2 * chimerabellerophoncommand.cpp
5 * Created by westcott on 4/1/10.
6 * Copyright 2010 Schloss Lab. All rights reserved.
10 #include "chimerabellerophoncommand.h"
11 #include "bellerophon.h"
13 //**********************************************************************************************************************
14 vector<string> ChimeraBellerophonCommand::setParameters(){
16 CommandParameter pfasta("fasta", "InputTypes", "", "", "none","none","none",false,true); parameters.push_back(pfasta);
17 CommandParameter pfilter("filter", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pfilter);
18 CommandParameter pcorrection("filter", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pcorrection);
19 CommandParameter pwindow("window", "Number", "", "0", "", "", "",false,false); parameters.push_back(pwindow);
20 CommandParameter pincrement("increment", "Number", "", "25", "", "", "",false,false); parameters.push_back(pincrement);
21 CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
22 CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
23 CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
25 vector<string> myArray;
26 for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
30 m->errorOut(e, "ChimeraBellerophonCommand", "setParameters");
34 //**********************************************************************************************************************
35 string ChimeraBellerophonCommand::getHelpString(){
37 string helpString = "";
38 helpString += "The chimera.bellerophon command reads a fastafile and creates list of potentially chimeric sequences.\n";
39 helpString += "The chimera.bellerophon command parameters are fasta, filter, correction, processors, window, increment. The fasta parameter is required, unless you have a valid current file.\n";
40 helpString += "The fasta parameter is required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n";
41 helpString += "The filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter, default=false. \n";
42 helpString += "The correction parameter allows you to put more emphasis on the distance between highly similar sequences and less emphasis on the differences between remote homologs, default=true.\n";
43 helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n";
45 helpString += "When using MPI, the processors parameter is set to the number of MPI processes running. \n";
47 helpString += "The window parameter allows you to specify the window size for searching for chimeras, default is 1/4 sequence length. \n";
48 helpString += "The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default is 25.\n";
49 helpString += "chimera.bellerophon(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors) \n";
50 helpString += "Example: chimera.bellerophon(fasta=AD.align, filter=True, correction=true, window=200) \n";
51 helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n";
55 m->errorOut(e, "ChimeraBellerophonCommand", "getHelpString");
59 //**********************************************************************************************************************
60 ChimeraBellerophonCommand::ChimeraBellerophonCommand(){
62 abort = true; calledHelp = true;
64 vector<string> tempOutNames;
65 outputTypes["chimera"] = tempOutNames;
66 outputTypes["accnos"] = tempOutNames;
69 m->errorOut(e, "ChimeraBellerophonCommand", "ChimeraBellerophonCommand");
73 //***************************************************************************************************************
74 ChimeraBellerophonCommand::ChimeraBellerophonCommand(string option) {
76 abort = false; calledHelp = false;
78 //allow user to run help
79 if(option == "help") { help(); abort = true; calledHelp = true; }
83 vector<string> myArray = setParameters();
85 OptionParser parser(option);
86 map<string,string> parameters = parser.getParameters();
88 ValidParameters validParameter("chimera.bellerophon");
89 map<string,string>::iterator it;
91 //check to make sure all parameters are valid for command
92 for (it = parameters.begin(); it != parameters.end(); it++) {
93 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
96 //initialize outputTypes
97 vector<string> tempOutNames;
98 outputTypes["chimera"] = tempOutNames;
99 outputTypes["accnos"] = tempOutNames;
101 //if the user changes the input directory command factory will send this info to us in the output parameter
102 string inputDir = validParameter.validFile(parameters, "inputdir", false);
103 if (inputDir == "not found"){ inputDir = ""; }
105 fastafile = validParameter.validFile(parameters, "fasta", false);
106 if (fastafile == "not found") {
107 //if there is a current fasta file, use it
108 string filename = m->getFastaFile();
109 if (filename != "") { fastaFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
110 else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
112 m->splitAtDash(fastafile, fastaFileNames);
114 //go through files and make sure they are good, if not, then disregard them
115 for (int i = 0; i < fastaFileNames.size(); i++) {
116 if (inputDir != "") {
117 string path = m->hasPath(fastaFileNames[i]);
118 //if the user has not given a path then, add inputdir. else leave path alone.
119 if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
125 ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
127 //if you can't open it, try default location
128 if (ableToOpen == 1) {
129 if (m->getDefaultPath() != "") { //default path is set
130 string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
131 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
133 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
135 fastaFileNames[i] = tryPath;
139 //if you can't open it, try default location
140 if (ableToOpen == 1) {
141 if (m->getOutputDir() != "") { //default path is set
142 string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
143 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
145 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
147 fastaFileNames[i] = tryPath;
153 if (ableToOpen == 1) {
154 m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
155 //erase from file list
156 fastaFileNames.erase(fastaFileNames.begin()+i);
162 //make sure there is at least one valid file left
163 if (fastaFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
166 //if the user changes the output directory command factory will send this info to us in the output parameter
167 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
170 temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; }
171 filter = m->isTrue(temp);
173 temp = validParameter.validFile(parameters, "correction", false); if (temp == "not found") { temp = "T"; }
174 correction = m->isTrue(temp);
176 temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
177 m->setProcessors(temp);
178 convert(temp, processors);
180 temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; }
181 convert(temp, window);
183 temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "25"; }
184 convert(temp, increment);
187 catch(exception& e) {
188 m->errorOut(e, "ChimeraBellerophonCommand", "ChimeraBellerophonCommand");
192 //***************************************************************************************************************
193 int ChimeraBellerophonCommand::execute(){
196 if (abort == true) { if (calledHelp) { return 0; } return 2; }
198 for (int i = 0; i < fastaFileNames.size(); i++) {
200 m->mothurOut("Checking sequences from " + fastaFileNames[i] + " ..." ); m->mothurOutEndLine();
202 int start = time(NULL);
204 chimera = new Bellerophon(fastaFileNames[i], filter, correction, window, increment, processors, outputDir);
206 if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[i]); }//if user entered a file with a path then preserve it
207 string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])) + "bellerophon.chimeras";
208 string accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])) + "bellerophon.accnos";
210 chimera->getChimeras();
212 if (m->control_pressed) { delete chimera; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); return 0; }
216 MPI_File outMPIAccnos;
218 int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY;
220 char outFilename[1024];
221 strcpy(outFilename, accnosFileName.c_str());
224 strcpy(FileName, outputFileName.c_str());
226 MPI_File_open(MPI_COMM_WORLD, FileName, outMode, MPI_INFO_NULL, &outMPI); //comm, filename, mode, info, filepointer
227 MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPIAccnos);
229 numSeqs = chimera->print(outMPI, outMPIAccnos, "");
231 MPI_File_close(&outMPI);
232 MPI_File_close(&outMPIAccnos);
237 m->openOutputFile(outputFileName, out);
240 m->openOutputFile(accnosFileName, out2);
242 numSeqs = chimera->print(out, out2, "");
248 if (m->control_pressed) { remove(accnosFileName.c_str()); remove(outputFileName.c_str()); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); delete chimera; return 0; }
250 m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine();
252 outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName);
253 outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName);
258 //set accnos file as new current accnosfile
260 itTypes = outputTypes.find("accnos");
261 if (itTypes != outputTypes.end()) {
262 if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); }
265 m->mothurOutEndLine();
266 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
267 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
268 m->mothurOutEndLine();
273 catch(exception& e) {
274 m->errorOut(e, "ChimeraBellerophonCommand", "execute");
278 //**********************************************************************************************************************