ #include "chimeraslayercommand.h" #include "chimeraslayer.h" #include "deconvolutecommand.h" +#include "referencedb.h" //********************************************************************************************************************** vector ChimeraSlayerCommand::setParameters(){ @@ -23,21 +24,22 @@ vector ChimeraSlayerCommand::setParameters(){ 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", "", "100", "", "", "",false,false); parameters.push_back(pminsnp); + 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-distance", "distance", "", "", "",false,false); parameters.push_back(psearch); + 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", "", "F", "", "", "",false,false); parameters.push_back(prealign); + 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", "", "100", "", "", "",false,false); parameters.push_back(piters); + 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); - + 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; @@ -53,9 +55,9 @@ string ChimeraSlayerCommand::getHelpString(){ 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 and numwanted.\n"; //realign, + 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 += "The name parameter allows you to provide a name file, if you are using reference=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"; @@ -72,13 +74,14 @@ string ChimeraSlayerCommand::getHelpString(){ 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=100.\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: 100) \n"; - helpString += "The search parameter allows you to specify search method for finding the closest parent. Choices are distance, blast, and kmer, default distance. \n"; - helpString += "The realign parameter allows you to realign the query to the potential parents. Choices are true or false, default false. \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 += "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.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"; @@ -109,9 +112,11 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(){ ChimeraSlayerCommand::ChimeraSlayerCommand(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(); @@ -148,47 +153,65 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(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 (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) { + + 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]; } } - } - - in.close(); + + 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 (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]); + } } } @@ -206,47 +229,65 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { //go through files and make sure they are good, if not, then disregard them for (int i = 0; i < nameFileNames.size(); i++) { - if (inputDir != "") { - string path = m->hasPath(nameFileNames[i]); - //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { nameFileNames[i] = inputDir + nameFileNames[i]; } - } - - int ableToOpen; - ifstream in; - ableToOpen = m->openInputFile(nameFileNames[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(nameFileNames[i]); - m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - nameFileNames[i] = tryPath; + bool ignore = false; + if (nameFileNames[i] == "current") { + nameFileNames[i] = m->getNameFile(); + if (nameFileNames[i] != "") { m->mothurOut("Using " + nameFileNames[i] + " as input file for the name parameter where you had given current."); m->mothurOutEndLine(); } + else { + m->mothurOut("You have no current namefile, ignoring current."); m->mothurOutEndLine(); ignore=true; + //erase from file list + nameFileNames.erase(nameFileNames.begin()+i); + i--; } } - if (ableToOpen == 1) { - if (m->getOutputDir() != "") { //default path is set - string tryPath = m->getOutputDir() + m->getSimpleName(nameFileNames[i]); - m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); - ifstream in2; - ableToOpen = m->openInputFile(tryPath, in2, "noerror"); - in2.close(); - nameFileNames[i] = tryPath; + if (!ignore) { + + if (inputDir != "") { + string path = m->hasPath(nameFileNames[i]); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { nameFileNames[i] = inputDir + nameFileNames[i]; } + } + + int ableToOpen; + ifstream in; + + ableToOpen = m->openInputFile(nameFileNames[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(nameFileNames[i]); + m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + nameFileNames[i] = tryPath; + } + } + + if (ableToOpen == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(nameFileNames[i]); + m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in2; + ableToOpen = m->openInputFile(tryPath, in2, "noerror"); + in2.close(); + nameFileNames[i] = tryPath; + } + } + + in.close(); + + if (ableToOpen == 1) { + m->mothurOut("Unable to open " + nameFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); + //erase from file list + nameFileNames.erase(nameFileNames.begin()+i); + i--; + }else { + m->setNameFile(nameFileNames[i]); } - } - - in.close(); - - if (ableToOpen == 1) { - m->mothurOut("Unable to open " + nameFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine(); - //erase from file list - nameFileNames.erase(nameFileNames.begin()+i); - i--; } } @@ -259,12 +300,29 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(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 = ""; } + string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); + convert(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(); + } string path; it = parameters.find("reference"); //user has given a template file if(it != parameters.end()){ - if (it->second == "self") { templatefile = "self"; } + if (it->second == "self") { + templatefile = "self"; + if (save) { + m->mothurOut("[WARNING]: You can't save reference=self, ignoring save."); + m->mothurOutEndLine(); + save = false; + } + } else { path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. @@ -272,13 +330,34 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { 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.slayer command."); m->mothurOutEndLine(); abort = true; } + else 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 (save) { rdb->setSavedReference(templatefile); } } + } + }else if (hasName) { templatefile = "self"; + if (save) { + m->mothurOut("[WARNING]: You can't save reference=self, ignoring save."); + m->mothurOutEndLine(); + save = false; } } + else { + 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(); + templatefile = ""; abort = true; + } + } + - string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } - m->setProcessors(temp); - convert(temp, processors); temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found") { temp = "7"; } convert(temp, ksize); @@ -304,13 +383,13 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { temp = validParameter.validFile(parameters, "minbs", false); if (temp == "not found") { temp = "90"; } convert(temp, minBS); - temp = validParameter.validFile(parameters, "minsnp", false); if (temp == "not found") { temp = "100"; } + temp = validParameter.validFile(parameters, "minsnp", false); if (temp == "not found") { temp = "10"; } convert(temp, minSNP); temp = validParameter.validFile(parameters, "parents", false); if (temp == "not found") { temp = "3"; } convert(temp, parents); - temp = validParameter.validFile(parameters, "realign", false); if (temp == "not found") { temp = "f"; } + temp = validParameter.validFile(parameters, "realign", false); if (temp == "not found") { temp = "t"; } realign = m->isTrue(temp); temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found") { temp = "f"; } @@ -319,9 +398,9 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { temp = validParameter.validFile(parameters, "split", false); if (temp == "not found") { temp = "f"; } trimera = m->isTrue(temp); - search = validParameter.validFile(parameters, "search", false); if (search == "not found") { search = "distance"; } + search = validParameter.validFile(parameters, "search", false); if (search == "not found") { search = "blast"; } - temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "100"; } + temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; } convert(temp, iters); temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "5"; } @@ -330,7 +409,9 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { temp = validParameter.validFile(parameters, "numwanted", false); if (temp == "not found") { temp = "15"; } convert(temp, numwanted); - if ((search != "distance") && (search != "blast") && (search != "kmer")) { m->mothurOut(search + " is not a valid search."); m->mothurOutEndLine(); abort = true; } + if ((search != "blast") && (search != "kmer")) { m->mothurOut(search + " is not a valid search."); m->mothurOutEndLine(); abort = true; } + + if (hasName && (templatefile != "self")) { m->mothurOut("You have provided a namefile and the reference parameter is not set to self. I am not sure what reference you are trying to use, aborting."); m->mothurOutEndLine(); abort=true; } } } catch(exception& e) { @@ -342,9 +423,8 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { int ChimeraSlayerCommand::execute(){ try{ - if (abort == true) { if (calledHelp) { return 0; } return 2; } - + for (int s = 0; s < fastaFileNames.size(); s++) { m->mothurOut("Checking sequences from " + fastaFileNames[s] + " ..." ); m->mothurOutEndLine(); @@ -384,7 +464,7 @@ int ChimeraSlayerCommand::execute(){ map priority = sortFastaFile(fastaFileNames[s], nameFile); m->mothurOut("Done."); m->mothurOutEndLine(); - if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } return 0; } + if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; } chimera = new ChimeraSlayer(fastaFileNames[s], templatefile, trim, priority, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign); } @@ -394,7 +474,7 @@ int ChimeraSlayerCommand::execute(){ string accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "slayer.accnos"; string trimFastaFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + "slayer.fasta"; - if (m->control_pressed) { delete chimera; for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } return 0; } + if (m->control_pressed) { delete chimera; for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; } if (chimera->getUnaligned()) { m->mothurOut("Your template sequences are different lengths, please correct."); m->mothurOutEndLine(); @@ -437,7 +517,7 @@ int ChimeraSlayerCommand::execute(){ MPI_File_open(MPI_COMM_WORLD, outAccnosFilename, outMode, MPI_INFO_NULL, &outMPIAccnos); if (trim) { MPI_File_open(MPI_COMM_WORLD, outFastaFilename, outMode, MPI_INFO_NULL, &outMPIFasta); } - if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } delete chimera; return 0; } + if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } delete chimera; return 0; } if (pid == 0) { //you are the root process m->mothurOutEndLine(); @@ -476,7 +556,17 @@ int ChimeraSlayerCommand::execute(){ //do your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, outMPIFasta, MPIPos); - if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } remove(outputFileName.c_str()); remove(accnosFileName.c_str()); delete chimera; return 0; } + int numNoParents = chimera->getNumNoParents(); + int temp; + for(int i = 1; i < processors; i++) { + MPI_Recv(&temp, 1, MPI_INT, 1, tag, MPI_COMM_WORLD, &status); + numNoParents += temp; + } + + + if (numSeqs == numNoParents) { m->mothurOut("[WARNING]: megablast returned 0 potential parents for all your sequences. This could be due to formatdb.exe not being setup properly, please check formatdb.log for errors."); m->mothurOutEndLine(); } + + if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } m->mothurRemove(outputFileName); m->mothurRemove(accnosFileName); delete chimera; return 0; } }else{ //you are a child process if (templatefile != "self") { //if template=self we can only use 1 processor @@ -491,8 +581,11 @@ int ChimeraSlayerCommand::execute(){ //do your part driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, outMPIFasta, MPIPos); + + int numNoParents = chimera->getNumNoParents(); + MPI_Send(&numNoParents, 1, MPI_INT, 0, tag, MPI_COMM_WORLD); - if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { remove(outputNames[j].c_str()); } delete chimera; return 0; } + if (m->control_pressed) { outputTypes.clear(); MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } delete chimera; return 0; } } } @@ -523,7 +616,10 @@ int ChimeraSlayerCommand::execute(){ if(processors == 1){ numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName, trimFastaFileName); - if (m->control_pressed) { outputTypes.clear(); if (trim) { remove(trimFastaFileName.c_str()); } 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]; } lines.clear(); delete chimera; return 0; } + int numNoParents = chimera->getNumNoParents(); + if (numNoParents == numSeqs) { m->mothurOut("[WARNING]: megablast returned 0 potential parents for all your sequences. This could be due to formatdb.exe not being setup properly, please check formatdb.log for errors."); m->mothurOutEndLine(); } + + if (m->control_pressed) { outputTypes.clear(); if (trim) { m->mothurRemove(trimFastaFileName); } 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]; } lines.clear(); delete chimera; return 0; } }else{ processIDS.resize(0); @@ -537,35 +633,39 @@ int ChimeraSlayerCommand::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 (trim) { for(int i=1;iappendFiles((trimFastaFileName + toString(processIDS[i]) + ".temp"), trimFastaFileName); - remove((trimFastaFileName + toString(processIDS[i]) + ".temp").c_str()); + m->mothurRemove((trimFastaFileName + toString(processIDS[i]) + ".temp")); } } - if (m->control_pressed) { outputTypes.clear(); if (trim) { remove(trimFastaFileName.c_str()); } remove(outputFileName.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]; } lines.clear(); delete chimera; return 0; } + if (m->control_pressed) { outputTypes.clear(); if (trim) { m->mothurRemove(trimFastaFileName); } m->mothurRemove(outputFileName); 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]; } lines.clear(); delete chimera; return 0; } } #else numSeqs = driver(lines[0], outputFileName, fastaFileNames[s], accnosFileName, trimFastaFileName); - if (m->control_pressed) { outputTypes.clear(); if (trim) { remove(trimFastaFileName.c_str()); } 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]; } lines.clear(); delete chimera; return 0; } + int numNoParents = chimera->getNumNoParents(); + if (numNoParents == numSeqs) { m->mothurOut("[WARNING]: megablast returned 0 potential parents for all your sequences. This could be due to formatdb.exe not being setup properly, please check formatdb.log for errors."); m->mothurOutEndLine(); } + + + if (m->control_pressed) { outputTypes.clear(); if (trim) { m->mothurRemove(trimFastaFileName); } 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]; } 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 @@ -635,9 +735,8 @@ int ChimeraSlayerCommand::driver(linePair* filePos, string outputFName, string f Sequence* candidateSeq = new Sequence(inFASTA); m->gobble(inFASTA); string candidateAligned = candidateSeq->getAligned(); - + if (candidateSeq->getName() != "") { //incase there is a commented sequence at the end of a file - if (candidateSeq->getAligned().length() != templateSeqsLength) { m->mothurOut(candidateSeq->getName() + " is not the same length as the template sequences. Skipping."); m->mothurOutEndLine(); }else{ @@ -683,22 +782,21 @@ int ChimeraSlayerCommand::driver(linePair* filePos, string outputFName, string f data_results rightResults = chimera->getResults(); //if either piece is chimeric then report - Sequence* trimmed = chimera->print(out, out2, leftResults, rightResults); - if (trim) { trimmed->printSequence(out3); delete trimmed; } + Sequence trimmed = chimera->print(out, out2, leftResults, rightResults); + if (trim) { trimmed.printSequence(out3); } delete left; delete right; }else { //already chimeric //print results - Sequence* trimmed = chimera->print(out, out2); - if (trim) { trimmed->printSequence(out3); delete trimmed; } + Sequence trimmed = chimera->print(out, out2); + if (trim) { trimmed.printSequence(out3); } } } count++; } - delete candidateSeq; #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) unsigned long int pos = inFASTA.tellg(); @@ -707,6 +805,7 @@ int ChimeraSlayerCommand::driver(linePair* filePos, string outputFName, string f if (inFASTA.eof()) { break; } #endif + delete candidateSeq; //report progress if((count) % 100 == 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine(); } } @@ -799,10 +898,9 @@ int ChimeraSlayerCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_Fil data_results rightResults = chimera->getResults(); //if either piece is chimeric then report - Sequence* trimmed = chimera->print(outMPI, outAccMPI, leftResults, rightResults); + Sequence trimmed = chimera->print(outMPI, outAccMPI, leftResults, rightResults); if (trim) { - string outputString = ">" + trimmed->getName() + "\n" + trimmed->getAligned() + "\n"; - delete trimmed; + string outputString = ">" + trimmed.getName() + "\n" + trimmed.getAligned() + "\n"; //write to accnos file int length = outputString.length(); @@ -817,11 +915,10 @@ int ChimeraSlayerCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_Fil }else { //print results - Sequence* trimmed = chimera->print(outMPI, outAccMPI); + Sequence trimmed = chimera->print(outMPI, outAccMPI); if (trim) { - string outputString = ">" + trimmed->getName() + "\n" + trimmed->getAligned() + "\n"; - delete trimmed; + string outputString = ">" + trimmed.getName() + "\n" + trimmed.getAligned() + "\n"; //write to accnos file int length = outputString.length(); @@ -875,9 +972,8 @@ int ChimeraSlayerCommand::createProcesses(string outputFileName, string filename ofstream out; string tempFile = outputFileName + toString(getpid()) + ".num.temp"; m->openOutputFile(tempFile, out); - out << num << endl; + out << num << '\t' << chimera->getNumNoParents() << endl; out.close(); - exit(0); }else { m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine(); @@ -892,14 +988,17 @@ int ChimeraSlayerCommand::createProcesses(string outputFileName, string filename wait(&temp); } + int numNoParents = 0; for (int i = 0; i < processIDS.size(); i++) { ifstream in; 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()); + if (!in.eof()) { int tempNum = 0; int tempNumParents = 0; in >> tempNum >> tempNumParents; num += tempNum; numNoParents += tempNumParents; } + in.close(); m->mothurRemove(tempFile); } + if (num == numNoParents) { m->mothurOut("[WARNING]: megablast returned 0 potential parents for all your sequences. This could be due to formatdb.exe not being setup properly, please check formatdb.log for errors."); m->mothurOutEndLine(); } + return num; #endif }