X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chimeraslayercommand.cpp;h=97edf1130be292c1495811a4a9c52acc77cde04b;hb=1cf188b912d6da8f2cd03dd71cecef664a699c1a;hp=9b4a87b6a45124d5e472952626207e82e1ebbb67;hpb=36a867cbd85d9c276d3c8d13f25a150bbbe2466b;p=mothur.git diff --git a/chimeraslayercommand.cpp b/chimeraslayercommand.cpp index 9b4a87b..97edf11 100644 --- a/chimeraslayercommand.cpp +++ b/chimeraslayercommand.cpp @@ -12,52 +12,96 @@ #include "deconvolutecommand.h" //********************************************************************************************************************** -vector ChimeraSlayerCommand::getValidParameters(){ +vector ChimeraSlayerCommand::setParameters(){ try { - string AlignArray[] = {"fasta", "processors","trim","split", "name","window", "include","template","numwanted", "ksize", "match","mismatch", - "divergence", "minsim","mincov","minbs", "minsnp","parents", "iters","outputdir","inputdir", "search","realign" }; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + 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 pwindow("window", "Number", "", "50", "", "", "",false,false); parameters.push_back(pwindow); + CommandParameter pksize("ksize", "Number", "", "7", "", "", "",false,false); parameters.push_back(pksize); + CommandParameter pmatch("match", "Number", "", "5.0", "", "", "",false,false); parameters.push_back(pmatch); + 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", "", "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 pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); + 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", "", "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); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } return myArray; } catch(exception& e) { - m->errorOut(e, "ChimeraSlayerCommand", "getValidParameters"); - exit(1); - } -} -//********************************************************************************************************************** -ChimeraSlayerCommand::ChimeraSlayerCommand(){ - try { - abort = true; calledHelp = true; - vector tempOutNames; - outputTypes["chimera"] = tempOutNames; - outputTypes["accnos"] = tempOutNames; - outputTypes["fasta"] = tempOutNames; - } - catch(exception& e) { - m->errorOut(e, "ChimeraSlayerCommand", "ChimeraSlayerCommand"); + m->errorOut(e, "ChimeraSlayerCommand", "setParameters"); exit(1); } } //********************************************************************************************************************** -vector ChimeraSlayerCommand::getRequiredParameters(){ +string ChimeraSlayerCommand::getHelpString(){ try { - string AlignArray[] = {"template","fasta"}; - vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); - return myArray; + 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 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 += "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"; +#ifdef USE_MPI + helpString += "When using MPI, the processors parameter is set to the number of MPI processes running. \n"; +#endif + helpString += "The trim parameter allows you to output a new fasta file containing your sequences with the chimeric ones trimmed to include only their longest piece, default=F. \n"; + helpString += "The split parameter allows you to check both pieces of non-chimeric sequence for chimeras, thus looking for trimeras and quadmeras. default=F. \n"; + helpString += "The window parameter allows you to specify the window size for searching for chimeras, default=50. \n"; + helpString += "The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default=5.\n"; + helpString += "The numwanted parameter allows you to specify how many sequences you would each query sequence compared with, default=15.\n"; + helpString += "The ksize parameter allows you to input kmersize, default is 7, used if search is kmer. \n"; + helpString += "The match parameter allows you to reward matched bases in blast search, default is 5. \n"; + 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=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: 10) \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 true. \n"; + 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"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n"; + return helpString; } catch(exception& e) { - m->errorOut(e, "ChimeraSlayerCommand", "getRequiredParameters"); + m->errorOut(e, "ChimeraSlayerCommand", "getHelpString"); exit(1); } } //********************************************************************************************************************** -vector ChimeraSlayerCommand::getRequiredFiles(){ +ChimeraSlayerCommand::ChimeraSlayerCommand(){ try { - vector myArray; - return myArray; + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["chimera"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + outputTypes["fasta"] = tempOutNames; } catch(exception& e) { - m->errorOut(e, "ChimeraSlayerCommand", "getRequiredFiles"); + m->errorOut(e, "ChimeraSlayerCommand", "ChimeraSlayerCommand"); exit(1); } } @@ -70,10 +114,7 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { if(option == "help") { help(); abort = true; calledHelp = true; } else { - //valid paramters for this command - string Array[] = {"fasta", "processors","name", "include","trim", "split","window", "template","numwanted", "ksize", "match","mismatch", - "divergence", "minsim","mincov","minbs", "minsnp","parents", "iters","outputdir","inputdir", "search","realign" }; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -97,53 +138,73 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", false); - if (fastafile == "not found") { fastafile = ""; m->mothurOut("[ERROR]: fasta is a required parameter for the chimera.slayer command."); m->mothurOutEndLine(); abort = true; } - else { + 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++) { - 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--; + } } } @@ -161,47 +222,63 @@ 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--; } - } - - 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--; } } @@ -216,27 +293,25 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { string path; - it = parameters.find("template"); + it = parameters.find("reference"); //user has given a template file if(it != parameters.end()){ if (it->second == "self") { templatefile = "self"; } else { path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { parameters["template"] = inputDir + it->second; } + if (path == "") { parameters["reference"] = inputDir + it->second; } - templatefile = validParameter.validFile(parameters, "template", true); + templatefile = validParameter.validFile(parameters, "reference", true); if (templatefile == "not open") { abort = true; } - else if (templatefile == "not found") { templatefile = ""; m->mothurOut("template is a required parameter for the chimera.slayer command."); m->mothurOutEndLine(); abort = true; } + else if (templatefile == "not found") { templatefile = ""; m->mothurOut("reference is a required parameter for the chimera.slayer command."); m->mothurOutEndLine(); abort = true; } } } - string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; } + string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } + m->setProcessors(temp); convert(temp, processors); - includeAbunds = validParameter.validFile(parameters, "include", false); if (includeAbunds == "not found") { includeAbunds = "greater"; } - if ((includeAbunds != "greater") && (includeAbunds != "greaterequal") && (includeAbunds != "all")) { includeAbunds = "greater"; m->mothurOut("Invalid include setting. options are greater, greaterequal or all. using greater."); m->mothurOutEndLine(); } - temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found") { temp = "7"; } convert(temp, ksize); @@ -261,24 +336,24 @@ 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"; } trim = m->isTrue(temp); - temp = validParameter.validFile(parameters, "split", false); if (temp == "not found") { temp = "f"; } + 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"; } - 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"; } @@ -295,59 +370,10 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { exit(1); } } -//********************************************************************************************************************** - -void ChimeraSlayerCommand::help(){ - try { - - m->mothurOut("The chimera.slayer command reads a fastafile and templatefile and outputs potentially chimeric sequences.\n"); - m->mothurOut("This command was modeled after the chimeraSlayer written by the Broad Institute.\n"); - m->mothurOut("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, - m->mothurOut("The fasta parameter allows you to enter the fasta file containing your potentially chimeric sequences, and is required. \n"); - m->mothurOut("The name parameter allows you to provide a name file, if you are using template=self. \n"); - m->mothurOut("You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amazon.fasta \n"); - m->mothurOut("The template parameter allows you to enter a template 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"); - 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 trim parameter allows you to output a new fasta file containing your sequences with the chimeric ones trimmed to include only their longest piece, default=F. \n"); - m->mothurOut("The split parameter allows you to check both pieces of non-chimeric sequence for chimeras, thus looking for trimeras and quadmeras. default=F. \n"); - m->mothurOut("The window parameter allows you to specify the window size for searching for chimeras, default=50. \n"); - m->mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default=5.\n"); - m->mothurOut("The numwanted parameter allows you to specify how many sequences you would each query sequence compared with, default=15.\n"); - m->mothurOut("The ksize parameter allows you to input kmersize, default is 7, used if search is kmer. \n"); - m->mothurOut("The match parameter allows you to reward matched bases in blast search, default is 5. \n"); - m->mothurOut("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"); - m->mothurOut("The mismatch parameter allows you to penalize mismatched bases in blast search, default is -4. \n"); - m->mothurOut("The divergence parameter allows you to set a cutoff for chimera determination, default is 1.007. \n"); - m->mothurOut("The iters parameter allows you to specify the number of bootstrap iters to do with the chimeraslayer method, default=100.\n"); - m->mothurOut("The minsim parameter allows you to specify a minimum similarity with the parent fragments, default=90. \n"); - m->mothurOut("The mincov parameter allows you to specify minimum coverage by closest matches found in template. Default is 70, meaning 70%. \n"); - m->mothurOut("The minbs parameter allows you to specify minimum bootstrap support for calling a sequence chimeric. Default is 90, meaning 90%. \n"); - m->mothurOut("The minsnp parameter allows you to specify percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default: 100) \n"); - m->mothurOut("The search parameter allows you to specify search method for finding the closest parent. Choices are distance, blast, and kmer, default distance. \n"); - m->mothurOut("The realign parameter allows you to realign the query to the potential parents. Choices are true or false, default false. \n"); - m->mothurOut("The chimera.slayer command should be in the following format: \n"); - m->mothurOut("chimera.slayer(fasta=yourFastaFile, template=yourTemplate, search=yourSearch) \n"); - m->mothurOut("Example: chimera.slayer(fasta=AD.align, template=core_set_aligned.imputed.fasta, search=kmer) \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, "ChimeraSlayerCommand", "help"); - exit(1); - } -} - -//*************************************************************************************************************** - -ChimeraSlayerCommand::~ChimeraSlayerCommand(){ /* do nothing */ } - //*************************************************************************************************************** int ChimeraSlayerCommand::execute(){ try{ - if (abort == true) { if (calledHelp) { return 0; } return 2; } for (int s = 0; s < fastaFileNames.size(); s++) { @@ -359,10 +385,11 @@ int ChimeraSlayerCommand::execute(){ 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); }else { + if (processors != 1) { m->mothurOut("When using template=self, mothur can only use 1 processor, continuing."); m->mothurOutEndLine(); processors = 1; } + string nameFile = ""; if (nameFileNames.size() != 0) { //you provided a namefile and we don't need to create one - chimera = new ChimeraSlayer(fastaFileNames[s], templatefile, trim, nameFileNames[s], search, includeAbunds, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign); + nameFile = nameFileNames[s]; }else { - m->mothurOutEndLine(); m->mothurOut("No namesfile given, running unique.seqs command to generate one."); m->mothurOutEndLine(); m->mothurOutEndLine(); //use unique.seqs to create new name and fastafile @@ -379,11 +406,18 @@ int ChimeraSlayerCommand::execute(){ m->mothurOut("/******************************************/"); m->mothurOutEndLine(); - string nameFile = filenames["name"][0]; + nameFile = filenames["name"][0]; fastaFileNames[s] = filenames["fasta"][0]; - - chimera = new ChimeraSlayer(fastaFileNames[s], templatefile, trim, nameFile, search, includeAbunds, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign); } + + //sort fastafile by abundance, returns new sorted fastafile name + m->mothurOut("Sorting fastafile according to abundance..."); cout.flush(); + 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; } + + chimera = new ChimeraSlayer(fastaFileNames[s], templatefile, trim, priority, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign); } if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]); }//if user entered a file with a path then preserve it @@ -453,36 +487,45 @@ int ChimeraSlayerCommand::execute(){ MPIPos = m->setFilePosFasta(fastaFileNames[s], numSeqs); //fills MPIPos, returns numSeqs - //send file positions to all processes - for(int i = 1; i < processors; i++) { - MPI_Send(&numSeqs, 1, MPI_INT, i, tag, MPI_COMM_WORLD); - MPI_Send(&MPIPos[0], (numSeqs+1), MPI_LONG, i, tag, MPI_COMM_WORLD); + if (templatefile != "self") { //if template=self we can only use 1 processor + //send file positions to all processes + for(int i = 1; i < processors; i++) { + MPI_Send(&numSeqs, 1, MPI_INT, i, tag, MPI_COMM_WORLD); + MPI_Send(&MPIPos[0], (numSeqs+1), MPI_LONG, i, tag, MPI_COMM_WORLD); + } } - //figure out how many sequences you have to align numSeqsPerProcessor = numSeqs / processors; int startIndex = pid * numSeqsPerProcessor; if(pid == (processors - 1)){ numSeqsPerProcessor = numSeqs - pid * numSeqsPerProcessor; } - + + if (templatefile == "self") { //if template=self we can only use 1 processor + startIndex = 0; + numSeqsPerProcessor = numSeqs; + } + //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; } }else{ //you are a child process - MPI_Recv(&numSeqs, 1, MPI_INT, 0, tag, MPI_COMM_WORLD, &status); - MPIPos.resize(numSeqs+1); - MPI_Recv(&MPIPos[0], (numSeqs+1), MPI_LONG, 0, tag, MPI_COMM_WORLD, &status); + if (templatefile != "self") { //if template=self we can only use 1 processor + MPI_Recv(&numSeqs, 1, MPI_INT, 0, tag, MPI_COMM_WORLD, &status); + MPIPos.resize(numSeqs+1); + MPI_Recv(&MPIPos[0], (numSeqs+1), MPI_LONG, 0, tag, MPI_COMM_WORLD, &status); - //figure out how many sequences you have to align - numSeqsPerProcessor = numSeqs / processors; - int startIndex = pid * numSeqsPerProcessor; - if(pid == (processors - 1)){ numSeqsPerProcessor = numSeqs - pid * numSeqsPerProcessor; } + //figure out how many sequences you have to align + numSeqsPerProcessor = numSeqs / processors; + int startIndex = pid * numSeqsPerProcessor; + if(pid == (processors - 1)){ numSeqsPerProcessor = numSeqs - pid * numSeqsPerProcessor; } - //do your part - driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, outMPIFasta, MPIPos); + //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()); } 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++) { remove(outputNames[j].c_str()); } delete chimera; return 0; } + + } } //close files @@ -623,7 +666,7 @@ 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) { @@ -686,15 +729,16 @@ int ChimeraSlayerCommand::driver(linePair* filePos, string outputFName, string f } count++; } - delete candidateSeq; #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) unsigned long int pos = inFASTA.tellg(); + //cout << candidateSeq->getName() << '\t' << pos << endl; if ((pos == -1) || (pos >= filePos->end)) { break; } #else if (inFASTA.eof()) { break; } #endif + delete candidateSeq; //report progress if((count) % 100 == 0){ m->mothurOut("Processing sequence: " + toString(count)); m->mothurOutEndLine(); } } @@ -935,6 +979,58 @@ int ChimeraSlayerCommand::divideInHalf(Sequence querySeq, string& leftQuery, str exit(1); } } +/**************************************************************************************************/ +map ChimeraSlayerCommand::sortFastaFile(string fastaFile, string nameFile) { + try { + map nameAbund; + + //read through fastafile and store info + map seqs; + ifstream in; + m->openInputFile(fastaFile, in); + + while (!in.eof()) { + + if (m->control_pressed) { in.close(); return nameAbund; } + + Sequence seq(in); m->gobble(in); + seqs[seq.getName()] = seq.getAligned(); + } + + in.close(); + + //read namefile + vector nameMapCount; + int error = m->readNames(nameFile, nameMapCount, seqs); + + if (m->control_pressed) { return nameAbund; } + + if (error == 1) { m->control_pressed = true; return nameAbund; } + if (seqs.size() != nameMapCount.size()) { m->mothurOut( "The number of sequences in your fastafile does not match the number of sequences in your namefile, aborting."); m->mothurOutEndLine(); m->control_pressed = true; return nameAbund; } + + sort(nameMapCount.begin(), nameMapCount.end(), compareSeqPriorityNodes); + + string newFasta = fastaFile + ".temp"; + ofstream out; + m->openOutputFile(newFasta, out); + + //print new file in order of + for (int i = 0; i < nameMapCount.size(); i++) { + out << ">" << nameMapCount[i].name << endl << nameMapCount[i].seq << endl; + nameAbund[nameMapCount[i].name] = nameMapCount[i].numIdentical; + } + out.close(); + + rename(newFasta.c_str(), fastaFile.c_str()); + + return nameAbund; + + } + catch(exception& e) { + m->errorOut(e, "ChimeraSlayerCommand", "sortFastaFile"); + exit(1); + } +} /**************************************************************************************************/