2 * binsequencecommand.cpp
5 * Created by Sarah Westcott on 4/3/09.
6 * Copyright 2009 Schloss Lab UMASS Amhers. All rights reserved.
10 #include "binsequencecommand.h"
12 //**********************************************************************************************************************
13 BinSeqCommand::BinSeqCommand(string option){
15 globaldata = GlobalData::getInstance();
21 //allow user to run help
22 if(option == "help") { help(); abort = true; }
25 //valid paramters for this command
26 string AlignArray[] = {"fasta","line","label","name", "group"};
27 vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
29 OptionParser parser(option);
30 map<string, string> parameters = parser.getParameters();
32 ValidParameters validParameter;
34 //check to make sure all parameters are valid for command
35 for (map<string, string>::iterator it = parameters.begin(); it != parameters.end(); it++) {
36 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
39 //make sure the user has already run the read.otu command
40 if (globaldata->getListFile() == "") { cout << "You must read a listfile before running the bin.seqs command." << endl; abort = true; }
43 //check for required parameters
44 fastafile = validParameter.validFile(parameters, "fasta", true);
45 if (fastafile == "not found") { cout << "fasta is a required parameter for the bin.seqs command." << endl; abort = true; }
46 else if (fastafile == "not open") { abort = true; }
48 //check for optional parameter and set defaults
49 // ...at some point should added some additional type checking...
50 line = validParameter.validFile(parameters, "line", false);
51 if (line == "not found") { line = ""; }
53 if(line != "all") { splitAtDash(line, lines); allLines = 0; }
54 else { allLines = 1; }
57 label = validParameter.validFile(parameters, "label", false);
58 if (label == "not found") { label = ""; }
60 if(label != "all") { splitAtDash(label, labels); allLines = 0; }
61 else { allLines = 1; }
64 //make sure user did not use both the line and label parameters
65 if ((line != "") && (label != "")) { cout << "You cannot use both the line and label parameters at the same time. " << endl; abort = true; }
66 //if the user has not specified any line or labels use the ones from read.otu
67 else if ((line == "") && (label == "")) {
68 allLines = globaldata->allLines;
69 labels = globaldata->labels;
70 lines = globaldata->lines;
73 namesfile = validParameter.validFile(parameters, "name", true);
74 if (namesfile == "not open") { abort = true; }
75 else if (namesfile == "not found") { namesfile = ""; }
77 groupfile = validParameter.validFile(parameters, "group", true);
78 if (groupfile == "not open") { abort = true; }
79 else if (groupfile == "not found") { groupfile = ""; }
82 // openInputFile(fastafile, in);
83 fasta = new FastaMap();
84 if (groupfile != "") {
85 groupMap = new GroupMap(groupfile);
93 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function BinSeqCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
97 cout << "An unknown error has occurred in the BinSeqCommand class function BinSeqCommand. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
101 //**********************************************************************************************************************
103 void BinSeqCommand::help(){
105 cout << "The bin.seqs command can only be executed after a successful read.otu command of a listfile." << "\n";
106 cout << "The bin.seqs command parameters are fasta, name, line, label and group. The fasta parameter is required, and you may not use line and label at the same time." << "\n";
107 cout << "The line and label allow you to select what distance levels you would like a output files created for, and are separated by dashes." << "\n";
108 cout << "The bin.seqs command should be in the following format: bin.seqs(fasta=yourFastaFile, name=yourNamesFile, group=yourGroupFile, line=yourLines, label=yourLabels)." << "\n";
109 cout << "Example bin.seqs(fasta=amazon.fasta, group=amazon.groups, line=1-3-5, name=amazon.names)." << "\n";
110 cout << "The default value for line and label are all lines in your inputfile." << "\n";
111 cout << "The bin.seqs command outputs a .fasta file for each distance you specify appending the OTU number to each name." << "\n";
112 cout << "If you provide a groupfile, then it also appends the sequences group to the name." << "\n";
113 cout << "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile)." << "\n" << "\n";
115 catch(exception& e) {
116 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
120 cout << "An unknown error has occurred in the BinSeqCommand class function help. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
127 //**********************************************************************************************************************
129 BinSeqCommand::~BinSeqCommand(){
130 //made new in execute
131 if (abort == false) {
132 delete input; globaldata->ginput = NULL;
134 globaldata->gListVector = NULL;
136 if (groupfile != "") { delete groupMap; globaldata->gGroupmap = NULL; }
140 //**********************************************************************************************************************
142 int BinSeqCommand::execute(){
144 if (abort == true) { return 0; }
150 fasta->readFastaFile(fastafile);
153 //set format to list so input can get listvector
154 // globaldata->setFormat("list");
156 //if user gave a namesfile then use it
157 if (namesfile != "") {
162 read = new ReadOTUFile(globaldata->getListFile());
163 read->read(&*globaldata);
165 input = globaldata->ginput;
166 list = globaldata->gListVector;
167 string lastLabel = list->getLabel();
169 //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
170 set<string> processedLabels;
171 set<string> userLabels = labels;
172 set<int> userLines = lines;
175 while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) {
177 if(allLines == 1 || lines.count(count) == 1 || labels.count(list->getLabel()) == 1){
179 error = process(list, count);
180 if (error == 1) { return 0; }
182 processedLabels.insert(list->getLabel());
183 userLabels.erase(list->getLabel());
184 userLines.erase(count);
187 if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) {
189 list = input->getListVector(lastLabel);
191 error = process(list, count);
192 if (error == 1) { return 0; }
194 processedLabels.insert(list->getLabel());
195 userLabels.erase(list->getLabel());
199 lastLabel = list->getLabel();
202 list = input->getListVector();
207 //output error messages about any remaining user labels
208 set<string>::iterator it;
209 bool needToRun = false;
210 for (it = userLabels.begin(); it != userLabels.end(); it++) {
211 cout << "Your file does not include the label "<< *it;
212 if (processedLabels.count(lastLabel) != 1) {
213 cout << ". I will use " << lastLabel << "." << endl;
216 cout << ". Please refer to " << lastLabel << "." << endl;
220 //run last line if you need to
221 if (needToRun == true) {
223 list = input->getListVector(lastLabel);
225 error = process(list, count);
226 if (error == 1) { return 0; }
233 catch(exception& e) {
234 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
238 cout << "An unknown error has occurred in the BinSeqCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
243 //**********************************************************************************************************************
244 void BinSeqCommand::readNamesFile() {
246 vector<string> dupNames;
247 openInputFile(namesfile, inNames);
249 string name, names, sequence;
252 inNames >> name; //read from first column A
253 inNames >> names; //read from second column A,B,C,D
257 //parse names into vector
258 splitAtComma(names, dupNames);
260 //store names in fasta map
261 sequence = fasta->getSequence(name);
262 for (int i = 0; i < dupNames.size(); i++) {
263 fasta->push_back(dupNames[i], sequence);
271 catch(exception& e) {
272 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
276 cout << "An unknown error has occurred in the BinSeqCommand class function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
280 //**********************************************************************************************************************
281 //return 1 if error, 0 otherwise
282 int BinSeqCommand::process(ListVector* list, int count) {
284 string binnames, name, sequence;
285 string outputFileName = getRootName(globaldata->getListFile()) + list->getLabel() + ".fasta";
286 openOutputFile(outputFileName, out);
288 cout << list->getLabel() << '\t' << count << endl;
290 //for each bin in the list vector
291 for (int i = 0; i < list->size(); i++) {
293 binnames = list->get(i);
294 while (binnames.find_first_of(',') != -1) {
295 name = binnames.substr(0,binnames.find_first_of(','));
296 binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
298 //do work for that name
299 sequence = fasta->getSequence(name);
300 if (sequence != "not found") {
301 //if you don't have groups
302 if (groupfile == "") {
303 name = name + "|" + toString(i+1);
304 out << ">" << name << endl;
305 out << sequence << endl;
306 }else {//if you do have groups
307 string group = groupMap->getGroup(name);
308 if (group == "not found") {
309 cout << name << " is missing from your group file. Please correct. " << endl;
310 remove(outputFileName.c_str());
313 name = name + "|" + group + "|" + toString(i+1);
314 out << ">" << name << endl;
315 out << sequence << endl;
319 cout << name << " is missing from your fasta or name file. Please correct. " << endl;
320 remove(outputFileName.c_str());
327 sequence = fasta->getSequence(binnames);
328 if (sequence != "not found") {
329 //if you don't have groups
330 if (groupfile == "") {
331 binnames = binnames + "|" + toString(i+1);
332 out << ">" << binnames << endl;
333 out << sequence << endl;
334 }else {//if you do have groups
335 string group = groupMap->getGroup(binnames);
336 if (group == "not found") {
337 cout << binnames << " is missing from your group file. Please correct. " << endl;
338 remove(outputFileName.c_str());
341 binnames = binnames + "|" + group + "|" + toString(i+1);
342 out << ">" << binnames << endl;
343 out << sequence << endl;
347 cout << binnames << " is missing from your fasta or name file. Please correct. " << endl;
348 remove(outputFileName.c_str());
357 catch(exception& e) {
358 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
362 cout << "An unknown error has occurred in the BinSeqCommand class function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
366 //**********************************************************************************************************************