1 #ifndef CLASSIFYSEQSCOMMAND_H
2 #define CLASSIFYSEQSCOMMAND_H
5 * classifyseqscommand.h
8 * Created by westcott on 11/2/09.
9 * Copyright 2009 Schloss Lab. All rights reserved.
14 #include "command.hpp"
15 //#include "alignment.hpp"
18 //KNN and Bayesian methods modeled from algorithms in
19 //Naı¨ve Bayesian Classifier for Rapid Assignment of rRNA Sequences
20 //into the New Bacterial Taxonomy†
21 //Qiong Wang,1 George M. Garrity,1,2 James M. Tiedje,1,2 and James R. Cole1*
22 //Center for Microbial Ecology1 and Department of Microbiology and Molecular Genetics,2 Michigan State University,
23 //East Lansing, Michigan 48824
24 //Received 10 January 2007/Accepted 18 June 2007
28 class ClassifySeqsCommand : public Command {
31 ClassifySeqsCommand(string);
32 ClassifySeqsCommand();
33 ~ClassifySeqsCommand();
34 vector<string> getRequiredParameters();
35 vector<string> getValidParameters();
36 vector<string> getRequiredFiles();
37 map<string, vector<string> > getOutputFiles() { return outputTypes; }
43 unsigned long int start;
44 unsigned long int end;
45 linePair(unsigned long int i, unsigned long int j) : start(i), end(j) {}
48 vector<int> processIDS; //processid
49 vector<linePair*> lines;
50 vector<string> fastaFileNames;
51 vector<string> namefileNames;
52 vector<string> groupfileNames;
53 vector<string> outputNames;
54 map<string, vector<string> > nameMap;
55 map<string, vector<string> >::iterator itNames;
56 map<string, vector<string> > outputTypes;
60 string fastaFileName, templateFileName, distanceFileName, namefile, search, method, taxonomyFileName, outputDir, groupfile;
61 int processors, kmerSize, numWanted, cutoff, iters;
62 float match, misMatch, gapOpen, gapExtend;
65 int driver(linePair*, string, string, string);
66 void appendTaxFiles(string, string);
67 int createProcesses(string, string, string);
68 string addUnclassifieds(string, int);
70 int MPIReadNamesFile(string);
72 int driverMPI(int, int, MPI_File&, MPI_File&, MPI_File&, vector<unsigned long int>&);