X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=consensusseqscommand.cpp;h=e32867f3737b27bc3b9e929a73f142fe564d48c4;hb=19fcbbdba99658f5eca244803280f9ee7f9f6607;hp=e81627df1be2e26b2c40d6322416d96d9bdcf893;hpb=e150b0b0664caec517485ee6d69dcdade6dcae77;p=mothur.git diff --git a/consensusseqscommand.cpp b/consensusseqscommand.cpp index e81627d..e32867f 100644 --- a/consensusseqscommand.cpp +++ b/consensusseqscommand.cpp @@ -18,6 +18,7 @@ vector ConsensusSeqsCommand::setParameters(){ CommandParameter pname("name", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pname); CommandParameter plist("list", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(plist); CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + CommandParameter pcutoff("cutoff", "Number", "", "100", "", "", "",false,false); parameters.push_back(pcutoff); CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); @@ -35,11 +36,12 @@ string ConsensusSeqsCommand::getHelpString(){ try { string helpString = ""; helpString += "The consensus.seqs command can be used in 2 ways: create a consensus sequence from a fastafile, or with a listfile create a consensus sequence for each otu. Sequences must be aligned.\n"; - helpString += "The consensus.seqs command parameters are fasta, list, name and label.\n"; + helpString += "The consensus.seqs command parameters are fasta, list, name, cutoff and label.\n"; helpString += "The fasta parameter allows you to enter the fasta file containing your sequences, and is required, unless you have a valid current fasta file. \n"; helpString += "The list parameter allows you to enter a your list file. \n"; helpString += "The name parameter allows you to enter a names file associated with the fasta file. \n"; helpString += "The label parameter allows you to select what distance levels you would like output files for, and are separated by dashes.\n"; + helpString += "The cutoff parameter allows you set a percentage of sequences that support the base. For example: cutoff=97 would only return a sequence that only showed ambiguities for bases that were not supported by at least 97% of sequences.\n"; helpString += "The consensus.seqs command should be in the following format: \n"; helpString += "consensus.seqs(fasta=yourFastaFile, list=yourListFile) \n"; helpString += "Example: consensus.seqs(fasta=abrecovery.align, list=abrecovery.fn.list) \n"; @@ -137,15 +139,17 @@ ConsensusSeqsCommand::ConsensusSeqsCommand(string option) { fastafile = m->getFastaFile(); if (fastafile != "") { m->mothurOut("Using " + fastafile + " 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->setFastaFile(fastafile); } namefile = validParameter.validFile(parameters, "name", true); if (namefile == "not open") { abort = true; } - else if (namefile == "not found") { namefile = ""; } + else if (namefile == "not found") { namefile = ""; } + else { m->setNameFile(namefile); } listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } + else { m->setListFile(listfile); } label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } @@ -154,6 +158,9 @@ ConsensusSeqsCommand::ConsensusSeqsCommand(string option) { else { allLines = 1; } } + string temp = validParameter.validFile(parameters, "cutoff", false); if (temp == "not found") { temp = "100"; } + convert(temp, cutoff); + //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 = m->hasPath(fastafile); } @@ -199,7 +206,7 @@ int ConsensusSeqsCommand::execute(){ int seqLength = 0; for (map::iterator it = nameMap.begin(); it != nameMap.end(); it++) { - if (m->control_pressed) { outSummary.close(); outFasta.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { outSummary.close(); outFasta.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } string seq = fastaMap[it->second]; seqs.push_back(seq); @@ -216,7 +223,7 @@ int ConsensusSeqsCommand::execute(){ //get counts for (int j = 0; j < seqLength; j++) { - if (m->control_pressed) { outSummary.close(); outFasta.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { outSummary.close(); outFasta.close(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } vector counts; counts.resize(5, 0); //A,T,G,C,Gap int numDots = 0; @@ -234,7 +241,7 @@ int ConsensusSeqsCommand::execute(){ } char conBase = '.'; - if (numDots != seqs.size()) { conBase = getBase(counts); } + if (numDots != seqs.size()) { conBase = getBase(counts, seqs.size()); } consSeq += conBase; @@ -269,7 +276,7 @@ int ConsensusSeqsCommand::execute(){ //as long as you are not at the end of the file or done wih the lines you want while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete list; delete input; return 0; } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete list; delete input; return 0; } if(allLines == 1 || labels.count(list->getLabel()) == 1){ @@ -307,7 +314,7 @@ int ConsensusSeqsCommand::execute(){ } - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } if (list != NULL) { delete list; } delete input; return 0; } + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } if (list != NULL) { delete list; } delete input; return 0; } //output error messages about any remaining user labels set::iterator it; @@ -477,7 +484,7 @@ string ConsensusSeqsCommand::getConsSeq(string bin, ofstream& outSummary, string } char conBase = '.'; - if (numDots != seqs.size()) { conBase = getBase(counts); } + if (numDots != seqs.size()) { conBase = getBase(counts, seqs.size()); } consSeq += conBase; @@ -503,7 +510,7 @@ string ConsensusSeqsCommand::getConsSeq(string bin, ofstream& outSummary, string } //*************************************************************************************************************** -char ConsensusSeqsCommand::getBase(vector counts){ //A,T,G,C,Gap +char ConsensusSeqsCommand::getBase(vector counts, int size){ //A,T,G,C,Gap try{ /* A = adenine * C = cytosine @@ -523,6 +530,14 @@ char ConsensusSeqsCommand::getBase(vector counts){ //A,T,G,C,Gap char conBase = 'N'; + //zero out counts that don't make the cutoff + float percentage = (100.0 - cutoff) / 100.0; + int zeroCutoff = percentage * size; + + for (int i = 0; i < counts.size(); i++) { + if (counts[i] < zeroCutoff) { counts[i] = 0; } + } + //any if ((counts[0] != 0) && (counts[1] != 0) && (counts[2] != 0) && (counts[3] != 0) && (counts[4] != 0)) { conBase = 'n'; } //any no gap @@ -585,6 +600,8 @@ char ConsensusSeqsCommand::getBase(vector counts){ //A,T,G,C,Gap else if ((counts[0] == 0) && (counts[1] == 0) && (counts[2] == 0) && (counts[3] != 0) && (counts[4] == 0)) { conBase = 'C'; } //only gap else if ((counts[0] == 0) && (counts[1] == 0) && (counts[2] == 0) && (counts[3] == 0) && (counts[4] != 0)) { conBase = '-'; } + //cutoff removed all counts + else if ((counts[0] == 0) && (counts[1] == 0) && (counts[2] == 0) && (counts[3] == 0) && (counts[4] == 0)) { conBase = 'N'; } else{ m->mothurOut("[ERROR]: cannot find consensus base."); m->mothurOutEndLine(); } return conBase;