#include "mothur.h"
#include "command.hpp"
-//#include "alignment.hpp"
#include "classify.h"
//KNN and Bayesian methods modeled from algorithms in
public:
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 {
unsigned long int start;
- int numSeqs;
- linePair(unsigned long int i, int j) : start(i), numSeqs(j) {}
+ 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;
int driver(linePair*, string, string, string);
void appendTaxFiles(string, string);
- void createProcesses(string, string, string);
+ int createProcesses(string, string, string);
string addUnclassifieds(string, int);
int MPIReadNamesFile(string);