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
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
|
/*
* splitmatrix.cpp
* Mothur
*
* Created by westcott on 5/19/10.
* Copyright 2010 Schloss Lab. All rights reserved.
*/
#include "splitmatrix.h"
#include "phylotree.h"
#include "distancecommand.h"
#include "pairwiseseqscommand.h"
#include "seqsummarycommand.h"
#include "getseqscommand.h"
#include "removeseqscommand.h"
/***********************************************************************/
SplitMatrix::SplitMatrix(string ffile, string name, string count, string tax, float c, float cu, int p, bool cl, string output, bool v){
m = MothurOut::getInstance();
fastafile = ffile;
namefile = name;
countfile = count;
taxFile = tax;
cutoff = c; //tax level cutoff
distCutoff = cu; //for fasta method if you are creating distance matrix you need a cutoff for that
processors = p;
classic = cl;
outputDir = output;
usingVsearchToCLuster = v;
splitClassify();
}
/***********************************************************************/
void SplitMatrix::splitClassify(){
try {
cutoff = int(cutoff);
map<string, string> temp; util.readTax(taxFile, temp, true);
PhyloTree phylo;
for (map<string, string>::iterator itTemp = temp.begin(); itTemp != temp.end();) {
if (m->getControl_pressed()) { return; }
phylo.addSeqToTree(itTemp->first, itTemp->second);
temp.erase(itTemp++);
}
phylo.assignHeirarchyIDs(0);
//make sure the cutoff is not greater than maxlevel
if (cutoff > phylo.getMaxLevel()) { m->mothurOut("splitcutoff is greater than the longest taxonomy, using " + toString(phylo.getMaxLevel())); m->mothurOutEndLine(); cutoff = phylo.getMaxLevel(); }
vector<vector<string> > seqGroups; //seqFroups[0] -> vector of string containing names of seqs assigned to group 0
vector<string> taxGroupNames;
//for each node in tree
for (int i = 0; i < phylo.getNumNodes(); i++) {
if (m->getControl_pressed()) { return; }
//is this node within the cutoff
TaxNode taxon = phylo.get(i);
if (taxon.level == cutoff) {//if yes, then create group containing this nodes sequences
if (taxon.accessions.size() > 1) { //if this taxon just has one seq its a singleton
vector<string> thisGroupsSeqs;
for (int j = 0; j < taxon.accessions.size(); j++) {
thisGroupsSeqs.push_back(taxon.accessions[j]);
}
seqGroups.push_back(thisGroupsSeqs);
taxGroupNames.push_back(taxon.name);
}
}
}
if (usingVsearchToCLuster) { createFastaFilesFromTax(seqGroups, taxGroupNames); }
else { createDistanceFilesFromTax(seqGroups, taxGroupNames); }
}
catch(exception& e) {
m->errorOut(e, "SplitMatrix", "splitClassify");
exit(1);
}
}
/***********************************************************************/
int SplitMatrix::createDistanceFilesFromTax(vector<vector<string> >& seqGroups, vector<string> groupNames){
try {
int numGroups = seqGroups.size();
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(fastafile); }
string nonSingletonsFile = thisOutputDir + util.getRootName(util.getSimpleName(fastafile)) + "nonsingleton.accnos";
ofstream outNonSingleton; util.openOutputFile(nonSingletonsFile, outNonSingleton);
ifstream inFASTA; util.openInputFile(fastafile, inFASTA);
SequenceDB fullDB(inFASTA); inFASTA.close();
if (m->getDebug()) { for (int i = 0; i < numGroups; i++) { m->mothurOut("[DEBUG]: Number of unique sequences for group " + groupNames[i] + " (" + toString(i+1) + " of " + toString(numGroups) + "): " + toString(seqGroups[i].size()) + "\n\n"); } }
//process each group
for (int i = 0; i < numGroups; i++) {
if (m->getControl_pressed()) { outNonSingleton.close(); util.mothurRemove(nonSingletonsFile); for (int i = 0; i < dists.size(); i++) { util.mothurRemove((dists[i].begin()->first)); util.mothurRemove((dists[i].begin()->second)); } dists.clear(); return 0; }
unordered_set<string> thisGroupsNames = util.mothurConvert(seqGroups[i]);
m->mothurOut("/******************************************/\n");
m->mothurOut("Selecting sequences for group " + groupNames[i] + " (" + toString(i+1) + " of " + toString(numGroups) + ")\nNumber of unique sequences: " + toString(seqGroups[i].size()) + "\n\n");
string outName = "";
if (namefile != "") {
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(namefile); }
outName = thisOutputDir + util.getRootName(util.getSimpleName(namefile)) + toString(i) + ".name.temp";
}
if (countfile != "") {
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(countfile); }
outName = thisOutputDir + util.getRootName(util.getSimpleName(countfile)) + toString(i) + ".count.temp";
}
pair<string,string> dupsFile(namefile, outName); string dupsFormat = "name";
if (countfile != "") { dupsFile.first = countfile; dupsFormat = "count"; }
Command* getCommand = new GetSeqsCommand(thisGroupsNames, nullStringPair, nullStringPair, dupsFile, dupsFormat);
delete getCommand;
StorageDatabase* thisDB;
m->mothurOut("\nCalculating distances for group " + groupNames[i] + " (" + toString(i+1) + " of " + toString(numGroups) + "):\n");
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(fastafile); }
string outputFileRoot = thisOutputDir + util.getRootName(util.getSimpleName(fastafile)) + toString(i) + ".";
string outputformat = "column"; if (classic) { outputformat = "lt"; }
Command* command;
vector< vector< int > > kmerDB; vector< int > lengths;
if (fullDB.sameLength()) {
thisDB = new SequenceDB(fullDB, thisGroupsNames);
command = new DistanceCommand(thisDB, outputFileRoot, distCutoff, outputformat, processors);
}
else {
thisDB = new SequenceDB(fullDB, thisGroupsNames, 7, kmerDB, lengths);
command = new PairwiseSeqsCommand(thisDB, kmerDB, lengths, outputFileRoot, distCutoff, outputformat, processors);
}
map<string, vector<string> > filenames = command->getOutputFiles();
string thisDistanceFile = "";
if (classic) { thisDistanceFile = filenames["phylip"][0]; }
else { thisDistanceFile = filenames["column"][0]; }
delete command;
m->mothurOut("/******************************************/\n");
if (!util.isBlank(thisDistanceFile)) {
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(fastafile); }
string outDist = thisOutputDir + util.getRootName(util.getSimpleName(fastafile)) + toString(i) + ".disttemp";
util.renameFile(thisDistanceFile, outDist);
map<string, string> thisFilePair; thisFilePair[outDist] = outName;
dists.push_back(thisFilePair);
for (int j = 0; j < thisDB->getNumSeqs(); j++) { outNonSingleton << thisDB->getSeq(j).getName() << endl; }
}else {
util.mothurRemove(thisDistanceFile);
util.mothurRemove(outName);
}
delete thisDB;
}
outNonSingleton.close();
if (!util.isBlank(nonSingletonsFile)) { //there are non singletons, so remove them to find the singletons
//get singletons
if (namefile != "") {
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(namefile); }
singleton = thisOutputDir + util.getRootName(util.getSimpleName(namefile)) + "singletons.temp";
}
if (countfile != "") {
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(countfile); }
singleton = thisOutputDir + util.getRootName(util.getSimpleName(countfile)) + "singletons.temp";
}
pair<string,string> dupsFile(namefile, singleton); string dupsFormat = "name";
if (countfile != "") { dupsFile.first = countfile; dupsFormat = "count"; }
m->mothurOut("/******************************************/\n");
m->mothurOut("Finding singletons (ignore 'Removing group' messages):\n\nRunning command: remove.seqs()\n");
Command* removeCommand = new RemoveSeqsCommand(nonSingletonsFile, dupsFile, dupsFormat);
delete removeCommand;
m->mothurOut("/******************************************/\n");
}else { //every seqs is a singleton
if (namefile != "") { singleton = namefile; }
else if (countfile != "") { singleton = countfile; }
}
if (util.isBlank(singleton)) {
util.mothurRemove(singleton);
singleton = "none";
}
util.mothurRemove(nonSingletonsFile);
if (m->getControl_pressed()) { for (int i = 0; i < dists.size(); i++) { util.mothurRemove((dists[i].begin()->first)); util.mothurRemove((dists[i].begin()->second)); } dists.clear(); }
return 0;
}
catch(exception& e) {
m->errorOut(e, "SplitMatrix", "createDistanceFilesFromTax");
exit(1);
}
}
/***********************************************************************/
int SplitMatrix::createFastaFilesFromTax(vector<vector<string> >& seqGroups, vector<string> groupNames){
try {
int numGroups = seqGroups.size();
string thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(fastafile); }
singleton = "none";
ifstream inFASTA; util.openInputFile(fastafile, inFASTA);
SequenceDB fullDB(inFASTA); inFASTA.close();
if (!fullDB.sameLength()) {
m->mothurOut("[ERROR]: Cannot cluster using vsearch with unaligned sequences, please correct.\n\n"); m->setControl_pressed(true);
}
if (m->getDebug()) { for (int i = 0; i < numGroups; i++) { m->mothurOut("[DEBUG]: Number of unique sequences for group " + groupNames[i] + " (" + toString(i+1) + " of " + toString(numGroups) + "): " + toString(seqGroups[i].size()) + "\n\n"); } }
//process each group
for (int i = 0; i < numGroups; i++) {
if (m->getControl_pressed()) { for (int i = 0; i < dists.size(); i++) { util.mothurRemove((dists[i].begin()->first)); util.mothurRemove((dists[i].begin()->second)); } dists.clear(); return 0; }
unordered_set<string> thisGroupsNames = util.mothurConvert(seqGroups[i]);
m->mothurOut("/******************************************/\n");
m->mothurOut("Selecting sequences for group " + groupNames[i] + " (" + toString(i+1) + " of " + toString(numGroups) + ")\nNumber of unique sequences: " + toString(seqGroups[i].size()) + "\n\n");
string outName = "";
if (namefile != "") {
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(namefile); }
outName = thisOutputDir + util.getRootName(util.getSimpleName(namefile)) + toString(i) + ".name.temp";
}
if (countfile != "") {
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(countfile); }
outName = thisOutputDir + util.getRootName(util.getSimpleName(countfile)) + toString(i) + ".count.temp";
}
pair<string, string> dupsFile(namefile, outName); string dupsFormat = "name";
if (countfile != "") { dupsFile.first = countfile; dupsFormat = "count"; }
Command* getCommand = new GetSeqsCommand(thisGroupsNames, nullStringPair, nullStringPair, dupsFile, dupsFormat);
delete getCommand;
StorageDatabase* thisDB;
thisOutputDir = outputDir;
if (outputDir == "") { thisOutputDir += util.hasPath(fastafile); }
string outFasta = thisOutputDir + util.getRootName(util.getSimpleName(fastafile)) + toString(i) + ".fastatemp";
thisDB = new SequenceDB(fullDB, thisGroupsNames);
thisDB->print(outFasta);
delete thisDB;
map<string, string> thisFilePair; thisFilePair[outFasta] = outName;
dists.push_back(thisFilePair);
}
if (m->getControl_pressed()) { for (int i = 0; i < dists.size(); i++) { util.mothurRemove((dists[i].begin()->first)); util.mothurRemove((dists[i].begin()->second)); } dists.clear(); }
return 0;
}
catch(exception& e) {
m->errorOut(e, "SplitMatrix", "createDistanceFilesFromTax");
exit(1);
}
}
/********************************************************************************************************************/
//sorts biggest to smallest
inline bool compareFileSizes(map<string, string> left, map<string, string> right){
FILE * pFile;
long leftsize = 0;
//get num bytes in file
string filename = left.begin()->first;
pFile = fopen (filename.c_str(),"rb");
string error = "Error opening " + filename;
if (pFile==nullptr) perror (error.c_str());
else{
fseek (pFile, 0, SEEK_END);
leftsize=ftell (pFile);
fclose (pFile);
}
FILE * pFile2;
long rightsize = 0;
//get num bytes in file
filename = right.begin()->first;
pFile2 = fopen (filename.c_str(),"rb");
error = "Error opening " + filename;
if (pFile2==nullptr) perror (error.c_str());
else{
fseek (pFile2, 0, SEEK_END);
rightsize=ftell (pFile2);
fclose (pFile2);
}
return (leftsize > rightsize);
}
/***********************************************************************/
//returns map of distance files -> namefile sorted by distance file size
vector< map< string, string> > SplitMatrix::getDistanceFiles(){
try {
sort(dists.begin(), dists.end(), compareFileSizes);
return dists;
}
catch(exception& e) {
m->errorOut(e, "SplitMatrix", "getDistanceFiles");
exit(1);
}
}
//********************************************************************************************************************/
|
