forked from mothur/mothur
-
Notifications
You must be signed in to change notification settings - Fork 1
/
chimeraslayercommand.cpp
2303 lines (1869 loc) · 98.1 KB
/
chimeraslayercommand.cpp
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
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* chimeraslayercommand.cpp
* Mothur
*
* Created by westcott on 3/31/10.
* Copyright 2010 Schloss Lab. All rights reserved.
*
*/
#include "chimeraslayercommand.h"
#include "deconvolutecommand.h"
#include "referencedb.h"
#include "sequenceparser.h"
#include "counttable.h"
//**********************************************************************************************************************
vector<string> ChimeraSlayerCommand::setParameters(){
try {
CommandParameter ptemplate("reference", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(ptemplate);
CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","chimera-accnos",false,true,true); parameters.push_back(pfasta);
CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","",false,false,true); parameters.push_back(pname);
CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","",false,false,true); parameters.push_back(pcount);
CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","",false,false,true); parameters.push_back(pgroup);
CommandParameter pwindow("window", "Number", "", "50", "", "", "","",false,false); parameters.push_back(pwindow);
CommandParameter pksize("ksize", "Number", "", "7", "", "", "","",false,false); parameters.push_back(pksize);
CommandParameter pmatch("match", "Number", "", "5.0", "", "", "","",false,false); parameters.push_back(pmatch);
CommandParameter pmismatch("mismatch", "Number", "", "-4.0", "", "", "","",false,false); parameters.push_back(pmismatch);
CommandParameter pminsim("minsim", "Number", "", "90", "", "", "","",false,false); parameters.push_back(pminsim);
CommandParameter pmincov("mincov", "Number", "", "70", "", "", "","",false,false); parameters.push_back(pmincov);
CommandParameter pminsnp("minsnp", "Number", "", "10", "", "", "","",false,false); parameters.push_back(pminsnp);
CommandParameter pminbs("minbs", "Number", "", "90", "", "", "","",false,false); parameters.push_back(pminbs);
CommandParameter psearch("search", "Multiple", "kmer-blast", "blast", "", "", "","",false,false); parameters.push_back(psearch);
CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors);
CommandParameter prealign("realign", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(prealign);
CommandParameter ptrim("trim", "Boolean", "", "F", "", "", "","fasta",false,false); parameters.push_back(ptrim);
CommandParameter psplit("split", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psplit);
CommandParameter pnumwanted("numwanted", "Number", "", "15", "", "", "","",false,false); parameters.push_back(pnumwanted);
CommandParameter piters("iters", "Number", "", "1000", "", "", "","",false,false); parameters.push_back(piters);
CommandParameter pdivergence("divergence", "Number", "", "1.007", "", "", "","",false,false); parameters.push_back(pdivergence);
CommandParameter pdups("dereplicate", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pdups);
CommandParameter pparents("parents", "Number", "", "3", "", "", "","",false,false); parameters.push_back(pparents);
CommandParameter pincrement("increment", "Number", "", "5", "", "", "","",false,false); parameters.push_back(pincrement);
CommandParameter pblastlocation("blastlocation", "String", "", "", "", "", "","",false,false); parameters.push_back(pblastlocation);
CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
CommandParameter psave("save", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psave);
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, "ChimeraSlayerCommand", "setParameters");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraSlayerCommand::getHelpString(){
try {
string helpString = "";
helpString += "The chimera.slayer command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n";
helpString += "This command was modeled after the chimeraSlayer written by the Broad Institute.\n";
helpString += "The chimera.slayer command parameters are fasta, name, group, template, processors, dereplicate, trim, ksize, window, match, mismatch, divergence. minsim, mincov, minbs, minsnp, parents, search, iters, increment, numwanted, blastlocation and realign.\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, if you are using reference=self. \n";
helpString += "The group parameter allows you to provide a group file. The group file can be used with a namesfile and reference=self. When checking sequences, only sequences from the same group as the query sequence will be used as the reference. \n";
helpString += "The count parameter allows you to provide a count file. The count file reference=self. If your count file contains group information, when checking sequences, only sequences from the same group as the query sequence will be used as the reference. 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 += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amazon.fasta \n";
helpString += "The reference parameter allows you to enter a reference file containing known non-chimeric sequences, and is required. You may also set template=self, in this case the abundant sequences will be used as potential parents. \n";
helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n";
#ifdef USE_MPI
helpString += "When using MPI, the processors parameter is set to the number of MPI processes running. \n";
#endif
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 trim parameter allows you to output a new fasta file containing your sequences with the chimeric ones trimmed to include only their longest piece, default=F. \n";
helpString += "The split parameter allows you to check both pieces of non-chimeric sequence for chimeras, thus looking for trimeras and quadmeras. default=F. \n";
helpString += "The window parameter allows you to specify the window size for searching for chimeras, default=50. \n";
helpString += "The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default=5.\n";
helpString += "The numwanted parameter allows you to specify how many sequences you would each query sequence compared with, default=15.\n";
helpString += "The ksize parameter allows you to input kmersize, default is 7, used if search is kmer. \n";
helpString += "The match parameter allows you to reward matched bases in blast search, default is 5. \n";
helpString += "The parents parameter allows you to select the number of potential parents to investigate from the numwanted best matches after rating them, default is 3. \n";
helpString += "The mismatch parameter allows you to penalize mismatched bases in blast search, default is -4. \n";
helpString += "The divergence parameter allows you to set a cutoff for chimera determination, default is 1.007. \n";
helpString += "The iters parameter allows you to specify the number of bootstrap iters to do with the chimeraslayer method, default=1000.\n";
helpString += "The minsim parameter allows you to specify a minimum similarity with the parent fragments, default=90. \n";
helpString += "The mincov parameter allows you to specify minimum coverage by closest matches found in template. Default is 70, meaning 70%. \n";
helpString += "The minbs parameter allows you to specify minimum bootstrap support for calling a sequence chimeric. Default is 90, meaning 90%. \n";
helpString += "The minsnp parameter allows you to specify percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default: 10) \n";
helpString += "The search parameter allows you to specify search method for finding the closest parent. Choices are blast, and kmer, default blast. \n";
helpString += "The realign parameter allows you to realign the query to the potential parents. Choices are true or false, default true. \n";
helpString += "The blastlocation parameter allows you to specify the location of your blast executable. By default mothur will look in ./blast/bin relative to mothur's executable. \n";
helpString += "If the save parameter is set to true the reference sequences will be saved in memory, to clear them later you can use the clear.memory command. Default=f.";
helpString += "The chimera.slayer command should be in the following format: \n";
helpString += "chimera.slayer(fasta=yourFastaFile, reference=yourTemplate, search=yourSearch) \n";
helpString += "Example: chimera.slayer(fasta=AD.align, reference=core_set_aligned.imputed.fasta, search=kmer) \n";
helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n";
return helpString;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "getHelpString");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraSlayerCommand::getOutputPattern(string type) {
try {
string pattern = "";
if (type == "chimera") { pattern = "[filename],slayer.chimeras"; }
else if (type == "accnos") { pattern = "[filename],slayer.accnos"; }
else if (type == "fasta") { pattern = "[filename],slayer.fasta"; }
else if (type == "count") { pattern = "[filename],slayer.pick.count_table"; }
else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
return pattern;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "getOutputPattern");
exit(1);
}
}
//**********************************************************************************************************************
ChimeraSlayerCommand::ChimeraSlayerCommand(){
try {
abort = true; calledHelp = true;
setParameters();
vector<string> tempOutNames;
outputTypes["chimera"] = tempOutNames;
outputTypes["accnos"] = tempOutNames;
outputTypes["fasta"] = tempOutNames;
outputTypes["count"] = tempOutNames;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "ChimeraSlayerCommand");
exit(1);
}
}
//***************************************************************************************************************
ChimeraSlayerCommand::ChimeraSlayerCommand(string option) {
try {
abort = false; calledHelp = false;
ReferenceDB* rdb = ReferenceDB::getInstance();
hasCount = false;
hasName = false;
//allow user to run help
if(option == "help") { help(); abort = true; calledHelp = true; }
else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else {
vector<string> myArray = setParameters();
OptionParser parser(option);
map<string,string> parameters = parser.getParameters();
ValidParameters validParameter("chimera.slayer");
map<string,string>::iterator it;
//check to make sure all parameters are valid for command
for (it = parameters.begin(); it != parameters.end(); it++) {
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
vector<string> tempOutNames;
outputTypes["chimera"] = tempOutNames;
outputTypes["accnos"] = tempOutNames;
outputTypes["fasta"] = tempOutNames;
outputTypes["count"] = tempOutNames;
//if the user changes the input directory command factory will send this info to us in the output parameter
string inputDir = validParameter.validFile(parameters, "inputdir", false);
if (inputDir == "not found"){ inputDir = ""; }
//check for required parameters
fastafile = validParameter.validFile(parameters, "fasta", false);
if (fastafile == "not found") {
//if there is a current fasta file, use it
string filename = m->getFastaFile();
if (filename != "") { fastaFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
}else {
m->splitAtDash(fastafile, fastaFileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < fastaFileNames.size(); i++) {
bool ignore = false;
if (fastaFileNames[i] == "current") {
fastaFileNames[i] = m->getFastaFile();
if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
fastaFileNames.erase(fastaFileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(fastaFileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
fastaFileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
fastaFileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
fastaFileNames.erase(fastaFileNames.begin()+i);
i--;
}else {
m->setFastaFile(fastaFileNames[i]);
}
}
}
//make sure there is at least one valid file left
if (fastaFileNames.size() == 0) { m->mothurOut("[ERROR]: no valid files."); m->mothurOutEndLine(); abort = true; }
}
//check for required parameters
namefile = validParameter.validFile(parameters, "name", false);
if (namefile == "not found") { namefile = ""; }
else {
m->splitAtDash(namefile, nameFileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < nameFileNames.size(); i++) {
bool ignore = false;
if (nameFileNames[i] == "current") {
nameFileNames[i] = m->getNameFile();
if (nameFileNames[i] != "") { m->mothurOut("Using " + nameFileNames[i] + " as input file for the name parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current namefile, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
nameFileNames.erase(nameFileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(nameFileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { nameFileNames[i] = inputDir + nameFileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(nameFileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(nameFileNames[i]);
m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
nameFileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(nameFileNames[i]);
m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
nameFileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + nameFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
nameFileNames.erase(nameFileNames.begin()+i);
i--;
}else {
m->setNameFile(nameFileNames[i]);
}
}
}
}
if (nameFileNames.size() != 0) { hasName = true; }
//check for required parameters
vector<string> countfileNames;
countfile = validParameter.validFile(parameters, "count", false);
if (countfile == "not found") {
countfile = "";
}else {
m->splitAtDash(countfile, countfileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < countfileNames.size(); i++) {
bool ignore = false;
if (countfileNames[i] == "current") {
countfileNames[i] = m->getCountTableFile();
if (nameFileNames[i] != "") { m->mothurOut("Using " + countfileNames[i] + " as input file for the count parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current count file, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
countfileNames.erase(countfileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(countfileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { countfileNames[i] = inputDir + countfileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(countfileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(countfileNames[i]);
m->mothurOut("Unable to open " + countfileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
countfileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(countfileNames[i]);
m->mothurOut("Unable to open " + countfileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
countfileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + countfileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
countfileNames.erase(countfileNames.begin()+i);
i--;
}else {
m->setCountTableFile(countfileNames[i]);
}
}
}
}
if (countfileNames.size() != 0) { 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."); m->mothurOutEndLine(); abort = true; }
if (!hasName && hasCount) { nameFileNames = countfileNames; }
if ((hasCount || hasName) && (nameFileNames.size() != fastaFileNames.size())) { m->mothurOut("[ERROR]: The number of name or count files does not match the number of fastafiles, please correct."); m->mothurOutEndLine(); abort=true; }
bool hasGroup = true;
groupfile = validParameter.validFile(parameters, "group", false);
if (groupfile == "not found") { groupfile = ""; hasGroup = false; }
else {
m->splitAtDash(groupfile, groupFileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < groupFileNames.size(); i++) {
bool ignore = false;
if (groupFileNames[i] == "current") {
groupFileNames[i] = m->getGroupFile();
if (groupFileNames[i] != "") { m->mothurOut("Using " + groupFileNames[i] + " as input file for the group parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current namefile, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
groupFileNames.erase(groupFileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(groupFileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { groupFileNames[i] = inputDir + groupFileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(groupFileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(groupFileNames[i]);
m->mothurOut("Unable to open " + groupFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
groupFileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(groupFileNames[i]);
m->mothurOut("Unable to open " + groupFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
groupFileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + groupFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
groupFileNames.erase(groupFileNames.begin()+i);
i--;
}else {
m->setGroupFile(groupFileNames[i]);
}
}
}
//make sure there is at least one valid file left
if (groupFileNames.size() == 0) { m->mothurOut("[ERROR]: no valid group files."); m->mothurOutEndLine(); abort = true; }
}
if (hasGroup && (groupFileNames.size() != fastaFileNames.size())) { m->mothurOut("[ERROR]: The number of groupfiles does not match the number of fastafiles, please correct."); m->mothurOutEndLine(); abort=true; }
if (hasGroup && hasCount) { m->mothurOut("[ERROR]: You must enter ONLY ONE of the following: count or group."); m->mothurOutEndLine(); abort = true; }
//if the user changes the output directory command factory will send this info to us in the output parameter
outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
m->setProcessors(temp);
m->mothurConvert(temp, processors);
temp = validParameter.validFile(parameters, "save", false); if (temp == "not found"){ temp = "f"; }
save = m->isTrue(temp);
rdb->save = save;
if (save) { //clear out old references
rdb->clearMemory();
}
string path;
it = parameters.find("reference");
//user has given a template file
if(it != parameters.end()){
if (it->second == "self") {
templatefile = "self";
if (save) {
m->mothurOut("[WARNING]: You can't save reference=self, ignoring save.");
m->mothurOutEndLine();
save = false;
}
}
else {
path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["reference"] = inputDir + it->second; }
templatefile = validParameter.validFile(parameters, "reference", true);
if (templatefile == "not open") { abort = true; }
else if (templatefile == "not found") { //check for saved reference sequences
if (rdb->referenceSeqs.size() != 0) {
templatefile = "saved";
}else {
m->mothurOut("[ERROR]: You don't have any saved reference sequences and the reference parameter is a required.");
m->mothurOutEndLine();
abort = true;
}
}else { if (save) { rdb->setSavedReference(templatefile); } }
}
}else if (hasName) { templatefile = "self";
if (save) {
m->mothurOut("[WARNING]: You can't save reference=self, ignoring save.");
m->mothurOutEndLine();
save = false;
}
}else if (hasCount) { templatefile = "self";
if (save) {
m->mothurOut("[WARNING]: You can't save reference=self, ignoring save.");
m->mothurOutEndLine();
save = false;
}
}
else {
if (rdb->referenceSeqs.size() != 0) {
templatefile = "saved";
}else {
m->mothurOut("[ERROR]: You don't have any saved reference sequences and the reference parameter is a required.");
m->mothurOutEndLine();
templatefile = ""; abort = true;
}
}
temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found") { temp = "7"; }
m->mothurConvert(temp, ksize);
temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "50"; }
m->mothurConvert(temp, window);
temp = validParameter.validFile(parameters, "match", false); if (temp == "not found") { temp = "5"; }
m->mothurConvert(temp, match);
temp = validParameter.validFile(parameters, "mismatch", false); if (temp == "not found") { temp = "-4"; }
m->mothurConvert(temp, mismatch);
temp = validParameter.validFile(parameters, "divergence", false); if (temp == "not found") { temp = "1.007"; }
m->mothurConvert(temp, divR);
temp = validParameter.validFile(parameters, "minsim", false); if (temp == "not found") { temp = "90"; }
m->mothurConvert(temp, minSimilarity);
temp = validParameter.validFile(parameters, "mincov", false); if (temp == "not found") { temp = "70"; }
m->mothurConvert(temp, minCoverage);
temp = validParameter.validFile(parameters, "minbs", false); if (temp == "not found") { temp = "90"; }
m->mothurConvert(temp, minBS);
temp = validParameter.validFile(parameters, "minsnp", false); if (temp == "not found") { temp = "10"; }
m->mothurConvert(temp, minSNP);
temp = validParameter.validFile(parameters, "parents", false); if (temp == "not found") { temp = "3"; }
m->mothurConvert(temp, parents);
temp = validParameter.validFile(parameters, "realign", false); if (temp == "not found") { temp = "t"; }
realign = m->isTrue(temp);
temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found") { temp = "f"; }
trim = m->isTrue(temp);
temp = validParameter.validFile(parameters, "split", false); if (temp == "not found") { temp = "f"; }
trimera = m->isTrue(temp);
search = validParameter.validFile(parameters, "search", false); if (search == "not found") { search = "blast"; }
temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; }
m->mothurConvert(temp, iters);
temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "5"; }
m->mothurConvert(temp, increment);
temp = validParameter.validFile(parameters, "numwanted", false); if (temp == "not found") { temp = "15"; }
m->mothurConvert(temp, numwanted);
temp = validParameter.validFile(parameters, "dereplicate", false);
if (temp == "not found") { temp = "false"; }
dups = m->isTrue(temp);
blastlocation = validParameter.validFile(parameters, "blastlocation", false);
if (blastlocation == "not found") { blastlocation = ""; }
else {
//add / to name if needed
string lastChar = blastlocation.substr(blastlocation.length()-1);
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
if (lastChar != "/") { blastlocation += "/"; }
#else
if (lastChar != "\\") { blastlocation += "\\"; }
#endif
blastlocation = m->getFullPathName(blastlocation);
string formatdbCommand = "";
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
formatdbCommand = blastlocation + "formatdb";
#else
formatdbCommand = blastlocation + "formatdb.exe";
#endif
//test to make sure formatdb exists
ifstream in;
formatdbCommand = m->getFullPathName(formatdbCommand);
int ableToOpen = m->openInputFile(formatdbCommand, in, "no error"); in.close();
if(ableToOpen == 1) { m->mothurOut("[ERROR]: " + formatdbCommand + " file does not exist. mothur requires formatdb.exe to run chimera.slayer."); m->mothurOutEndLine(); abort = true; }
string blastCommand = "";
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
blastCommand = blastlocation + "megablast";
#else
blastCommand = blastlocation + "megablast.exe";
#endif
//test to make sure formatdb exists
ifstream in2;
blastCommand = m->getFullPathName(blastCommand);
ableToOpen = m->openInputFile(blastCommand, in2, "no error"); in2.close();
if(ableToOpen == 1) { m->mothurOut("[ERROR]: " + blastCommand + " file does not exist. mothur requires blastall.exe to run chimera.slayer."); m->mothurOutEndLine(); abort = true; }
}
if ((search != "blast") && (search != "kmer")) { m->mothurOut(search + " is not a valid search."); m->mothurOutEndLine(); abort = true; }
if ((hasName || hasCount) && (templatefile != "self")) { m->mothurOut("You have provided a namefile or countfile and the reference parameter is not set to self. I am not sure what reference you are trying to use, aborting."); m->mothurOutEndLine(); abort=true; }
if (hasGroup && (templatefile != "self")) { m->mothurOut("You have provided a group file and the reference parameter is not set to self. I am not sure what reference you are trying to use, aborting."); m->mothurOutEndLine(); abort=true; }
//until we resolve the issue 10-18-11
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
#else
//processors=1;
#endif
}
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "ChimeraSlayerCommand");
exit(1);
}
}
//***************************************************************************************************************
int ChimeraSlayerCommand::execute(){
try{
if (abort == true) { if (calledHelp) { return 0; } return 2; }
for (int s = 0; s < fastaFileNames.size(); s++) {
m->mothurOut("Checking sequences from " + fastaFileNames[s] + " ..." ); m->mothurOutEndLine();
int start = time(NULL);
if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]); }//if user entered a file with a path then preserve it
map<string, string> variables;
variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s]));
string outputFileName = getOutputFileName("chimera", variables);
string accnosFileName = getOutputFileName("accnos", variables);
string trimFastaFileName = getOutputFileName("fasta", variables);
string newCountFile = "";
//clears files
ofstream out, out1, out2;
m->openOutputFile(outputFileName, out); out.close();
m->openOutputFile(accnosFileName, out1); out1.close();
if (trim) { m->openOutputFile(trimFastaFileName, out2); out2.close(); }
outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName);
outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName);
if (trim) { outputNames.push_back(trimFastaFileName); outputTypes["fasta"].push_back(trimFastaFileName); }
//maps a filename to priority map.
//if no groupfile this is fastafileNames[s] -> prioirity
//if groupfile then this is each groups seqs -> priority
map<string, map<string, int> > fileToPriority;
map<string, map<string, int> >::iterator itFile;
map<string, string> fileGroup;
fileToPriority[fastaFileNames[s]] = priority; //default
fileGroup[fastaFileNames[s]] = "noGroup";
map<string, string> uniqueNames;
int totalChimeras = 0;
lines.clear();
if (templatefile == "self") {
if (hasCount) {
SequenceCountParser* parser = NULL;
setUpForSelfReference(parser, fileGroup, fileToPriority, s);
if (parser != NULL) { uniqueNames = parser->getAllSeqsMap(); delete parser; }
}else {
SequenceParser* parser = NULL;
setUpForSelfReference(parser, fileGroup, fileToPriority, s);
if (parser != NULL) { uniqueNames = parser->getAllSeqsMap(); delete parser; }
}
}
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
if (fileToPriority.size() == 1) { //you running without a groupfile
itFile = fileToPriority.begin();
string thisFastaName = itFile->first;
map<string, int> thisPriority = itFile->second;
#ifdef USE_MPI
MPIExecute(thisFastaName, outputFileName, accnosFileName, trimFastaFileName, thisPriority);
#else
//break up file
vector<unsigned long long> positions;
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
positions = m->divideFile(thisFastaName, processors);
for (int i = 0; i < (positions.size()-1); i++) { lines.push_back(linePair(positions[i], positions[(i+1)])); }
#else
if (processors == 1) { lines.push_back(linePair(0, 1000)); }
else {
positions = m->setFilePosFasta(thisFastaName, numSeqs);
if (positions.size() < processors) { processors = positions.size(); }
//figure out how many sequences you have to process
int numSeqsPerProcessor = numSeqs / processors;
for (int i = 0; i < processors; i++) {
int startIndex = i * numSeqsPerProcessor;
if(i == (processors - 1)){ numSeqsPerProcessor = numSeqs - i * numSeqsPerProcessor; }
lines.push_back(linePair(positions[startIndex], numSeqsPerProcessor));
}
}
#endif
if(processors == 1){ numSeqs = driver(lines[0], outputFileName, thisFastaName, accnosFileName, trimFastaFileName, thisPriority); }
else{ numSeqs = createProcesses(outputFileName, thisFastaName, accnosFileName, trimFastaFileName, thisPriority); }
if (m->control_pressed) { outputTypes.clear(); if (trim) { m->mothurRemove(trimFastaFileName); } m->mothurRemove(outputFileName); m->mothurRemove(accnosFileName); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
#endif
}else { //you have provided a groupfile
string countFile = "";
if (hasCount) {
countFile = nameFileNames[s];
variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(nameFileNames[s]));
newCountFile = getOutputFileName("count", variables);
}
#ifdef USE_MPI
MPIExecuteGroups(outputFileName, accnosFileName, trimFastaFileName, fileToPriority, fileGroup, newCountFile, countFile);
#else
if (processors == 1) {
numSeqs = driverGroups(outputFileName, accnosFileName, trimFastaFileName, fileToPriority, fileGroup, newCountFile);
if (hasCount && dups) {
CountTable c; c.readTable(nameFileNames[s], true);
if (!m->isBlank(newCountFile)) {
ifstream in2;
m->openInputFile(newCountFile, in2);
string name, group;
while (!in2.eof()) {
in2 >> name >> group; m->gobble(in2);
c.setAbund(name, group, 0);
}
in2.close();
}
m->mothurRemove(newCountFile);
c.printTable(newCountFile);
}
}
else { numSeqs = createProcessesGroups(outputFileName, accnosFileName, trimFastaFileName, fileToPriority, fileGroup, newCountFile, countFile); } //destroys fileToPriority
#endif
#ifdef USE_MPI
int pid;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
if (pid == 0) {
#endif
if (!dups) {
totalChimeras = deconvoluteResults(uniqueNames, outputFileName, accnosFileName, trimFastaFileName);
m->mothurOutEndLine(); m->mothurOut(toString(totalChimeras) + " chimera found."); m->mothurOutEndLine();
}else {
if (hasCount) {
set<string> doNotRemove;
CountTable c; c.readTable(newCountFile, true);
vector<string> namesInTable = c.getNamesOfSeqs();
for (int i = 0; i < namesInTable.size(); i++) {
int temp = c.getNumSeqs(namesInTable[i]);
if (temp == 0) { c.remove(namesInTable[i]); }
else { doNotRemove.insert((namesInTable[i])); }
}
//remove names we want to keep from accnos file.
set<string> accnosNames = m->readAccnos(accnosFileName);
ofstream out2;
m->openOutputFile(accnosFileName, out2);
for (set<string>::iterator it = accnosNames.begin(); it != accnosNames.end(); it++) {
if (doNotRemove.count(*it) == 0) { out2 << (*it) << endl; }
}
out2.close();
c.printTable(newCountFile);
outputNames.push_back(newCountFile); outputTypes["count"].push_back(newCountFile);
}
}
#ifdef USE_MPI
}
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait
#endif
}
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine();
}
//set accnos file as new current accnosfile
string current = "";
itTypes = outputTypes.find("accnos");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); }
}
if (trim) {
itTypes = outputTypes.find("fasta");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
}
}
itTypes = outputTypes.find("count");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
}
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
m->mothurOutEndLine();
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "execute");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::MPIExecuteGroups(string outputFileName, string accnosFileName, string trimFastaFileName, map<string, map<string, int> >& fileToPriority, map<string, string>& fileGroup, string countlist, string countfile){
try {
#ifdef USE_MPI
int pid;
int tag = 2001;
MPI_Status status;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
MPI_Comm_size(MPI_COMM_WORLD, &processors);
//put filenames in a vector, then pass each process a starting and ending point in the vector
//all processes already have the fileToPriority and fileGroup, they just need to know which files to process
map<string, map<string, int> >::iterator itFile;
vector<string> filenames;
for(itFile = fileToPriority.begin(); itFile != fileToPriority.end(); itFile++) { filenames.push_back(itFile->first); }
int numGroupsPerProcessor = filenames.size() / processors;
int startIndex = pid * numGroupsPerProcessor;
int endIndex = (pid+1) * numGroupsPerProcessor;
if(pid == (processors - 1)){ endIndex = filenames.size(); }
vector<unsigned long long> MPIPos;
MPI_File outMPI;
MPI_File outMPIAccnos;
MPI_File outMPIFasta;
MPI_File outMPICount;
int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY;
int inMode=MPI_MODE_RDONLY;
char outFilename[1024];
strcpy(outFilename, outputFileName.c_str());
char outAccnosFilename[1024];
strcpy(outAccnosFilename, accnosFileName.c_str());
char outFastaFilename[1024];
strcpy(outFastaFilename, trimFastaFileName.c_str());
char outCountFilename[1024];
strcpy(outCountFilename, countlist.c_str());
MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPI);
MPI_File_open(MPI_COMM_WORLD, outAccnosFilename, outMode, MPI_INFO_NULL, &outMPIAccnos);
if (trim) { MPI_File_open(MPI_COMM_WORLD, outFastaFilename, outMode, MPI_INFO_NULL, &outMPIFasta); }
if (hasCount && dups) { MPI_File_open(MPI_COMM_WORLD, outCountFilename, outMode, MPI_INFO_NULL, &outMPICount); }
if (m->control_pressed) { MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); if (hasCount && dups) { MPI_File_close(&outMPICount); } return 0; }
//print headers
if (pid == 0) { //you are the root process
m->mothurOutEndLine();
m->mothurOut("Only reporting sequence supported by " + toString(minBS) + "% of bootstrapped results.");
m->mothurOutEndLine();
string outTemp = "Name\tLeftParent\tRightParent\tDivQLAQRB\tPerIDQLAQRB\tBootStrapA\tDivQLBQRA\tPerIDQLBQRA\tBootStrapB\tFlag\tLeftWindow\tRightWindow\n";
//print header
int length = outTemp.length();
char* buf2 = new char[length];
memcpy(buf2, outTemp.c_str(), length);
MPI_File_write_shared(outMPI, buf2, length, MPI_CHAR, &status);
delete buf2;
}
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait
for (int i = startIndex; i < endIndex; i++) {
int start = time(NULL);
int num = 0;
string thisFastaName = filenames[i];
map<string, int> thisPriority = fileToPriority[thisFastaName];
char inFileName[1024];
strcpy(inFileName, thisFastaName.c_str());
MPI_File inMPI;
MPI_File_open(MPI_COMM_SELF, inFileName, inMode, MPI_INFO_NULL, &inMPI); //comm, filename, mode, info, filepointer
MPIPos = m->setFilePosFasta(thisFastaName, num); //fills MPIPos, returns numSeqs
cout << endl << "Checking sequences from group: " << fileGroup[thisFastaName] << "." << endl;
set<string> cnames;
driverMPI(0, num, inMPI, outMPI, outMPIAccnos, outMPIFasta, cnames, MPIPos, thisFastaName, thisPriority, true);
numSeqs += num;
MPI_File_close(&inMPI);
m->mothurRemove(thisFastaName);
if (dups) {
if (cnames.size() != 0) {
if (hasCount) {
for (set<string>::iterator it = cnames.begin(); it != cnames.end(); it++) {
string outputString = (*it) + "\t" + fileGroup[thisFastaName] + "\n";
int length = outputString.length();
char* buf2 = new char[length];
memcpy(buf2, outputString.c_str(), length);
MPI_File_write_shared(outMPICount, buf2, length, MPI_CHAR, &status);
delete buf2;
}
}else {
map<string, map<string, string> >::iterator itGroupNameMap = group2NameMap.find(fileGroup[thisFastaName]);
if (itGroupNameMap != group2NameMap.end()) {
map<string, string> thisnamemap = itGroupNameMap->second;
map<string, string>::iterator itN;
for (set<string>::iterator it = cnames.begin(); it != cnames.end(); it++) {
itN = thisnamemap.find(*it);
if (itN != thisnamemap.end()) {
vector<string> tempNames; m->splitAtComma(itN->second, tempNames);
for (int j = 0; j < tempNames.size(); j++) { //write to accnos file
string outputString = tempNames[j] + "\n";
int length = outputString.length();
char* buf2 = new char[length];
memcpy(buf2, outputString.c_str(), length);
MPI_File_write_shared(outMPIAccnos, buf2, length, MPI_CHAR, &status);
delete buf2;
}
}else { m->mothurOut("[ERROR]: parsing cannot find " + *it + ".\n"); m->control_pressed = true; }
}
}else { m->mothurOut("[ERROR]: parsing cannot find " + fileGroup[thisFastaName] + ".\n"); m->control_pressed = true; }
}
}
}
cout << endl << "It took " << toString(time(NULL) - start) << " secs to check " + toString(num) + " sequences from group " << fileGroup[thisFastaName] << "." << endl;
}
if (pid == 0) {
for(int i = 1; i < processors; i++) {
int temp = 0;
MPI_Recv(&temp, 1, MPI_INT, i, 2001, MPI_COMM_WORLD, &status);
numSeqs += temp;
}
}else{ MPI_Send(&numSeqs, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD); }
MPI_File_close(&outMPI);
MPI_File_close(&outMPIAccnos);
if (trim) { MPI_File_close(&outMPIFasta); }
if (hasCount && dups) { MPI_File_close(&outMPICount); }