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::getValidParameters(){
16 string AlignArray[] = {"fasta","filter","correction","processors","window","increment","outputdir","inputdir"};
17 vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
21 m->errorOut(e, "ChimeraBellerophonCommand", "getValidParameters");
25 //**********************************************************************************************************************
26 vector<string> ChimeraBellerophonCommand::getRequiredParameters(){
28 string AlignArray[] = {"fasta"};
29 vector<string> myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string)));
33 m->errorOut(e, "ChimeraBellerophonCommand", "getRequiredParameters");
37 //**********************************************************************************************************************
38 vector<string> ChimeraBellerophonCommand::getRequiredFiles(){
40 vector<string> myArray;
44 m->errorOut(e, "ChimeraBellerophonCommand", "getRequiredFiles");
48 //**********************************************************************************************************************
49 ChimeraBellerophonCommand::ChimeraBellerophonCommand(){
51 abort = true; calledHelp = true;
52 vector<string> tempOutNames;
53 outputTypes["chimera"] = tempOutNames;
54 outputTypes["accnos"] = tempOutNames;
55 outputTypes["fasta"] = tempOutNames;
58 m->errorOut(e, "ChimeraBellerophonCommand", "ChimeraBellerophonCommand");
62 //***************************************************************************************************************
63 ChimeraBellerophonCommand::ChimeraBellerophonCommand(string option) {
65 abort = false; calledHelp = false;
67 //allow user to run help
68 if(option == "help") { help(); abort = true; calledHelp = true; }
71 //valid paramters for this command
72 string Array[] = {"fasta","filter","correction","processors","window","increment","outputdir","inputdir"};
73 vector<string> myArray (Array, Array+(sizeof(Array)/sizeof(string)));
75 OptionParser parser(option);
76 map<string,string> parameters = parser.getParameters();
78 ValidParameters validParameter("chimera.bellerophon");
79 map<string,string>::iterator it;
81 //check to make sure all parameters are valid for command
82 for (it = parameters.begin(); it != parameters.end(); it++) {
83 if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
86 //initialize outputTypes
87 vector<string> tempOutNames;
88 outputTypes["chimera"] = tempOutNames;
89 outputTypes["accnos"] = tempOutNames;
90 outputTypes["fasta"] = tempOutNames;
92 //if the user changes the input directory command factory will send this info to us in the output parameter
93 string inputDir = validParameter.validFile(parameters, "inputdir", false);
94 if (inputDir == "not found"){ inputDir = ""; }
96 fastafile = validParameter.validFile(parameters, "fasta", false);
97 if (fastafile == "not found") { fastafile = ""; m->mothurOut("fasta is a required parameter for the chimera.bellerophon command."); m->mothurOutEndLine(); abort = true; }
99 m->splitAtDash(fastafile, fastaFileNames);
101 //go through files and make sure they are good, if not, then disregard them
102 for (int i = 0; i < fastaFileNames.size(); i++) {
103 if (inputDir != "") {
104 string path = m->hasPath(fastaFileNames[i]);
105 //if the user has not given a path then, add inputdir. else leave path alone.
106 if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
112 ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
114 //if you can't open it, try default location
115 if (ableToOpen == 1) {
116 if (m->getDefaultPath() != "") { //default path is set
117 string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
118 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
120 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
122 fastaFileNames[i] = tryPath;
126 //if you can't open it, try default location
127 if (ableToOpen == 1) {
128 if (m->getOutputDir() != "") { //default path is set
129 string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
130 m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
132 ableToOpen = m->openInputFile(tryPath, in2, "noerror");
134 fastaFileNames[i] = tryPath;
140 if (ableToOpen == 1) {
141 m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
142 //erase from file list
143 fastaFileNames.erase(fastaFileNames.begin()+i);
149 //make sure there is at least one valid file left
150 if (fastaFileNames.size() == 0) { m->mothurOut("no valid files."); m->mothurOutEndLine(); abort = true; }
153 //if the user changes the output directory command factory will send this info to us in the output parameter
154 outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
157 temp = validParameter.validFile(parameters, "filter", false); if (temp == "not found") { temp = "F"; }
158 filter = m->isTrue(temp);
160 temp = validParameter.validFile(parameters, "correction", false); if (temp == "not found") { temp = "T"; }
161 correction = m->isTrue(temp);
163 temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found") { temp = "1"; }
164 convert(temp, processors);
166 temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "0"; }
167 convert(temp, window);
169 temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "25"; }
170 convert(temp, increment);
173 catch(exception& e) {
174 m->errorOut(e, "ChimeraBellerophonCommand", "ChimeraBellerophonCommand");
178 //**********************************************************************************************************************
180 void ChimeraBellerophonCommand::help(){
182 m->mothurOut("The chimera.bellerophon command reads a fastafile and creates list of potentially chimeric sequences.\n");
183 m->mothurOut("The chimera.bellerophon command parameters are fasta, filter, correction, processors, window, increment. The fasta parameter is required.\n");
184 m->mothurOut("The fasta parameter is required. You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amzon.fasta \n");
185 m->mothurOut("The filter parameter allows you to specify if you would like to apply a vertical and 50% soft filter, default=false. \n");
186 m->mothurOut("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");
187 m->mothurOut("The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n");
189 m->mothurOut("When using MPI, the processors parameter is set to the number of MPI processes running. \n");
191 m->mothurOut("The window parameter allows you to specify the window size for searching for chimeras, default is 1/4 sequence length. \n");
192 m->mothurOut("The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default is 25.\n");
193 m->mothurOut("chimera.bellerophon(fasta=yourFastaFile, filter=yourFilter, correction=yourCorrection, processors=yourProcessors) \n");
194 m->mothurOut("Example: chimera.bellerophon(fasta=AD.align, filter=True, correction=true, window=200) \n");
195 m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n\n");
197 catch(exception& e) {
198 m->errorOut(e, "ChimeraBellerophonCommand", "help");
203 //***************************************************************************************************************
205 ChimeraBellerophonCommand::~ChimeraBellerophonCommand(){ /* do nothing */ }
207 //***************************************************************************************************************
209 int ChimeraBellerophonCommand::execute(){
212 if (abort == true) { if (calledHelp) { return 0; } return 2; }
214 for (int i = 0; i < fastaFileNames.size(); i++) {
216 m->mothurOut("Checking sequences from " + fastaFileNames[i] + " ..." ); m->mothurOutEndLine();
218 int start = time(NULL);
220 chimera = new Bellerophon(fastaFileNames[i], filter, correction, window, increment, processors, outputDir);
222 if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[i]); }//if user entered a file with a path then preserve it
223 string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])) + "bellerophon.chimeras";
224 string accnosFileName = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[i])) + "bellerophon.accnos";
226 chimera->getChimeras();
228 if (m->control_pressed) { delete chimera; for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } outputTypes.clear(); return 0; }
232 MPI_File outMPIAccnos;
234 int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY;
236 char outFilename[1024];
237 strcpy(outFilename, accnosFileName.c_str());
240 strcpy(FileName, outputFileName.c_str());
242 MPI_File_open(MPI_COMM_WORLD, FileName, outMode, MPI_INFO_NULL, &outMPI); //comm, filename, mode, info, filepointer
243 MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPIAccnos);
245 numSeqs = chimera->print(outMPI, outMPIAccnos, "");
247 MPI_File_close(&outMPI);
248 MPI_File_close(&outMPIAccnos);
253 m->openOutputFile(outputFileName, out);
256 m->openOutputFile(accnosFileName, out2);
258 numSeqs = chimera->print(out, out2, "");
264 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; }
266 m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine(); m->mothurOutEndLine();
268 outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName);
269 outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName);
274 m->mothurOutEndLine();
275 m->mothurOut("Output File Names: "); m->mothurOutEndLine();
276 for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
277 m->mothurOutEndLine();
282 catch(exception& e) {
283 m->errorOut(e, "ChimeraBellerophonCommand", "execute");
287 //**********************************************************************************************************************