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
|
/*
* classify.cpp
* Mothur
*
* Created by westcott on 11/3/09.
* Copyright 2009 Schloss Lab. All rights reserved.
*
*/
#include "classify.h"
#include "sequence.hpp"
#include "kmerdb.hpp"
#include "suffixdb.hpp"
#include "distancedb.hpp"
/**************************************************************************************************/
void Classify::generateDatabaseAndNames(string tfile, string tempFile, string method, int kmerSize, float gapOpen, float gapExtend, float match, float misMatch, string version) {
try {
Utils util;
int numSeqs = 0; maxLevel = 0;
taxFile = tfile;
templateFile = tempFile;
long start = time(nullptr); m->mothurOut("Generating search database... "); cout.flush();
//need to know number of template seqs for suffixdb
if (method == "suffix") {
ifstream inFASTA; util.openInputFile(tempFile, inFASTA);
util.getNumSeqs(inFASTA, numSeqs);
inFASTA.close();
}
bool needToGenerate = true;
string dBName;
if(method == "kmer") {
database = new KmerDB(tempFile, kmerSize);
dBName = tempFile.substr(0,tempFile.find_last_of(".")+1) + char('0'+ kmerSize) + "mer";
ifstream kmerFileTest(dBName.c_str());
if(kmerFileTest){
string line = util.getline(kmerFileTest);
bool GoodFile = util.checkReleaseVersion(line, version); kmerFileTest.close();
int shortcutTimeStamp = util.getTimeStamp(dBName);
int referenceTimeStamp = util.getTimeStamp(tempFile);
//if the shortcut file is older then the reference file, remake shortcut file
if (shortcutTimeStamp < referenceTimeStamp) { GoodFile = false; }
if (GoodFile) { needToGenerate = false; }
}
}
else if(method == "suffix") { database = new SuffixDB(numSeqs); }
else if(method == "distance") { database = new DistanceDB(); }
else {
m->mothurOut(method + " is not a valid search option. I will run the command using kmer, ksize=8.\n");
database = new KmerDB(tempFile, 8);
}
if (!m->getControl_pressed()) {
if (needToGenerate) {
ifstream fastaFile; util.openInputFile(tempFile, fastaFile);
while (!fastaFile.eof()) {
Sequence temp(fastaFile); gobble(fastaFile);
names.push_back(temp.getName());
database->addSequence(temp);
}
fastaFile.close();
if ((method == "kmer") && (!shortcuts)) {;} //don't print
else {database->generateDB(); }
}else if ((method == "kmer") && (!needToGenerate)) {
ifstream FileTest(dBName.c_str());
database->readDB(FileTest);
ifstream fastaFile; util.openInputFile(tempFile, fastaFile);
while (!fastaFile.eof()) {
Sequence temp(fastaFile); gobble(fastaFile);
names.push_back(temp.getName());
}
fastaFile.close();
}
database->setNumSeqs(names.size());
m->mothurOut("DONE.\nIt took " + toString(time(nullptr) - start) + " seconds generate search database.\n");
readTaxonomy(taxFile);
//sanity check
bool okay = phyloTree->ErrorCheck(names);
if (!okay) { m->setControl_pressed(true); }
}
}
catch(exception& e) {
m->errorOut(e, "Classify", "generateDatabaseAndNames");
exit(1);
}
}
/**************************************************************************************************/
Classify::Classify() { m = MothurOut::getInstance(); database = nullptr; phyloTree=nullptr; maxLevel = 0; }
/**************************************************************************************************/
int Classify::readTaxonomy(string file) {
try {
phyloTree = new PhyloTree();
string name, taxInfo;
m->mothurOut("\nReading in the " + file + " taxonomy...\t"); cout.flush();
if (m->getDebug()) { m->mothurOut("[DEBUG]: Taxonomies read in...\n"); }
taxonomy.clear();
Utils util; util.readTax(file, taxonomy, true);
for (map<string, string>::iterator itTax = taxonomy.begin(); itTax != taxonomy.end(); itTax++) {
phyloTree->addSeqToTree(itTax->first, itTax->second);
if (m->getControl_pressed()) { break; }
}
phyloTree->assignHeirarchyIDs(0);
maxLevel = phyloTree->getMaxLevel();
phyloTree->setUp(file);
m->mothurOut("DONE.\n"); cout.flush();
return phyloTree->getNumSeqs();
}
catch(exception& e) {
m->errorOut(e, "Classify", "readTaxonomy");
exit(1);
}
}
/**************************************************************************************************/
vector<string> Classify::parseTax(string tax) {
try {
vector<string> taxons;
Utils util; util.splitAtChar(tax, taxons, ';');
return taxons;
}
catch(exception& e) {
m->errorOut(e, "Classify", "parseTax");
exit(1);
}
}
/**************************************************************************************************/
double Classify::getLogExpSum(vector<double> probabilities, int& maxIndex){
try {
// http://jblevins.org/notes/log-sum-exp
double maxProb = probabilities[0];
maxIndex = 0;
int numProbs = (int)probabilities.size();
for(int i=1;i<numProbs;i++){
if(probabilities[i] >= maxProb){
maxProb = probabilities[i];
maxIndex = i;
}
}
double probSum = 0.0000;
for(int i=0;i<numProbs;i++){
probSum += exp(probabilities[i] - maxProb);
}
probSum = log(probSum) + maxProb;
return probSum;
}
catch(exception& e) {
m->errorOut(e, "Classify", "getLogExpSum");
exit(1);
}
}
/**************************************************************************************************/
bool Classify::checkReleaseDate(vector<ifstream*>& files, string version) {
try {
Utils util;
bool good = true;
vector<string> versionVector;
util.splitAtChar(version, versionVector, '.');
for (int i = 0; i < files.size(); i++) {
string line = util.getline(*files[i]);
if (line[0] != '#') { good = false; break; } //shortcut files from before we added this check
else {
line = line.substr(1);
vector<string> linesVector; util.splitAtChar(line, linesVector, '.');
if (versionVector.size() != linesVector.size()) { good = false; break; }
else {
for (int j = 0; j < versionVector.size(); j++) {
int num1, num2;
convert(versionVector[j], num1);
convert(linesVector[j], num2);
//if mothurs version is newer than this files version, then we want to remake it
if (num1 > num2) { good = false; break; }
}
}
if (!good) { break; }
}
}
if (!good) { for (int i = 0; i < files.size(); i++) { files[i]->close(); } }
else { for (int i = 0; i < files.size(); i++) { files[i]->seekg(0); } }
return good;
}
catch(exception& e) {
m->errorOut(e, "Classify", "checkReleaseDate");
exit(1);
}
}
/**************************************************************************************************/
|
