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
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
|
/*
* chimeraperseuscommand.cpp
* Mothur
*
* Created by westcott on 10/26/11.
* Copyright 2011 Schloss Lab. All rights reserved.
*
*/
#include "chimeraperseuscommand.h"
#include "uniqueseqscommand.h"
#include "sequence.hpp"
#include "counttable.h"
#include "sequencecountparser.h"
#include "removeseqscommand.h"
//**********************************************************************************************************************
vector<string> ChimeraPerseusCommand::setParameters(){
try {
CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","chimera-accnos",false,true,true); parameters.push_back(pfasta);
CommandParameter pname("name", "InputTypes", "", "", "NameCount", "NameCount", "none","",false,false,true); parameters.push_back(pname);
CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "NameCount", "none","",false,false,true); parameters.push_back(pcount);
CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","",false,false,true); parameters.push_back(pgroup);
CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors);
CommandParameter pdups("dereplicate", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pdups);
CommandParameter premovechimeras("removechimeras", "Boolean", "", "t", "", "", "","fasta",false,false); parameters.push_back(premovechimeras);
CommandParameter pseed("seed", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pseed);
CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
CommandParameter pcutoff("cutoff", "Number", "", "0.5", "", "", "","",false,false); parameters.push_back(pcutoff);
CommandParameter palpha("alpha", "Number", "", "-5.54", "", "", "","",false,false); parameters.push_back(palpha);
CommandParameter pbeta("beta", "Number", "", "0.33", "", "", "","",false,false); parameters.push_back(pbeta);
abort = false; calledHelp = false;
vector<string> tempOutNames;
outputTypes["chimera"] = tempOutNames;
outputTypes["accnos"] = tempOutNames;
outputTypes["count"] = tempOutNames;
outputTypes["fasta"] = tempOutNames;
vector<string> myArray;
for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
return myArray;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "setParameters");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraPerseusCommand::getHelpString(){
try {
string helpString = "";
helpString += "The chimera.perseus command reads a fastafile and namefile or countfile and outputs potentially chimeric sequences.\n";
helpString += "The chimera.perseus command parameters are fasta, name, group, cutoff, processors, dereplicate, alpha and beta.\n";
helpString += "The fasta parameter allows you to enter the fasta file containing your potentially chimeric sequences, and is required, unless you have a valid current fasta file. \n";
helpString += "The name parameter allows you to provide a name file associated with your fasta file.\n";
helpString += "The count parameter allows you to provide a count file associated with your fasta file. A count or name file is required. When you use a count file with group info and dereplicate=T, mothur will create a *.pick.count_table file containing seqeunces after chimeras are removed.\n";
helpString += "The group parameter allows you to provide a group file. When checking sequences, only sequences from the same group as the query sequence will be used as the reference. \n";
helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n";
helpString += "If the dereplicate parameter is false, then if one group finds the seqeunce to be chimeric, then all groups find it to be chimeric, default=f.\n";
helpString += "The removechimeras parameter allows you to indicate you would like to automatically remove the sequences that are flagged as chimeric. Default=t.\n";
helpString += "The alpha parameter .... The default is -5.54. \n";
helpString += "The beta parameter .... The default is 0.33. \n";
helpString += "The cutoff parameter .... The default is 0.50. \n";
helpString += "The chimera.perseus command should be in the following format: \n";
helpString += "chimera.perseus(fasta=yourFastaFile, name=yourNameFile) \n";
helpString += "Example: chimera.perseus(fasta=AD.align, name=AD.names) \n";
return helpString;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "getHelpString");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraPerseusCommand::getOutputPattern(string type) {
try {
string pattern = "";
if (type == "chimera") { pattern = "[filename],perseus.chimeras"; }
else if (type == "accnos") { pattern = "[filename],perseus.accnos"; }
else if (type == "fasta") { pattern = "[filename],perseus.fasta"; }
else if (type == "count") { pattern = "[filename],perseus.count_table"; }
else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->setControl_pressed(true); }
return pattern;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "getOutputPattern");
exit(1);
}
}
//***************************************************************************************************************
ChimeraPerseusCommand::ChimeraPerseusCommand(string option) : Command() {
try {
hasCount = false;
//allow user to run help
if(option == "help") { help(); abort = true; calledHelp = true; }
else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else if(option == "category") { abort = true; calledHelp = true; }
else {
OptionParser parser(option, setParameters());
map<string,string> parameters = parser.getParameters();
//check for required parameters
ValidParameters validParameter;
fastafile = validParameter.validFile(parameters, "fasta");
if (fastafile == "not found") {
fastafile = current->getFastaFile();
if (fastafile != "") { m->mothurOut("Using " + fastafile + " as input file for the fasta parameter.\n"); }
else { m->mothurOut("[ERROR]: You have no current fasta file and the fasta parameter is required.\n"); abort = true; }
}
else if (fastafile == "not open") { abort = true; }
else { current->setFastaFile(fastafile); }
bool hasName = false;
string namefile = validParameter.validFile(parameters, "name");
if (namefile == "not open") { namefile = ""; abort = true; }
else if (namefile == "not found") { namefile = ""; }
else { current->setNameFile(namefile); }
if (namefile != "") { hasName = true; }
countfile = validParameter.validFile(parameters, "count");
if (countfile == "not open") { countfile = ""; abort = true; }
else if (countfile == "not found") { countfile = ""; }
else { current->setCountFile(countfile); }
if (countfile != "") { hasCount = true; }
//make sure there is at least one valid file left
if (hasName && hasCount) { m->mothurOut("[ERROR]: You must enter ONLY ONE of the following: count or name.\n"); abort = true; }
if (!hasName && !hasCount) {
//if there is a current name file, use it, else look for current count file
string filename = current->getNameFile();
if (filename != "") { hasName = true; namefile = filename; m->mothurOut("Using " + filename + " as input file for the name parameter.\n"); }
else {
filename = current->getCountFile();
if (filename != "") { hasCount = true; countfile = filename; m->mothurOut("Using " + filename + " as input file for the count parameter.\n"); }
else { m->mothurOut("[ERROR]: You must provide a count or name file.\n"); abort = true; }
}
}
bool hasGroup = false;
string groupfile = validParameter.validFile(parameters, "group");
if (groupfile == "not open") { abort = true; }
else if (groupfile == "not found") { groupfile = ""; }
else { current->setGroupFile(groupfile); hasGroup = true; }
if (hasGroup && hasCount) { m->mothurOut("[ERROR]: You must enter ONLY ONE of the following: count or group.\n"); abort = true; }
string temp = validParameter.valid(parameters, "processors"); if (temp == "not found"){ temp = current->getProcessors(); }
processors = current->setProcessors(temp);
temp = validParameter.valid(parameters, "cutoff"); if (temp == "not found"){ temp = "0.50"; }
util.mothurConvert(temp, cutoff);
temp = validParameter.valid(parameters, "alpha"); if (temp == "not found"){ temp = "-5.54"; }
util.mothurConvert(temp, alpha);
temp = validParameter.valid(parameters, "beta"); if (temp == "not found"){ temp = "0.33"; }
util.mothurConvert(temp, beta);
temp = validParameter.valid(parameters, "dereplicate");
if (temp == "not found") { temp = "false"; }
dups = util.isTrue(temp);
temp = validParameter.valid(parameters, "removechimeras"); if (temp == "not found") { temp = "t"; }
removeChimeras = util.isTrue(temp);
if (!abort) {
if ((namefile != "") || (groupfile != "")) { //convert to count
string rootFileName = namefile;
if (rootFileName == "") { rootFileName = groupfile; }
if (outputdir == "") { outputdir = util.hasPath(rootFileName); }
string outputFileName = outputdir + util.getRootName(util.getSimpleName(rootFileName)) + "count_table";
CountTable ct; ct.createTable(namefile, groupfile, nullVector); ct.printCompressedTable(outputFileName);
outputNames.push_back(outputFileName);
current->setCountFile(outputFileName);
countfile = outputFileName;
hasCount = true;
}
}
}
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "ChimeraPerseusCommand");
exit(1);
}
}
/**************************************************************************************************/
struct perseusData {
Utils util;
MothurOut* m;
vector<seqData> sequences;
string group;
int count, numChimeras;
string chimeraFileName;
string accnosFileName;
double alpha, beta, cutoff;
perseusData(string cf, string ac, double a, double b, double c){
m = MothurOut::getInstance();
count = 0;
numChimeras = 0;
accnosFileName = ac;
chimeraFileName = cf;
alpha = a;
beta = b;
cutoff = c;
}
};
//**********************************************************************************************************************
//void driver(string chimeraFileName, vector<seqData>& sequences, string accnosFileName, int& numChimeras){
void driver(perseusData* params){
try {
vector<vector<double> > correctModel(4); //could be an option in the future to input own model matrix
for(int i=0;i<4;i++){ correctModel[i].resize(4); }
correctModel[0][0] = 0.000000; //AA
correctModel[1][0] = 11.619259; //CA
correctModel[2][0] = 11.694004; //TA
correctModel[3][0] = 7.748623; //GA
correctModel[1][1] = 0.000000; //CC
correctModel[2][1] = 7.619657; //TC
correctModel[3][1] = 12.852562; //GC
correctModel[2][2] = 0.000000; //TT
correctModel[3][2] = 10.964048; //TG
correctModel[3][3] = 0.000000; //GG
for(int i=0;i<4;i++){ for(int j=0;j<i;j++){ correctModel[j][i] = correctModel[i][j]; } }
int numSeqs = params->sequences.size();
int alignLength = params->sequences[0].sequence.size();
ofstream chimeraFile;
ofstream accnosFile;
params->util.openOutputFile(params->chimeraFileName, chimeraFile);
params->util.openOutputFile(params->accnosFileName, accnosFile);
Perseus myPerseus;
vector<vector<double> > binMatrix = myPerseus.binomial(alignLength);
chimeraFile << "SequenceIndex\tName\tDiffsToBestMatch\tBestMatchIndex\tBestMatchName\tDiffstToChimera\tIndexofLeftParent\tIndexOfRightParent\tNameOfLeftParent\tNameOfRightParent\tDistanceToBestMatch\tcIndex\t(cIndex - singleDist)\tloonIndex\tMismatchesToChimera\tMismatchToTrimera\tChimeraBreakPoint\tLogisticProbability\tTypeOfSequence\n";
vector<bool> chimeras(numSeqs, 0);
for(int i=0;i<numSeqs;i++){
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
vector<bool> restricted = chimeras;
vector<vector<int> > leftDiffs(numSeqs);
vector<vector<int> > leftMaps(numSeqs);
vector<vector<int> > rightDiffs(numSeqs);
vector<vector<int> > rightMaps(numSeqs);
vector<int> singleLeft, bestLeft;
vector<int> singleRight, bestRight;
int bestSingleIndex, bestSingleDiff;
vector<pwAlign> alignments(numSeqs);
int comparisons = myPerseus.getAlignments(i, params->sequences, alignments, leftDiffs, leftMaps, rightDiffs, rightMaps, bestSingleIndex, bestSingleDiff, restricted);
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
int minMismatchToChimera, leftParentBi, rightParentBi, breakPointBi;
string dummyA, dummyB;
if (params->sequences[i].sequence.size() < 3) {
chimeraFile << i << '\t' << params->sequences[i].seqName << "\t0\t0\tNull\t0\t0\t0\tNull\tNull\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\tgood" << endl;
}else if(comparisons >= 2){
minMismatchToChimera = myPerseus.getChimera(params->sequences, leftDiffs, rightDiffs, leftParentBi, rightParentBi, breakPointBi, singleLeft, bestLeft, singleRight, bestRight, restricted);
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
int minMismatchToTrimera = numeric_limits<int>::max();
int leftParentTri, middleParentTri, rightParentTri, breakPointTriA, breakPointTriB;
if(minMismatchToChimera >= 3 && comparisons >= 3){
minMismatchToTrimera = myPerseus.getTrimera(params->sequences, leftDiffs, leftParentTri, middleParentTri, rightParentTri, breakPointTriA, breakPointTriB, singleLeft, bestLeft, singleRight, bestRight, restricted);
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
}
double singleDist = myPerseus.modeledPairwiseAlignSeqs(params->sequences[i].sequence, params->sequences[bestSingleIndex].sequence, dummyA, dummyB, correctModel);
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
string type;
string chimeraRefSeq;
if(minMismatchToChimera - minMismatchToTrimera >= 3){
type = "trimera";
chimeraRefSeq = myPerseus.stitchTrimera(alignments, leftParentTri, middleParentTri, rightParentTri, breakPointTriA, breakPointTriB, leftMaps, rightMaps);
}
else{
type = "chimera";
chimeraRefSeq = myPerseus.stitchBimera(alignments, leftParentBi, rightParentBi, breakPointBi, leftMaps, rightMaps);
}
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
double chimeraDist = myPerseus.modeledPairwiseAlignSeqs(params->sequences[i].sequence, chimeraRefSeq, dummyA, dummyB, correctModel);
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
double cIndex = chimeraDist;//modeledPairwiseAlignSeqs(sequences[i].sequence, chimeraRefSeq);
double loonIndex = myPerseus.calcLoonIndex(params->sequences[i].sequence, params->sequences[leftParentBi].sequence, params->sequences[rightParentBi].sequence, breakPointBi, binMatrix);
if (params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); break; }
chimeraFile << i << '\t' << params->sequences[i].seqName << '\t' << bestSingleDiff << '\t' << bestSingleIndex << '\t' << params->sequences[bestSingleIndex].seqName << '\t';
chimeraFile << minMismatchToChimera << '\t' << leftParentBi << '\t' << rightParentBi << '\t' << params->sequences[leftParentBi].seqName << '\t' << params->sequences[rightParentBi].seqName << '\t';
chimeraFile << singleDist << '\t' << cIndex << '\t' << (cIndex - singleDist) << '\t' << loonIndex << '\t';
chimeraFile << minMismatchToChimera << '\t' << minMismatchToTrimera << '\t' << breakPointBi << '\t';
double probability = myPerseus.classifyChimera(singleDist, cIndex, loonIndex, params->alpha, params->beta);
chimeraFile << probability << '\t';
if(probability > params->cutoff){
chimeraFile << type << endl;
accnosFile << params->sequences[i].seqName << endl;
chimeras[i] = 1;
params->numChimeras++;
}
else{ chimeraFile << "good" << endl; }
}
else{
chimeraFile << i << '\t' << params->sequences[i].seqName << "\t0\t0\tNull\t0\t0\t0\tNull\tNull\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\tgood" << endl;
}
//report progress
if((i+1) % 100 == 0){ params->m->mothurOutJustToScreen("Processing sequence: " + toString(i+1) + "\n"); }
params->count++; //# of sequences completed. Used by calling function to check for failure
}
if((numSeqs) % 100 != 0){ params->m->mothurOutJustToScreen("Processing sequence: " + toString(numSeqs) + "\n"); }
if (!params->m->getControl_pressed()) { chimeraFile.close(); accnosFile.close(); }
}
catch(exception& e) {
params->m->errorOut(e, "ChimeraPerseusCommand", "driver");
exit(1);
}
}
//***************************************************************************************************************
int ChimeraPerseusCommand::execute(){
try{
if (abort) { if (calledHelp) { return 0; } return 2; }
m->mothurOut("Checking sequences from " + fastafile + " ...\n" );
long start = time(nullptr);
if (outputdir == "") { outputdir = util.hasPath(fastafile); }
map<string, string> variables;
variables["[filename]"] = outputdir + util.getRootName(util.getSimpleName(fastafile));
string outputFileName = getOutputFileName("chimera", variables);
string accnosFileName = getOutputFileName("accnos", variables);
string newCountFile = "";
if (countfile == "") { countfile = getCountFile(fastafile); hasCount=true; }
if (m->getControl_pressed()) { return 0; }
int numSeqs = 0; int numChimeras = 0;
if (hasCount) {
CountTable ct;
vector<string> groups;
if (ct.testGroups(countfile, groups)) { //fills groups if count file has them
variables["[filename]"] = outputdir + util.getRootName(util.getSimpleName(countfile));
newCountFile = getOutputFileName("count", variables);
vector<string> groups;
map<string, vector<string> > group2Files;
if (hasCount) {
current->setMothurCalling(true);
SequenceCountParser cparser(countfile, fastafile, nullVector);
current->setMothurCalling(false);
groups = cparser.getNamesOfGroups();
group2Files = cparser.getFiles();
}
if (m->getControl_pressed()) { return 0; }
//clears files
ofstream out, out1, out2;
util.openOutputFile(outputFileName, out); out.close();
util.openOutputFile(accnosFileName, out1); out1.close();
string countlist = accnosFileName+".byCount";
numSeqs = createProcessesGroups(group2Files, outputFileName, countlist, accnosFileName, newCountFile, groups, fastafile, countfile, numChimeras);
if (m->getControl_pressed()) { for (int j = 0; j < outputNames.size(); j++) { util.mothurRemove(outputNames[j]); } return 0; }
if (!dups) {
numChimeras = deconvoluteResults(outputFileName, accnosFileName);
}else {
CountTable newCount; newCount.readTable(countfile, true, false);
if (!util.isBlank(countlist)) {
ifstream in2; util.openInputFile(countlist, in2);
string name, group;
while (!in2.eof()) {
in2 >> name; gobble(in2); in2 >> group; gobble(in2);
newCount.setAbund(name, group, 0);
}
in2.close();
}
util.mothurRemove(countlist);
//print new *.pick.count_table
vector<string> namesInTable = newCount.printTable(newCountFile); //returns non zeroed names
outputNames.push_back(newCountFile); outputTypes["count"].push_back(newCountFile);
unordered_set<string> doNotRemove = util.mothurConvert(namesInTable);
//remove names we want to keep from accnos file.
unordered_set<string> accnosNames = util.readAccnos(accnosFileName);
ofstream out2; util.openOutputFile(accnosFileName, out2);
for (auto it = accnosNames.begin(); it != accnosNames.end(); it++) { if (doNotRemove.count(*it) == 0) { out2 << (*it) << endl; } }
out2.close();
}
util.mothurRemove(countlist);
m->mothurOut("The number of sequences checked may be larger than the number of unique sequences because some sequences are found in several samples.\n");
if (m->getControl_pressed()) { for (int j = 0; j < outputNames.size(); j++) { util.mothurRemove(outputNames[j]); } return 0; }
}else {
if (processors != 1) { m->mothurOut("Your count file does not contain group information, mothur can only use 1 processor, continuing.\n"); processors = 1; }
//read sequences and store sorted by frequency
ct.readTable(countfile, false, false);
vector<seqData> sequences = readFiles(fastafile, ct.getNameMap());
if (m->getControl_pressed()) { for (int j = 0; j < outputNames.size(); j++) { util.mothurRemove(outputNames[j]); } return 0; }
perseusData* dataBundle = new perseusData(outputFileName, accnosFileName, alpha, beta, cutoff);
dataBundle->sequences = sequences;
driver(dataBundle);
numSeqs = dataBundle->count; numChimeras = dataBundle->numChimeras;
delete dataBundle;
}
}
if (m->getControl_pressed()) { for (int j = 0; j < outputNames.size(); j++) { util.mothurRemove(outputNames[j]); } return 0; }
m->mothurOut("\nIt took " + toString(time(nullptr) - start) + " secs to check " + toString(numSeqs) + " sequences. " + toString(numChimeras) + " chimeras were found.\n");
outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName);
outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName);
if (removeChimeras) {
if (!util.isBlank(accnosFileName)) {
m->mothurOut("\nRemoving chimeras from your input files:\n");
string inputString = "fasta=" + fastafile + ", accnos=" + accnosFileName;
if ((countfile != "") && (!dups)) { inputString += ", count=" + countfile; }
m->mothurOut("/******************************************/\n");
m->mothurOut("Running command: remove.seqs(" + inputString + ")\n");
current->setMothurCalling(true);
Command* removeCommand = new RemoveSeqsCommand(inputString);
removeCommand->execute();
map<string, vector<string> > filenames = removeCommand->getOutputFiles();
delete removeCommand;
current->setMothurCalling(false);
m->mothurOut("/******************************************/\n");
if (countfile != "") {
if (!dups) { //dereplicate=f, so remove sequences where any sample found the reads to be chimeric
map<string, string> variables;
variables["[filename]"] = outputdir + util.getRootName(util.getSimpleName(countfile));
string currentName = getOutputFileName("count", variables);
util.renameFile(filenames["count"][0], currentName);
util.mothurRemove(filenames["count"][0]);
outputNames.push_back(currentName); outputTypes["count"].push_back(currentName);
}//else, mothur created a modified count file removing chimeras by sample. No need to include count file on remove.seqs command. Deconvolute function created modified count table already
}
map<string, string> variables;
variables["[filename]"] = outputdir + util.getRootName(util.getSimpleName(fastafile));
string currentName = getOutputFileName("fasta", variables);
util.renameFile(filenames["fasta"][0], currentName);
util.mothurRemove(filenames["fasta"][0]);
outputNames.push_back(currentName); outputTypes["fasta"].push_back(currentName);
}else { m->mothurOut("\nNo chimeras found, skipping remove.seqs.\n"); }
}
//set accnos file as new current accnosfile
string currentName = "";
itTypes = outputTypes.find("accnos");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { currentName = (itTypes->second)[0]; current->setAccnosFile(currentName); }
}
itTypes = outputTypes.find("count");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { currentName = (itTypes->second)[0]; current->setCountFile(currentName); }
}
itTypes = outputTypes.find("fasta");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { currentName = (itTypes->second)[0]; current->setFastaFile(currentName); }
}
m->mothurOut("\nOutput File Names: \n");
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
m->mothurOutEndLine();
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "execute");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraPerseusCommand::getCountFile(string& inputFile){
try {
string countFile = "";
m->mothurOut("\nNo count file given, running unique.seqs command to generate one.\n\n");
//use unique.seqs to create new name and fastafile
string inputString = "format=count, fasta=" + inputFile;
m->mothurOut("/******************************************/\n");
m->mothurOut("Running command: unique.seqs(" + inputString + ")\n");
current->setMothurCalling(true);
Command* uniqueCommand = new UniqueSeqsCommand(inputString);
uniqueCommand->execute();
map<string, vector<string> > filenames = uniqueCommand->getOutputFiles();
delete uniqueCommand;
current->setMothurCalling(false);
m->mothurOut("/******************************************/\n");
countFile = filenames["count"][0];
inputFile = filenames["fasta"][0];
return countFile;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "getNamesFile");
exit(1);
}
}
/**************************************************************************************************/
struct perseusGroupsData {
string fastafile;
string dupsfile;
string chimeraFileName;
string accnosFileName;
string countlist;
map<string, vector<string> > parsedFiles;
bool hasCount, dups;
int threadID, count, numChimeras;
double alpha, beta, cutoff;
vector<string> groups;
Utils util;
MothurOut* m;
perseusGroupsData(){}
perseusGroupsData(map<string, vector<string> >& g2f,bool dps, bool hc, double a, double b, double c, string o, string f, string n, string ac, string ctlist, vector<string> gr, int tid) {
alpha = a;
beta = b;
cutoff = c;
fastafile = f;
dupsfile = n;
chimeraFileName = o;
countlist = ctlist;
accnosFileName = ac;
m = MothurOut::getInstance();
threadID = tid;
groups = gr;
hasCount = hc;
dups = dps;
count = 0;
numChimeras = 0;
parsedFiles = g2f;
}
};
//**********************************************************************************************************************
vector<seqData> loadSequences(map<string, int>& nameMap, string thisGroupsFastaFile, perseusGroupsData* params){
try {
bool error = false;
vector<seqData> sequences;
ifstream in; params->util.openInputFile(thisGroupsFastaFile, in);
vector<seqPriorityNode> nameVector;
map<string, int>::iterator itNameMap;
while (!in.eof()) {
if (params->m->getControl_pressed()) { break; }
Sequence seq(in); gobble(in);
itNameMap = nameMap.find(seq.getName());
if (itNameMap == nameMap.end()){
error = true;
params->m->mothurOut("[ERROR]: " + seq.getName() + " is in your fastafile, but is not in your name or count file, please correct.\n");
}else {
int num = itNameMap->second;
seq.setAligned(params->util.removeNs(seq.getUnaligned()));
sequences.push_back(seqData(seq.getName(), seq.getUnaligned(), num));
}
}
in.close();
if (error) { params->m->setControl_pressed(true); }
//sort by frequency
sort(sequences.rbegin(), sequences.rend());
return sequences;
}
catch(exception& e) {
params->m->errorOut(e, "ChimeraPerseusCommand", "loadSequences");
exit(1);
}
}
//**********************************************************************************************************************
//string outputFName, string accnos, string countlist, int start, int end, vector<string> groups
void driverGroups(perseusGroupsData* params){
try {
//clears files
ofstream out, out1, out2;
params->util.openOutputFile(params->chimeraFileName, out); out.close();
params->util.openOutputFile(params->accnosFileName, out1); out1.close();
int totalSeqs = 0;
ofstream outCountList;
if (params->hasCount && params->dups) { params->util.openOutputFile(params->countlist, outCountList); }
for (map<string, vector<string> >::iterator it = params->parsedFiles.begin(); it != params->parsedFiles.end(); it++) {
long start = time(nullptr); if (params->m->getControl_pressed()) { break; }
string thisGroup = it->first;
map<string, int> nameMap;
if (params->hasCount) {
CountTable ct; ct.readTable(it->second[1], false, true);
nameMap = ct.getNameMap();
}
params->m->mothurOut("\nChecking sequences from group " + thisGroup + "...\n");
perseusData* driverParams = new perseusData((params->chimeraFileName+thisGroup), (params->accnosFileName+thisGroup), params->alpha, params->beta, params->cutoff);
driverParams->sequences = loadSequences(nameMap, it->second[0], params);
if (params->m->getControl_pressed()) { break; }
driver(driverParams);
totalSeqs += driverParams->count;
params->numChimeras += driverParams->numChimeras;
if (params->m->getControl_pressed()) { break; }
if (params->dups) {
if (!params->util.isBlank(driverParams->accnosFileName)) {
ifstream in;
params->util.openInputFile(driverParams->accnosFileName, in);
string name;
if (params->hasCount) {
while (!in.eof()) {
in >> name; gobble(in);
outCountList << name << '\t' << thisGroup << endl;
}
in.close();
}
}
}
//append files
params->util.appendFiles(driverParams->chimeraFileName, params->chimeraFileName); params->util.mothurRemove(driverParams->chimeraFileName);
params->util.appendFiles(driverParams->accnosFileName, params->accnosFileName); params->util.mothurRemove(driverParams->accnosFileName);
params->m->mothurOut("\nIt took " + toString(time(nullptr) - start) + " secs to check " + toString(driverParams->count) + " sequences from group " + thisGroup + ".\n");
delete driverParams;
}
if (params->hasCount && params->dups) { outCountList.close(); }
params->count = totalSeqs;
}
catch(exception& e) {
params->m->errorOut(e, "ChimeraPerseusCommand", "driverGroups");
exit(1);
}
}
//**********************************************************************************************************************
vector<seqData> ChimeraPerseusCommand::readFiles(string inputFile, map<string, int> nameMap){
try {
map<string, int>::iterator it;
//read fasta file and create sequenceData structure - checking for file mismatches
vector<seqData> sequences;
bool error = false;
ifstream in; util.openInputFile(inputFile, in);
alignLength = 0;
while (!in.eof()) {
if (m->getControl_pressed()) { in.close(); return sequences; }
Sequence temp(in); gobble(in);
it = nameMap.find(temp.getName());
if (it == nameMap.end()) { error = true; m->mothurOut("[ERROR]: " + temp.getName() + " is in your fasta file and not in your namefile, please correct.\n"); }
else {
temp.setAligned(util.removeNs(temp.getUnaligned()));
sequences.push_back(seqData(temp.getName(), temp.getUnaligned(), it->second));
if (temp.getUnaligned().length() > alignLength) { alignLength = temp.getUnaligned().length(); }
}
}
in.close();
if (error) { m->setControl_pressed(true); }
//sort by frequency
sort(sequences.rbegin(), sequences.rend());
return sequences;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "readFiles");
exit(1);
}
}
/**************************************************************************************************/
//perseusData(vector<seqData>& s, double a, double b, double c, string o, string ac, MothurOut* mout)
//numSeqs = createProcessesGroups(outputFileName, countlist, accnosFileName, newCountFile, groups, fastafile, countfile, numChimeras);
int ChimeraPerseusCommand::createProcessesGroups(map<string, vector<string> >& parsedFiles, string outputFName, string countlisttemp, string accnos, string newCountFile, vector<string> groups, string fasta, string dupsFile, int& numChimeras) {
try {
numChimeras = 0;
//sanity check
if (groups.size() < processors) { processors = groups.size(); m->mothurOut("Reducing processors to " + toString(groups.size()) + ".\n"); }
//divide the groups between the processors
vector<linePair> lines;
int remainingPairs = groups.size();
int startIndex = 0;
for (int remainingProcessors = processors; remainingProcessors > 0; remainingProcessors--) {
int numPairs = remainingPairs; //case for last processor
if (remainingProcessors != 1) { numPairs = ceil(remainingPairs / remainingProcessors); }
lines.push_back(linePair(startIndex, (startIndex+numPairs))); //startIndex, endIndex
startIndex = startIndex + numPairs;
remainingPairs = remainingPairs - numPairs;
}
//create array of worker threads
vector<std::thread*> workerThreads;
vector<perseusGroupsData*> data;
long long num = 0;
time_t start, end;
time(&start);
//Lauch worker threads
for (int i = 0; i < processors-1; i++) {
string extension = toString(i+1) + ".temp";
vector<string> thisGroups;
map<string, vector<string> > thisGroupsParsedFiles;
for (int j = lines[i+1].start; j < lines[i+1].end; j++) {
map<string, vector<string> >::iterator it = parsedFiles.find(groups[j]);
if (it != parsedFiles.end()) {
thisGroupsParsedFiles[groups[j]] = (it->second);
thisGroups.push_back(groups[j]);
}
else { m->mothurOut("[ERROR]: missing files for group " + groups[j] + ", skipping\n"); }
}
perseusGroupsData* dataBundle = new perseusGroupsData(thisGroupsParsedFiles, dups, hasCount, alpha, beta, cutoff, (outputFName+extension), fasta, dupsFile, (accnos+extension), (countlisttemp+extension), thisGroups, (i+1));
data.push_back(dataBundle);
workerThreads.push_back(new std::thread(driverGroups, dataBundle));
}
vector<string> thisGroups;
map<string, vector<string> > thisGroupsParsedFiles;
for (int j = lines[0].start; j < lines[0].end; j++) {
map<string, vector<string> >::iterator it = parsedFiles.find(groups[j]);
if (it != parsedFiles.end()) {
thisGroupsParsedFiles[groups[j]] = (it->second);
thisGroups.push_back(groups[j]);
}
else { m->mothurOut("[ERROR]: missing files for group " + groups[j] + ", skipping\n"); }
}
perseusGroupsData* dataBundle = new perseusGroupsData(thisGroupsParsedFiles, dups, hasCount, alpha, beta, cutoff, outputFName, fasta, dupsFile, accnos, countlisttemp, thisGroups, 0);
driverGroups(dataBundle);
num = dataBundle->count;
numChimeras = dataBundle->numChimeras;
for (int i = 0; i < processors-1; i++) {
workerThreads[i]->join();
num += data[i]->count;
numChimeras += data[i]->numChimeras;
string extension = toString(i+1) + ".temp";
util.appendFiles((outputFName+extension), outputFName);
util.mothurRemove((outputFName+extension));
util.appendFiles((accnos+extension), accnos);
util.mothurRemove((accnos+extension));
util.appendFiles((countlisttemp+extension), countlisttemp);
util.mothurRemove((countlisttemp+extension));
delete data[i];
delete workerThreads[i];
}
delete dataBundle;
time(&end);
m->mothurOut("It took " + toString(difftime(end, start)) + " secs to check " + toString(num) + " sequences.\n\n");
return num;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "createProcessesGroups");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraPerseusCommand::deconvoluteResults(string outputFileName, string accnosFileName){
try {
int total = 0;
unordered_set<string> chimerasInFile = util.readAccnos(accnosFileName);//this is so if a sequence is found to be chimera in several samples we dont write it to the results file more than once
util.printAccnos(accnosFileName, chimerasInFile);
//edit chimera file
ifstream in; util.openInputFile(outputFileName, in);
ofstream out; util.openOutputFile(outputFileName+".temp", out); out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint);
int DiffsToBestMatch, BestMatchIndex, DiffstToChimera, IndexofLeftParent, IndexOfRightParent;
float temp1,temp2, temp3, temp4, temp5, temp6, temp7, temp8;
string index, BestMatchName, parent1, parent2, flag;
string name = "";
set<string> namesInFile;
//assumptions - in file each read will always look like
/*
SequenceIndex Name DiffsToBestMatch BestMatchIndex BestMatchName DiffstToChimera IndexofLeftParent IndexOfRightParent NameOfLeftParent NameOfRightParent DistanceToBestMatch cIndex (cIndex - singleDist) loonIndex MismatchesToChimera MismatchToTrimera ChimeraBreakPoint LogisticProbability TypeOfSequence
0 F01QG4L02JVBQY 0 0 Null 0 0 0 Null Null 0.0 0.0 0.0 0.0 0 0 0 0.0 0.0 good
1 F01QG4L02ICTC6 0 0 Null 0 0 0 Null Null 0.0 0.0 0.0 0.0 0 0 0 0.0 0.0 good
2 F01QG4L02JZOEC 48 0 F01QG4L02JVBQY 47 0 0 F01QG4L02JVBQY F01QG4L02JVBQY 2.0449 2.03545 -0.00944493 0 47 2147483647 138 0 good
3 F01QG4L02G7JEC 42 0 F01QG4L02JVBQY 40 1 0 F01QG4L02ICTC6 F01QG4L02JVBQY 1.87477 1.81113 -0.0636404 5.80145 40 2147483647 25 0 good
*/
//get and print headers
BestMatchName = util.getline(in); gobble(in);
out << BestMatchName << endl;
while (!in.eof()) {
if (m->getControl_pressed()) { in.close(); out.close(); util.mothurRemove((outputFileName+".temp")); return 0; }
bool print = false;
in >> index; gobble(in);
if (index != "SequenceIndex") { //if you are not a header line, there will be a header line for each group if group file is given
in >> name; gobble(in);
in >> DiffsToBestMatch; gobble(in);
in >> BestMatchIndex; gobble(in);
in >> BestMatchName; gobble(in);
in >> DiffstToChimera; gobble(in);
in >> IndexofLeftParent; gobble(in);
in >> IndexOfRightParent; gobble(in);
in >> parent1; gobble(in);
in >> parent2; gobble(in);
in >> temp1 >> temp2 >> temp3 >> temp4 >> temp5 >> temp6 >> temp7 >> temp8 >> flag; gobble(in);
//is this name already in the file
auto itNames = namesInFile.find((name));
if (itNames == namesInFile.end()) { //no not in file
if (flag == "good") { //are you really a no??
//is this sequence really not chimeric??
auto itChimeras = chimerasInFile.find(name);
//then you really are a no so print, otherwise skip
if (itChimeras == chimerasInFile.end()) { print = true; }
}else{ print = true; }
}
if (print) {
namesInFile.insert(name);
out << index << '\t' << name << '\t' << DiffsToBestMatch << '\t' << BestMatchIndex << '\t';
out << BestMatchName << '\t' << DiffstToChimera << '\t' << IndexofLeftParent << '\t' << IndexOfRightParent << '\t' << parent1 << '\t' << parent2 << '\t';
out << temp1 << '\t' << temp2 << '\t' << temp3 << '\t' << temp4 << '\t' << temp5 << '\t' << temp6 << '\t' << temp7 << '\t' << temp8 << '\t' << flag << endl;
}
}else { index = util.getline(in); gobble(in); }
}
in.close();
out.close();
util.mothurRemove(outputFileName);
rename((outputFileName+".temp").c_str(), outputFileName.c_str());
return total;
}
catch(exception& e) {
m->errorOut(e, "ChimeraPerseusCommand", "deconvoluteResults");
exit(1);
}
}
//**********************************************************************************************************************
|
