From: westcott Date: Tue, 7 Dec 2010 17:14:58 +0000 (+0000) Subject: consensus.seqs can now find a consensus on a whole fasta file without needing a listfile X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=commitdiff_plain;h=fd5f17bcbe5fadab2c525f3d1fcfd1d79a60ae72 consensus.seqs can now find a consensus on a whole fasta file without needing a listfile --- diff --git a/consensusseqscommand.cpp b/consensusseqscommand.cpp index 84519b8..9c447c2 100644 --- a/consensusseqscommand.cpp +++ b/consensusseqscommand.cpp @@ -135,7 +135,7 @@ ConsensusSeqsCommand::ConsensusSeqsCommand(string option) { listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } - else if (listfile == "not found") { listfile = ""; m->mothurOut("list is a required parameter for the consensus.seqs command."); m->mothurOutEndLine(); abort = true; } + else if (listfile == "not found") { listfile = ""; } label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } @@ -158,7 +158,7 @@ ConsensusSeqsCommand::ConsensusSeqsCommand(string option) { void ConsensusSeqsCommand::help(){ try { - m->mothurOut("The consensus.seqs command reads a fastafile and listfile and creates a consensus sequence for each otu. Sequences must be aligned.\n"); + m->mothurOut("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"); m->mothurOut("The consensus.seqs command parameters are fasta, list, name and label.\n"); m->mothurOut("The fasta parameter allows you to enter the fasta file containing your sequences, and is required. \n"); m->mothurOut("The list parameter allows you to enter a your list file. \n"); @@ -194,85 +194,176 @@ int ConsensusSeqsCommand::execute(){ if (m->control_pressed) { return 0; } - InputData* input = new InputData(listfile, "list"); - ListVector* list = input->getListVector(); - - string lastLabel = list->getLabel(); - set processedLabels; - set userLabels = labels; - - //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(allLines == 1 || labels.count(list->getLabel()) == 1){ - m->mothurOut(list->getLabel()); m->mothurOutEndLine(); + if (listfile == "") { + + ofstream outSummary; + string outputSummaryFile = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "cons.summary"; + m->openOutputFile(outputSummaryFile, outSummary); + outSummary.setf(ios::fixed, ios::floatfield); outSummary.setf(ios::showpoint); + outputNames.push_back(outputSummaryFile); outputTypes["summary"].push_back(outputSummaryFile); + + ofstream outFasta; + string outputFastaFile = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "cons.fasta"; + m->openOutputFile(outputFastaFile, outFasta); + outputNames.push_back(outputFastaFile); outputTypes["fasta"].push_back(outputFastaFile); + + vector seqs; + int seqLength = 0; + for (map::iterator it = nameMap.begin(); it != nameMap.end(); it++) { - processList(list); + if (m->control_pressed) { outSummary.close(); outFasta.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - processedLabels.insert(list->getLabel()); - userLabels.erase(list->getLabel()); + string seq = fastaMap[it->second]; + seqs.push_back(seq); + + if (seqLength == 0) { seqLength = seq.length(); } + else if (seqLength != seq.length()) { m->mothurOut("[ERROR]: sequence are not the same length, please correct."); m->mothurOutEndLine(); m->control_pressed = true; } + } - if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { - string saveLabel = list->getLabel(); + vector< vector > percentages; percentages.resize(5); + for (int j = 0; j < percentages.size(); j++) { percentages[j].resize(seqLength, 0.0); } + + string consSeq = ""; + //get counts + for (int j = 0; j < seqLength; j++) { - delete list; + if (m->control_pressed) { outSummary.close(); outFasta.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } - list = input->getListVector(lastLabel); - m->mothurOut(list->getLabel()); m->mothurOutEndLine(); + vector counts; counts.resize(5, 0); //A,T,G,C,Gap + int numDots = 0; - processList(list); + for (int i = 0; i < seqs.size(); i++) { + + if (seqs[i][j] == '.') { numDots++; } + + char base = toupper(seqs[i][j]); + if (base == 'A') { counts[0]++; } + else if (base == 'T') { counts[1]++; } + else if (base == 'G') { counts[2]++; } + else if (base == 'C') { counts[3]++; } + else { counts[4]++; } + } + + char conBase = '.'; + if (numDots != seqs.size()) { conBase = getBase(counts); } - processedLabels.insert(list->getLabel()); - userLabels.erase(list->getLabel()); + consSeq += conBase; + + percentages[0][j] = counts[0] / (float) seqs.size(); + percentages[1][j] = counts[1] / (float) seqs.size(); + percentages[2][j] = counts[2] / (float) seqs.size(); + percentages[3][j] = counts[3] / (float) seqs.size(); + percentages[4][j] = counts[4] / (float) seqs.size(); - //restore real lastlabel to save below - list->setLabel(saveLabel); } - lastLabel = list->getLabel(); + outSummary << "A" << '\t'; + for (int j = 0; j < seqLength; j++) { outSummary << percentages[0][j] << '\t'; } + outSummary << endl; + outSummary << "T" << '\t'; + for (int j = 0; j < seqLength; j++) { outSummary << percentages[1][j] << '\t'; } + outSummary << endl; + outSummary << "G" << '\t'; + for (int j = 0; j < seqLength; j++) { outSummary << percentages[2][j] << '\t'; } + outSummary << endl; + outSummary << "C" << '\t'; + for (int j = 0; j < seqLength; j++) { outSummary << percentages[3][j] << '\t'; } + outSummary << endl; + outSummary << "Gap" << '\t'; + for (int j = 0; j < seqLength; j++) { outSummary << percentages[4][j] << '\t'; } + outSummary << endl; - delete list; list = NULL; + + outFasta << ">conseq" << endl << consSeq << endl; + + outSummary.close(); outFasta.close(); - //get next line to process - list = input->getListVector(); - } - - - 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; } - //output error messages about any remaining user labels - set::iterator it; - bool needToRun = false; - for (it = userLabels.begin(); it != userLabels.end(); it++) { - m->mothurOut("Your file does not include the label " + *it); - if (processedLabels.count(lastLabel) != 1) { - m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); - needToRun = true; - }else { - m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + }else { + + + InputData* input = new InputData(listfile, "list"); + ListVector* list = input->getListVector(); + + string lastLabel = list->getLabel(); + set processedLabels; + set userLabels = labels; + + //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(allLines == 1 || labels.count(list->getLabel()) == 1){ + + m->mothurOut(list->getLabel()); m->mothurOutEndLine(); + + processList(list); + + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + } + + if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = list->getLabel(); + + delete list; + + list = input->getListVector(lastLabel); + m->mothurOut(list->getLabel()); m->mothurOutEndLine(); + + processList(list); + + processedLabels.insert(list->getLabel()); + userLabels.erase(list->getLabel()); + + //restore real lastlabel to save below + list->setLabel(saveLabel); + } + + lastLabel = list->getLabel(); + + delete list; list = NULL; + + //get next line to process + list = input->getListVector(); } - } - - //run last label if you need to - if (needToRun == true) { - if (list != NULL) { delete list; } - list = input->getListVector(lastLabel); - m->mothurOut(list->getLabel()); m->mothurOutEndLine(); + 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; } - processList(list); + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); + needToRun = true; + }else { + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + } + } - delete list; list = NULL; + //run last label if you need to + if (needToRun == true) { + if (list != NULL) { delete list; } + + list = input->getListVector(lastLabel); + + m->mothurOut(list->getLabel()); m->mothurOutEndLine(); + + processList(list); + + delete list; list = NULL; + } + + if (list != NULL) { delete list; } + delete input; } - if (list != NULL) { delete list; } - delete input; - m->mothurOutEndLine(); m->mothurOut("Output File Name: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } diff --git a/mothur b/mothur index dd02cf2..f98378a 100755 Binary files a/mothur and b/mothur differ diff --git a/removeotuscommand.cpp b/removeotuscommand.cpp index 6828c72..0e7d302 100644 --- a/removeotuscommand.cpp +++ b/removeotuscommand.cpp @@ -367,11 +367,17 @@ int RemoveOtusCommand::processList(ListVector*& list, GroupMap*& groupMap, ofstr if (m->inUsersGroups(group, Groups)) { removeBin = true; } groupFileOutput += individual + "\t" + group + "\n"; - //if there are no sequences from the groups we want to remove in this bin add to new list, output to groupfile - newList.push_back(binnames); - outGroup << groupFileOutput; + if (!removeBin) { + //if there are no sequences from the groups we want to remove in this bin add to new list, output to groupfile + newList.push_back(binnames); + outGroup << groupFileOutput; + }else { + numOtus++; + } + }else { numOtus++; } + } //print new listvector diff --git a/subsamplecommand.cpp b/subsamplecommand.cpp index 7a857e8..ac45d2f 100644 --- a/subsamplecommand.cpp +++ b/subsamplecommand.cpp @@ -245,6 +245,7 @@ void SubSampleCommand::help(){ try { m->mothurOut("The sub.sample command is designed to be used as a way to normalize your data, or create a smaller set from your original set.\n"); m->mothurOut("The sub.sample command parameters are fasta, name, list, group, rabund, sabund, shared, groups, size and label. You must provide a fasta, list, sabund, rabund or shared file as an input file.\n"); + m->mothurOut("The namefile is only used with the fasta file, not with the listfile, because the list file should contain all sequences.\n"); m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like included. The group names are separated by dashes.\n"); m->mothurOut("The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n"); m->mothurOut("The size parameter allows you indicate the size of your subsample.\n"); diff --git a/trimseqscommand.cpp b/trimseqscommand.cpp index 3c0d378..7ee5c99 100644 --- a/trimseqscommand.cpp +++ b/trimseqscommand.cpp @@ -337,7 +337,7 @@ int TrimSeqsCommand::execute(){ outputNames.push_back(groupFile); outputTypes["group"].push_back(groupFile); getOligos(fastaFileNames, qualFileNames); } - cout << fastaFileNames.size() << '\t' << qualFileNames.size() << endl; + vector fastaFilePos; vector qFilePos; @@ -362,7 +362,6 @@ int TrimSeqsCommand::execute(){ if (m->control_pressed) { return 0; } for(int i=0;iisBlank(fastaFileNames[i])) { remove(fastaFileNames[i].c_str()); } else if (filesToRemove.count(fastaFileNames[i]) > 0) { remove(fastaFileNames[i].c_str()); } @@ -397,7 +396,6 @@ int TrimSeqsCommand::execute(){ if(qFileName != ""){ for(int i=0;iisBlank(qualFileNames[i])) { remove(qualFileNames[i].c_str()); } else if (filesToRemove.count(qualFileNames[i]) > 0) { remove(qualFileNames[i].c_str()); } else { @@ -860,7 +858,7 @@ void TrimSeqsCommand::getOligos(vector& outFASTAVec, vector& out //int indexPrimer = 0; while(!inOligos.eof()){ - inOligos >> type; + inOligos >> type; m->gobble(inOligos); if(type[0] == '#'){ while (!inOligos.eof()) { char c = inOligos.get(); if (c == 10 || c == 13){ break; } } // get rest of line if there's any crap there @@ -891,29 +889,29 @@ void TrimSeqsCommand::getOligos(vector& outFASTAVec, vector& out map::iterator itPrime = primers.find(oligo); if (itPrime != primers.end()) { m->mothurOut("primer " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); } - primers[oligo]=index; index++; - groupVector.push_back(group); + primers[oligo]=index; index++; + groupVector.push_back(group); - if(allFiles){ - outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); - if(qFileName != ""){ - outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); - } - if (group == "") { //if there is not a group for this primer, then this file will not get written to, but we add it to keep the indexes correct - filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); + if(allFiles){ + outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); if(qFileName != ""){ - filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + } + if (group == "") { //if there is not a group for this primer, then this file will not get written to, but we add it to keep the indexes correct + filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); + if(qFileName != ""){ + filesToRemove.insert((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + } + }else { + outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); + outputTypes["fasta"].push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); + if(qFileName != ""){ + outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + } } - }else { - outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); - outputTypes["fasta"].push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); - if(qFileName != ""){ - outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); - outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); - } } - } - + } else if(type == "REVERSE"){ Sequence oligoRC("reverse", oligo); @@ -927,19 +925,20 @@ void TrimSeqsCommand::getOligos(vector& outFASTAVec, vector& out map::iterator itBar = barcodes.find(oligo); if (itBar != barcodes.end()) { m->mothurOut("barcode " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); } - barcodes[oligo]=index; index++; - groupVector.push_back(group); + barcodes[oligo]=index; index++; + groupVector.push_back(group); + + if(allFiles){ + outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); + outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); + outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); + if(qFileName != ""){ + outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); + } + } - if(allFiles){ - outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); - outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); - outFASTAVec.push_back((outputDir + m->getRootName(m->getSimpleName(fastaFile)) + group + ".fasta")); - if(qFileName != ""){ - outQualVec.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); - outputNames.push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); - outputTypes["qual"].push_back((outputDir + m->getRootName(m->getSimpleName(qFileName)) + group + ".qual")); - } - } }else{ m->mothurOut(type + " is not recognized as a valid type. Choices are forward, reverse, and barcode. Ignoring " + oligo + "."); m->mothurOutEndLine(); } } m->gobble(inOligos);