working on citations

[mothur.git] / classifyseqscommand.h

diff --git a/classifyseqscommand.h b/classifyseqscommand.h
index a77b7d1d7193b862c88e036553a7616fb3f33dc9..f075b41495afc9002e2a695d47972d4d947eafc9 100644 (file)
--- a/classifyseqscommand.h
+++ b/classifyseqscommand.h
@@ -12,36 +12,69 @@
 
 #include "mothur.h"
 #include "command.hpp"
-#include "alignment.hpp"
 #include "classify.h"
 
+//KNN and Bayesian methods modeled from algorithms in
+//Naı¨ve Bayesian Classifier for Rapid Assignment of rRNA Sequences 
+//into the New Bacterial Taxonomy􏰎† 
+//Qiong Wang,1 George M. Garrity,1,2 James M. Tiedje,1,2 and James R. Cole1* 
+//Center for Microbial Ecology1 and Department of Microbiology and Molecular Genetics,2 Michigan State University, 
+//East Lansing, Michigan 48824 
+//Received 10 January 2007/Accepted 18 June 2007 
+
+
+
 class ClassifySeqsCommand : public Command {
        
 public:
-       ClassifySeqsCommand(string);    
+       ClassifySeqsCommand(string);
+       ClassifySeqsCommand();
        ~ClassifySeqsCommand();
+       
+       vector<string> setParameters();
+       string getCommandName()                 { return "classify.seqs";               }
+       string getCommandCategory()             { return "Phylotype Analysis";  }
+       string getHelpString(); 
+       string getCitation() { return "Wang Q, Garrity GM, Tiedje JM, Cole JR (2007). Naive Bayesian classifier for rapid assignment of rRNA sequences into the new bacterial taxonomy. Appl Environ Microbiol 73: 5261-7. [ for Bayesian classifier ] \nAltschul SF, Madden TL, Schaffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ (1997). Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res 25: 3389-402. [ for BLAST ] \nDeSantis TZ, Hugenholtz P, Larsen N, Rojas M, Brodie EL, Keller K, Huber T, Dalevi D, Hu P, Andersen GL (2006). Greengenes, a chimera-checked 16S rRNA gene database and workbench compatible with ARB. Appl Environ Microbiol 72: 5069-72. [ for kmer ] \nhttp://www.mothur.org/wiki/Classify.seqs"; }
+
+       
        int execute(); 
-       void help();    
+       void help() { m->mothurOut(getHelpString()); }  
+       
+       
        
 private:
        struct linePair {
-               int start;
-               int numSeqs;
-               linePair(int i, int j) : start(i), numSeqs(j) {}
+               unsigned long int start;
+               unsigned long int end;
+               linePair(unsigned long int i, unsigned long int j) : start(i), end(j) {}
        };
+
        vector<int> processIDS;   //processid
        vector<linePair*> lines;
+       vector<string> fastaFileNames;
+       vector<string> namefileNames;
+       vector<string> groupfileNames;
+       vector<string> outputNames;
+       map<string, vector<string> > nameMap;
+       map<string,  vector<string> >::iterator itNames;
        
        Classify* classify;
        
-       string fastaFileName, templateFileName, distanceFileName, search, method, taxonomyFileName;
-       int processors, kmerSize, numWanted;
+       string fastaFileName, templateFileName, distanceFileName, namefile, search, method, taxonomyFileName, outputDir, groupfile;
+       int processors, kmerSize, numWanted, cutoff, iters;
        float match, misMatch, gapOpen, gapExtend;
-       bool abort;
+       bool abort, probs;
        
-       int driver(linePair*, string);
+       int driver(linePair*, string, string, string);
        void appendTaxFiles(string, string);
-       void createProcesses(string); 
+       int createProcesses(string, string, string); 
+       string addUnclassifieds(string, int);
+       
+       int MPIReadNamesFile(string);
+       #ifdef USE_MPI
+       int driverMPI(int, int, MPI_File&, MPI_File&, MPI_File&, vector<unsigned long int>&);
+       #endif
 };
 
 #endif