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 pblastlocation("blastlocation", "String", "", "", "", "", "",false,false); parameters.push_back(pblastlocation);
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);
string helpString = "";
helpString += "The chimera.slayer command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n";
helpString += "This command was modeled after the chimeraSlayer written by the Broad Institute.\n";
- helpString += "The chimera.slayer command parameters are fasta, name, template, processors, trim, ksize, window, match, mismatch, divergence. minsim, mincov, minbs, minsnp, parents, search, iters, increment, numwanted, and realign.\n";
+ helpString += "The chimera.slayer command parameters are fasta, name, template, processors, trim, ksize, window, match, mismatch, divergence. minsim, mincov, minbs, minsnp, parents, search, iters, increment, numwanted, blastlocation 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 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 minsnp parameter allows you to specify percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default: 10) \n";
helpString += "The search parameter allows you to specify search method for finding the closest parent. Choices are blast, and kmer, default blast. \n";
helpString += "The realign parameter allows you to realign the query to the potential parents. Choices are true or false, default true. \n";
+ helpString += "The blastlocation parameter allows you to specify the location of your blast executable. By default mothur will look in ./blast/bin relative to mothur's executable. \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";
temp = validParameter.validFile(parameters, "numwanted", false); if (temp == "not found") { temp = "15"; }
convert(temp, numwanted);
+
+ blastlocation = validParameter.validFile(parameters, "blastlocation", false);
+ if (blastlocation == "not found") { blastlocation = ""; }
+ else {
+ //add / to name if needed
+ string lastChar = blastlocation.substr(blastlocation.length()-1);
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+ if (lastChar != "/") { blastlocation += "/"; }
+#else
+ if (lastChar != "\\") { blastlocation += "\\"; }
+#endif
+ blastlocation = m->getFullPathName(blastlocation);
+ string formatdbCommand = "";
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+ formatdbCommand = blastlocation + "formatdb";
+#else
+ formatdbCommand = blastlocation + "formatdb.exe";
+#endif
+
+ //test to make sure formatdb exists
+ ifstream in;
+ formatdbCommand = m->getFullPathName(formatdbCommand);
+ int ableToOpen = m->openInputFile(formatdbCommand, in, "no error"); in.close();
+ if(ableToOpen == 1) { m->mothurOut("[ERROR]: " + formatdbCommand + " file does not exist. mothur requires formatdb.exe to run chimera.slayer."); m->mothurOutEndLine(); abort = true; }
+
+ string blastCommand = "";
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+ blastCommand = blastlocation + "megablast";
+#else
+ blastCommand = blastlocation + "megablast.exe";
+#endif
+ //test to make sure formatdb exists
+ ifstream in2;
+ blastCommand = m->getFullPathName(blastCommand);
+ ableToOpen = m->openInputFile(blastCommand, in2, "no error"); in2.close();
+ if(ableToOpen == 1) { m->mothurOut("[ERROR]: " + blastCommand + " file does not exist. mothur requires blastall.exe to run chimera.slayer."); m->mothurOutEndLine(); abort = true; }
+ }
if ((search != "blast") && (search != "kmer")) { m->mothurOut(search + " is not a valid search."); m->mothurOutEndLine(); abort = true; }
int start = time(NULL);
if (templatefile != "self") { //you want to run slayer with a refernce template
- chimera = new ChimeraSlayer(fastaFileNames[s], templatefile, trim, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign);
+ chimera = new ChimeraSlayer(fastaFileNames[s], templatefile, trim, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign, blastlocation);
}else {
if (processors != 1) { m->mothurOut("When using template=self, mothur can only use 1 processor, continuing."); m->mothurOutEndLine(); processors = 1; }
string nameFile = "";
map<string, int> 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);
+ chimera = new ChimeraSlayer(fastaFileNames[s], templatefile, trim, priority, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign, blastlocation);
}
if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]); }//if user entered a file with a path then preserve it
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();
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();
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++) { remove(outputNames[j].c_str()); } remove(outputFileName.c_str()); remove(accnosFileName.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]); } 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
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; }
}
}
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) { 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; }
+ 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);
//append output files
for(int i=1;i<processors;i++){
m->appendFiles((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;i<processors;i++){
m->appendFiles((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;i<processors;i++){
m->appendFiles((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
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) { 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; }
+ 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
string tempFile = outputFileName + toString(processIDS[i]) + ".num.temp";
m->openInputFile(tempFile, in);
if (!in.eof()) { int tempNum = 0; int tempNumParents = 0; in >> tempNum >> tempNumParents; num += tempNum; numNoParents += tempNumParents; }
- in.close(); remove(tempFile.c_str());
+ 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(); }