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(in);
154 //set format to list so input can get listvector
155 // globaldata->setFormat("list");
157 //if user gave a namesfile then use it
158 if (namesfile != "") {
163 read = new ReadOTUFile(globaldata->getListFile());
164 read->read(&*globaldata);
166 input = globaldata->ginput;
167 list = globaldata->gListVector;
168 ListVector* lastList = list;
170 //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label.
171 set<string> processedLabels;
172 set<string> userLabels = labels;
173 set<int> userLines = lines;
176 while((list != NULL) && ((allLines == 1) || (userLabels.size() != 0) || (userLines.size() != 0))) {
178 if(allLines == 1 || lines.count(count) == 1 || labels.count(list->getLabel()) == 1){
180 error = process(list, count);
181 if (error == 1) { return 0; }
183 processedLabels.insert(list->getLabel());
184 userLabels.erase(list->getLabel());
185 userLines.erase(count);
188 if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastList->getLabel()) != 1)) {
190 error = process(lastList, count);
191 if (error == 1) { return 0; }
193 processedLabels.insert(lastList->getLabel());
194 userLabels.erase(lastList->getLabel());
198 if (count != 1) { delete lastList; }
201 list = input->getListVector();
206 //output error messages about any remaining user labels
207 set<string>::iterator it;
208 bool needToRun = false;
209 for (it = userLabels.begin(); it != userLabels.end(); it++) {
210 cout << "Your file does not include the label "<< *it;
211 if (processedLabels.count(lastList->getLabel()) != 1) {
212 cout << ". I will use " << lastList->getLabel() << "." << endl;
215 cout << ". Please refer to " << lastList->getLabel() << "." << endl;
219 //run last line if you need to
220 if (needToRun == true) {
221 error = process(lastList, count);
222 if (error == 1) { return 0; }
228 catch(exception& e) {
229 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
233 cout << "An unknown error has occurred in the BinSeqCommand class function execute. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
238 //**********************************************************************************************************************
239 void BinSeqCommand::readNamesFile() {
241 vector<string> dupNames;
242 openInputFile(namesfile, inNames);
244 string name, names, sequence;
247 inNames >> name; //read from first column A
248 inNames >> names; //read from second column A,B,C,D
252 //parse names into vector
253 splitAtComma(names, dupNames);
255 //store names in fasta map
256 sequence = fasta->getSequence(name);
257 for (int i = 0; i < dupNames.size(); i++) {
258 fasta->push_back(dupNames[i], sequence);
266 catch(exception& e) {
267 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
271 cout << "An unknown error has occurred in the BinSeqCommand class function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
275 //**********************************************************************************************************************
276 //return 1 if error, 0 otherwise
277 int BinSeqCommand::process(ListVector* list, int count) {
279 string binnames, name, sequence;
280 string outputFileName = getRootName(globaldata->getListFile()) + list->getLabel() + ".fasta";
281 openOutputFile(outputFileName, out);
283 cout << list->getLabel() << '\t' << count << endl;
285 //for each bin in the list vector
286 for (int i = 0; i < list->size(); i++) {
288 binnames = list->get(i);
289 while (binnames.find_first_of(',') != -1) {
290 name = binnames.substr(0,binnames.find_first_of(','));
291 binnames = binnames.substr(binnames.find_first_of(',')+1, binnames.length());
293 //do work for that name
294 sequence = fasta->getSequence(name);
295 if (sequence != "not found") {
296 //if you don't have groups
297 if (groupfile == "") {
298 name = name + "|" + toString(i+1);
299 out << ">" << name << endl;
300 out << sequence << endl;
301 }else {//if you do have groups
302 string group = groupMap->getGroup(name);
303 if (group == "not found") {
304 cout << name << " is missing from your group file. Please correct. " << endl;
305 remove(outputFileName.c_str());
308 name = name + "|" + group + "|" + toString(i+1);
309 out << ">" << name << endl;
310 out << sequence << endl;
314 cout << name << " is missing from your fasta or name file. Please correct. " << endl;
315 remove(outputFileName.c_str());
322 sequence = fasta->getSequence(binnames);
323 if (sequence != "not found") {
324 //if you don't have groups
325 if (groupfile == "") {
326 binnames = binnames + "|" + toString(i+1);
327 out << ">" << binnames << endl;
328 out << sequence << endl;
329 }else {//if you do have groups
330 string group = groupMap->getGroup(binnames);
331 if (group == "not found") {
332 cout << binnames << " is missing from your group file. Please correct. " << endl;
333 remove(outputFileName.c_str());
336 binnames = binnames + "|" + group + "|" + toString(i+1);
337 out << ">" << binnames << endl;
338 out << sequence << endl;
342 cout << binnames << " is missing from your fasta or name file. Please correct. " << endl;
343 remove(outputFileName.c_str());
352 catch(exception& e) {
353 cout << "Standard Error: " << e.what() << " has occurred in the BinSeqCommand class Function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
357 cout << "An unknown error has occurred in the BinSeqCommand class function readNamesFile. Please contact Pat Schloss at pschloss@microbio.umass.edu." << "\n";
361 //**********************************************************************************************************************