1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
|
#ifndef CLASSIFYSEQSCOMMAND_H
#define CLASSIFYSEQSCOMMAND_H
/*
* classifyseqscommand.h
* Mothur
*
* Created by westcott on 11/2/09.
* Copyright 2009 Schloss Lab. All rights reserved.
*
*/
#include "command.hpp"
#include "classify.h"
#include "referencedb.h"
#include "sequence.hpp"
#include "bayesian.h"
#include "phylotree.h"
#include "phylosummary.h"
#include "knn.h"
#include "kmertree.h"
#include "aligntree.h"
//KNN and Wang 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();
~ClassifySeqsCommand();
vector<string> setParameters();
string getCommandName() { return "classify.seqs"; }
string getCommandCategory() { return "Phylotype Analysis"; }
string getHelpString();
string getOutputPattern(string);
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"; }
string getDescription() { return "classify sequences"; }
int execute();
void help() { m->mothurOut(getHelpString()); }
private:
struct linePair {
unsigned long long start;
unsigned long long end;
linePair(unsigned long long i, unsigned long long j) : start(i), end(j) {}
};
vector<int> processIDS; //processid
vector<linePair*> lines;
vector<string> fastaFileNames;
vector<string> namefileNames;
vector<string> countfileNames;
vector<string> groupfileNames;
vector<string> outputNames;
map<string, vector<string> > nameMap;
map<string, vector<string> >::iterator itNames;
Classify* classify;
ReferenceDB* rdb;
string fastaFileName, templateFileName, countfile, distanceFileName, namefile, search, method, taxonomyFileName, outputDir, groupfile;
int processors, kmerSize, numWanted, cutoff, iters;
float match, misMatch, gapOpen, gapExtend;
bool abort, probs, save, flip, hasName, hasCount, writeShortcuts, relabund;
int driver(linePair*, string, string, string, string);
int createProcesses(string, string, string, string);
string addUnclassifieds(string, int);
int MPIReadNamesFile(string);
#ifdef USE_MPI
int driverMPI(int, int, MPI_File&, MPI_File&, MPI_File&, MPI_File&, vector<unsigned long long>&);
#endif
};
/**************************************************************************************************/
//custom data structure for threads to use.
// This is passed by void pointer so it can be any data type
// that can be passed using a single void pointer (LPVOID).
struct classifyData {
string taxFName;
string tempTFName;
string filename;
string search, taxonomyFileName, templateFileName, method, accnos;
unsigned long long start;
unsigned long long end;
MothurOut* m;
float match, misMatch, gapOpen, gapExtend;
int count, kmerSize, threadID, cutoff, iters, numWanted;
bool probs, flip, writeShortcuts;
classifyData(){}
classifyData(string acc, bool p, string me, string te, string tx, string a, string r, string f, string se, int ks, int i, int numW, MothurOut* mout, unsigned long long st, unsigned long long en, float ma, float misMa, float gapO, float gapE, int cut, int tid, bool fli, bool wsh) {
accnos = acc;
taxonomyFileName = tx;
templateFileName = te;
taxFName = a;
tempTFName = r;
filename = f;
search = se;
method = me;
m = mout;
start = st;
end = en;
match = ma;
misMatch = misMa;
gapOpen = gapO;
gapExtend = gapE;
kmerSize = ks;
cutoff = cut;
iters = i;
numWanted = numW;
threadID = tid;
probs = p;
count = 0;
flip = fli;
writeShortcuts = wsh;
}
};
/**************************************************************************************************/
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
#else
static DWORD WINAPI MyClassThreadFunction(LPVOID lpParam){
classifyData* pDataArray;
pDataArray = (classifyData*)lpParam;
try {
ofstream outTax;
pDataArray->m->openOutputFile(pDataArray->taxFName, outTax);
ofstream outTaxSimple;
pDataArray->m->openOutputFile(pDataArray->tempTFName, outTaxSimple);
ofstream outAcc;
pDataArray->m->openOutputFile(pDataArray->accnos, outAcc);
ifstream inFASTA;
pDataArray->m->openInputFile(pDataArray->filename, inFASTA);
string taxonomy;
//print header if you are process 0
if ((pDataArray->start == 0) || (pDataArray->start == 1)) {
inFASTA.seekg(0);
}else { //this accounts for the difference in line endings.
inFASTA.seekg(pDataArray->start-1); pDataArray->m->gobble(inFASTA);
}
//make classify
Classify* myclassify;
string outputMethodTag = pDataArray->method + ".";
if(pDataArray->method == "wang"){ myclassify = new Bayesian(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->cutoff, pDataArray->iters, pDataArray->threadID, pDataArray->flip, pDataArray->writeShortcuts); }
else if(pDataArray->method == "knn"){ myclassify = new Knn(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->gapOpen, pDataArray->gapExtend, pDataArray->match, pDataArray->misMatch, pDataArray->numWanted, pDataArray->threadID); }
else if(pDataArray->method == "zap"){
outputMethodTag = pDataArray->search + "_" + outputMethodTag;
if (pDataArray->search == "kmer") { myclassify = new KmerTree(pDataArray->templateFileName, pDataArray->taxonomyFileName, pDataArray->kmerSize, pDataArray->cutoff); }
else { myclassify = new AlignTree(pDataArray->templateFileName, pDataArray->taxonomyFileName, pDataArray->cutoff); }
}
else {
pDataArray->m->mothurOut(pDataArray->method + " is not a valid method option. I will run the command using wang.");
pDataArray->m->mothurOutEndLine();
myclassify = new Bayesian(pDataArray->taxonomyFileName, pDataArray->templateFileName, pDataArray->search, pDataArray->kmerSize, pDataArray->cutoff, pDataArray->iters, pDataArray->threadID, pDataArray->flip, pDataArray->writeShortcuts);
}
if (pDataArray->m->control_pressed) { delete myclassify; return 0; }
pDataArray->count = 0;
for(int i = 0; i < pDataArray->end; i++){ //end is the number of sequences to process
if (pDataArray->m->control_pressed) { delete myclassify; return 0; }
Sequence* candidateSeq = new Sequence(inFASTA); pDataArray->m->gobble(inFASTA);
if (candidateSeq->getName() != "") {
taxonomy = myclassify->getTaxonomy(candidateSeq);
if (pDataArray->m->control_pressed) { delete candidateSeq; return 0; }
if (taxonomy == "unknown;") { pDataArray->m->mothurOut("[WARNING]: " + candidateSeq->getName() + " could not be classified. You can use the remove.lineage command with taxon=unknown; to remove such sequences."); pDataArray->m->mothurOutEndLine(); }
//output confidence scores or not
if (pDataArray->probs) {
outTax << candidateSeq->getName() << '\t' << taxonomy << endl;
}else{
outTax << candidateSeq->getName() << '\t' << myclassify->getSimpleTax() << endl;
}
outTaxSimple << candidateSeq->getName() << '\t' << myclassify->getSimpleTax() << endl;
if (myclassify->getFlipped()) { outAcc << candidateSeq->getName() << endl; }
pDataArray->count++;
}
delete candidateSeq;
//report progress
if((pDataArray->count) % 100 == 0){ pDataArray->m->mothurOutJustToScreen("Processing sequence: " + toString(pDataArray->count)+"\n"); }
}
//report progress
if((pDataArray->count) % 100 != 0){ pDataArray->m->mothurOutJustToScreen("Processing sequence: " + toString(pDataArray->count)+"\n"); }
delete myclassify;
inFASTA.close();
outTax.close();
outTaxSimple.close();
}
catch(exception& e) {
pDataArray->m->errorOut(e, "ClassifySeqsCommand", "MyClassThreadFunction");
exit(1);
}
}
#endif
#endif
|
