X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chimeraslayercommand.cpp;h=7dfebb06b8ff229639ced1b7fb1aec472cd9a689;hb=2405cc589aaaf0c44809a48fe98d3b96863dac0b;hp=f6baa0a2074d75e01c73eeb50cae1f77f291ee20;hpb=1e4552ceb0f67f70a147d1cdca7244b62ac115ab;p=mothur.git diff --git a/chimeraslayercommand.cpp b/chimeraslayercommand.cpp index f6baa0a..7dfebb0 100644 --- a/chimeraslayercommand.cpp +++ b/chimeraslayercommand.cpp @@ -23,15 +23,15 @@ 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-distance", "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); @@ -53,7 +53,7 @@ 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 += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amazon.fasta \n"; @@ -72,13 +72,13 @@ 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 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 false. \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"; @@ -148,47 +148,63 @@ 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--; + } } } @@ -206,47 +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--; } } @@ -304,13 +336,13 @@ 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"; } @@ -321,7 +353,7 @@ ChimeraSlayerCommand::ChimeraSlayerCommand(string option) { 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"; } @@ -342,7 +374,6 @@ 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++) { @@ -635,7 +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) { @@ -698,15 +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(); } }