1 #ifndef GETOTUREPCOMMAND_H
2 #define GETOTUREPCOMMAND_H
7 * Created by Sarah Westcott on 4/6/09.
8 * Copyright 2009 Schloss Lab UMASS Amherst. All rights reserved.
12 /* The get.oturep command outputs a .fastarep file for each distance you specify, selecting one OTU representative for each bin. */
14 #include "command.hpp"
15 #include "globaldata.hpp"
16 #include "sparsematrix.hpp"
17 #include "listvector.hpp"
18 #include "inputdata.h"
23 typedef list<PCell>::iterator MatData;
24 typedef map<int, float> SeqMap;
33 repStruct(string n, int b, int s, string g) : name(n), bin(b), size(s), group(g) {}
37 class GetOTURepCommand : public Command {
40 GetOTURepCommand(string);
46 GlobalData* globaldata;
53 string filename, fastafile, listfile, namesfile, groupfile, label, sorted;
59 set<string> labels; //holds labels to be used
60 map<string, int> nameToIndex; //maps sequence name to index in sparsematrix
62 vector<SeqMap> seqVec; // contains maps with sequence index and distance
63 // for all distances related to a certain sequence
67 int process(ListVector*);
68 string findRep(int, string&, ListVector*, int&); // returns the name of the "representative" sequence of given bin,
69 // fills a string containing the groups in that bin if a groupfile is given,
70 // and returns the number of sequences in the given bin