-
Notifications
You must be signed in to change notification settings - Fork 4
/
functions.cpp
3061 lines (2688 loc) · 127 KB
/
functions.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
//
// functions.cpp
// frequencyDependentSimulation
//
// Created by Nicholas Croucher on 28/09/2015.
// Copyright (c) 2015 Imperial College. All rights reserved.
//
#include <iostream>
#include <string>
#include <fstream>
#include <getopt.h>
#include <stdio.h>
#include <string.h>
#include <vector>
#include <sstream>
#include <string>
#include <algorithm>
#include <numeric>
#include <gsl/gsl_rng.h>
#include <gsl/gsl_randist.h>
#include <gsl/gsl_vector.h>
#include <gsl/gsl_statistics.h>
#include <sys/time.h>
#include <cmath>
#include "functions.h"
#include "parms.h"
///////////////////////
// Generic functions //
///////////////////////
/////////////////////////////
// random number generator //
/////////////////////////////
unsigned long int random_seed() {
unsigned int seed;
struct timeval tv;
FILE *devrandom;
if ((devrandom = fopen("/dev/urandom","r")) == NULL) {
gettimeofday(&tv,0);
seed = tv.tv_sec + tv.tv_usec;
} else {
size_t nread = 0;
nread = fread(&seed,sizeof(seed),1,devrandom);
fclose(devrandom);
}
return(seed);
}
///////////////////
// usage message //
///////////////////
void usage (char* fn) {
std::cerr << "Programme:" << fn << std::endl << "\tp\tprogramme type:" << std::endl << "\t\t's' - simulation without fitting" << std::endl << "\t\t'x' - extended simulation output" << std::endl << "\t\t'f' - just return fitting metrics" << std::endl << "\t\t'b' - both fit to data and print simulation" << std::endl << std::endl << "Simulation parameters:" << std::endl << "\ts\tfrequency dependent selection pressure [double between 0 and 1]" << std::endl << "\tv\tvaccine selection pressure [double between 0 and 1]" << std::endl << "\ti\timmigration rate [double between 0 and 1]" << std::endl << "\tt\timmigration type [0 - by strain, 1 - by SC]" << std::endl << "\tn\tpopulation carrying capacity [integer]" << std::endl << "\tg\tnumber of generations [integer]" << std::endl << "\tu\tupper gene frequency limit [double between 0 and 1]" << std::endl << "\tl\tlower gene frequency limit [double between 0 and 1]" << std::endl << "\tq\tgeneration in which vaccine formulation is changed" << std::endl << std::endl << "Model fitting parameters:" << std::endl << "\tc\tvaccine target COG name [string]" << std::endl << "\tb\tbeginning year [integer]" << std::endl << "\tm\tmid year [integer]" << std::endl << "\te\tending year [integer]" << std::endl << std::endl << "Filenames:" << std::endl << "\tf\tinputFilename" << std::endl << "\tx\tfrequency file name [only for simulating]" << std::endl << "\to\toutput file prefix" << std::endl << "\tw\tweighting file" << std::endl << "\tr\tcog reordering file" << std::endl;
}
////////////////////////
// Input file parsing //
////////////////////////
//////////////////////
// parse input file //
//////////////////////
int parseInputFile(std::vector<isolate*> *pop, std::vector<cog*> *accessoryLoci, double lower, double upper, std::vector<int> *samplingList,std::vector<std::string> *st, std::vector<int> *sc, std::vector<std::string> *cogList, char *inputFilename, char * vtCogName, int &minGen, bool useCogList) {
// indices
int s = 0;
int v = -1;
// COG sampling data structure
std::vector<std::string> tmpCogList;
std::vector<int> samplingTimes;
int eqPop = 0;
// parse file
std::ifstream infile;
infile.open(inputFilename, std::ifstream::in);
if (infile) {
std::string line;
// parse lines
while (std::getline(infile, line)) {
// temporary information stores
std::string sample_id;
int sample_time = -1;
int sample_sc = -1;
std::string sample_serotype = "noSero";
bool sample_vt = 0;
bool sample_latent_vt = 0;
std::vector<bool> sample_genotype;
std::string iname;
std::istringstream iss(line);
int sIndex = 0;
while (iss) {
std::string temp;
while (getline(iss, temp, '\t')) {
if (sIndex == 0) {
iname = temp;
sample_id = iname;
} else if (sIndex == 1) {
sample_time = atoi(temp.c_str());
if (sample_time < minGen) {
minGen = sample_time;
}
} else if (sIndex == 2) {
sample_serotype = temp;
} else if (sIndex == 3) {
int vt_int = atoi(temp.c_str());
if (vt_int == 0) {
sample_vt = false;
sample_latent_vt = false;
} else if (vt_int == 1) {
sample_vt = true;
sample_latent_vt = false;
} else if (vt_int == 2) {
sample_vt = false;
sample_latent_vt = true;
} else {
std::cerr << "Unknown VT status for " << sample_id << std::endl;
}
} else if (sIndex == 4) {
sample_sc = atoi(temp.c_str());
} else if (sIndex > 4) {
if (iname == "Taxon") {
// record COG names
tmpCogList.push_back(temp);
// identify the key VT COG
if (vtCogName != 0 && temp == vtCogName) {
v = sIndex - 5;
}
} else {
sample_genotype.push_back(atoi(temp.c_str()));
}
}
sIndex++;
}
}
if (iname != "Taxon" && sample_time != -1 && sample_sc != -1 && sample_serotype.compare("noSero") != 0) {
std::vector<bool> sample_markers(0);
isolate* tmp = new isolate(sample_id,sample_time,sample_sc,sample_serotype,sample_vt,sample_latent_vt,&sample_genotype,&sample_markers,1.0);
pop->push_back(tmp);
// record isolate information
samplingTimes.push_back(sample_time);
sc->push_back(sample_sc);
st->push_back(sample_serotype);
// calculate pre- and peri-vaccine population size
if (sample_time <= 0) {
eqPop++;
}
// increment index
s++;
}
}
infile.close();
// get unique serotypes and sequence clusters
sort(st->begin(),st->end());
st->erase(unique(st->begin(),st->end()),st->end());
sort(sc->begin(),sc->end());
sc->erase(unique(sc->begin(),sc->end()),sc->end());
// calculate sample timings and sizes
int maxTime = 0;
std::vector<int>::iterator iter;
for (iter = samplingTimes.begin(), samplingTimes.end() ; iter != samplingTimes.end(); ++iter) {
if ((*iter)-minGen > maxTime) {
maxTime = (*iter)-minGen;
}
}
samplingList->resize(maxTime+1,0);
for (iter = samplingTimes.begin(), samplingTimes.end() ; iter != samplingTimes.end(); ++iter) {
(*samplingList)[(*iter)-minGen]++;
}
// create vector of accessory locus COG objects
if (useCogList) {
// find matching positions between pre-calculated coglist
// and new input file
std::vector<int> cogMatches;
if (cogMatches.size() < cogList->size()) {
for (unsigned int i = 0; i < cogList->size(); i++) {
int match_pos = -1;
for (unsigned int j = 0; j < tmpCogList.size(); j++) {
if ((*cogList)[i] == tmpCogList[j]) {
match_pos = j;
j = tmpCogList.size();
}
}
if (match_pos == -1) {
std::cerr << "Unable to find COG " << (*cogList)[i] << " in migrant strain input file" << std::endl;
return 1;
} else {
cogMatches.push_back(match_pos);
}
}
}
// add ordered cogs to input file
std::vector<isolate*>::iterator iiter;
for (iiter = pop->begin(), pop->end() ; iiter != pop->end(); ++iiter) {
std::vector<bool> tmpGenotype;
for (unsigned int j = 0; j < cogMatches.size(); j++) {
tmpGenotype.push_back((*iiter)->genotype[j]);
}
(*iiter)->genotype = tmpGenotype;
}
} else {
std::vector<int> includeLocus(tmpCogList.size(),0);
std::vector<isolate*>::iterator iiter;
std::vector<std::string> intCogList;
for (unsigned int i = 0; i < tmpCogList.size(); i++) {
// data structures for recording frequencies
int overallFreq = 0;
std::vector<double> cogFrequencies(samplingTimes.size(),0);
double eqFreq = 0;
// calculate gene frequencies from isolates
for (iiter = pop->begin(), pop->end() ; iiter != pop->end(); ++iiter) {
overallFreq+=(*iiter)->genotype[i];
cogFrequencies[((*iiter)->year)-minGen]+=(double((*iiter)->genotype[i])/double((*samplingList)[((*iiter)->year)-minGen]));
if ((*iiter)->year <= 0) {
eqFreq+=(double((*iiter)->genotype[i])/double(eqPop));
}
}
// retain if present at intermediate frequency OR vt-defining COG
if ((eqFreq >= (lower-1e-07) && eqFreq <= (upper+1e-07)) || i == unsigned(v)) {
includeLocus[i] = 1;
int vtType = 0;
if (i == unsigned(v)) {
vtType = 1;
}
intCogList.push_back(tmpCogList[i]);
cog* tmpCog = new cog(tmpCogList[i],vtType,1.0,eqFreq,&cogFrequencies);
if (tmpCog->id.length() > 0) {
accessoryLoci->push_back(tmpCog);
} else {
std::cerr << "Undefined COG ID at line " << i << std::endl;
}
} else {
includeLocus[i] = 0;
}
}
// recalculate isolate genotypes to only include COGs at intermediate frequency
for (iiter = pop->begin(), pop->end() ; iiter != pop->end(); ++iiter) {
std::vector<bool> tmpGenotype;
for (unsigned int i = 0; i < includeLocus.size(); i++) {
if (includeLocus[i] == 1) {
tmpGenotype.push_back((*iiter)->genotype[i]);
}
}
(*iiter)->genotype = tmpGenotype;
}
// return cog list
*cogList = intCogList;
}
} else {
std::cerr << "Problem with input file: " << strerror(errno) << std::endl;
return 1;
}
return 0;
}
//////////////////////////////
// parse marker information //
//////////////////////////////
int parseMarkerFile(std::vector<isolate*> *pop,char *markerFilename,std::vector<std::string> *markerList, bool useMarkerList) {
// data structures
std::vector<std::string> tmpMarkerList;
// parse file
std::ifstream infile;
infile.open(markerFilename, std::ifstream::in);
if (infile) {
std::string line;
// parse lines
while (std::getline(infile, line)) {
// temporary information stores
std::string sample_id;
std::vector<bool> sample_markers;
std::string iname;
std::istringstream iss(line);
int sIndex = 0;
while (iss) {
std::string temp;
while (getline(iss, temp, '\t')) {
if (sIndex == 0) {
sample_id = temp;
} else if (sIndex > 4) {
if (sample_id == "Taxon") {
// record COG names
tmpMarkerList.push_back(temp);
} else {
sample_markers.push_back(atoi(temp.c_str()));
}
}
sIndex++;
}
}
// record marker genotypes and attach to isolate objects
std::vector<isolate*>::iterator iiter;
for (iiter = pop->begin(), pop->end() ; iiter != pop->end(); ++iiter) {
if ((*iiter)->id == sample_id) {
(*iiter)->markers = sample_markers;
}
}
}
infile.close();
// check whether markers need reordering
if (useMarkerList) {
// find matching positions between pre-calculated coglist
// and new input file
// data structure
std::vector<int> markerMatches;
if (markerMatches.size() < markerList->size()) {
for (unsigned int i = 0; i < markerList->size(); i++) {
int match_pos = -1;
for (unsigned int j = 0; j < tmpMarkerList.size(); j++) {
if ((*markerList)[i] == tmpMarkerList[j]) {
match_pos = j;
j = tmpMarkerList.size();
}
}
if (match_pos == -1) {
std::cerr << "Unable to find marker " << (*markerList)[i] << " in migrant strain input file" << std::endl;
return 1;
} else {
markerMatches.push_back(match_pos);
}
}
}
// add ordered markers to correct isolate
std::vector<isolate*>::iterator iiter;
for (iiter = pop->begin(), pop->end() ; iiter != pop->end(); ++iiter) {
std::vector<bool> tmpGenotype;
std::vector<bool> sample_markers = (*iiter)->markers;
for (unsigned int j = 0; j < markerMatches.size(); j++) {
tmpGenotype.push_back(sample_markers[j]);
}
(*iiter)->markers = tmpGenotype;
}
} else {
// modify marker list
(*markerList) = tmpMarkerList;
// modify individual isolates
}
// check all marker lengths are the same
std::vector<isolate*>::iterator iiter;
long markerLength = tmpMarkerList.size();
for (iiter = pop->begin(), pop->end() ; iiter != pop->end(); ++iiter) {
if (unsigned(markerLength) != (*iiter)->markers.size()) {
std::cerr << "Isolate " << (*iiter)->id << " has incorrect marker information; expecting " << markerLength << " but found " << (*iiter)->markers.size() << std::endl;
return 1;
}
}
} else {
std::cerr << "Problem with marker file: " << strerror(errno) << std::endl;
return 1;
}
return 0;
}
//////////////////////////
// validate input files //
//////////////////////////
int compareInputPopulations(std::vector<isolate*> *popA, std::vector<isolate*> *popB, bool check_markers) {
long genotype_length = -1;
std::vector<isolate*>::iterator iter;
// check populationA genotype lengths are consistent
for (iter = popA->begin(), popA->end() ; iter != popA->end(); ++iter) {
long current_genotype_size = (*iter)->genotype.size(); // explicit cast for precision reasons
if (genotype_length != -1 && genotype_length != current_genotype_size) {
std::cerr << "Inconsistent genotype length for isolate " << (*iter)->id << " in first population" << std::endl;
return 1;
} else {
genotype_length = (*iter)->genotype.size();
}
}
// check populationB genotype lengths are consistent
for (iter = popB->begin(), popB->end() ; iter != popB->end(); ++iter) {
long current_genotype_size = (*iter)->genotype.size();
if (genotype_length != current_genotype_size) {
std::cerr << "Inconsistent genotype length for isolate " << (*iter)->id << " in second population - may not match that in the first population" << std::endl;
return 1;
}
}
if (check_markers) {
genotype_length = -1;
// check populationA genotype lengths are consistent
for (iter = popA->begin(), popA->end() ; iter != popA->end(); ++iter) {
long current_marker_size = (*iter)->markers.size();
if (genotype_length != -1 && genotype_length != current_marker_size) {
std::cerr << "Inconsistent marker genotype length for isolate " << (*iter)->id << " in first population" << std::endl;
return 1;
} else {
genotype_length = (*iter)->markers.size();
}
}
// check populationB genotype lengths are consistent
for (iter = popB->begin(), popB->end() ; iter != popB->end(); ++iter) {
long current_marker_size = (*iter)->markers.size();
if (genotype_length != current_marker_size) {
std::cerr << "Inconsistent marker genotype length for isolate " << (*iter)->id << " in second population - may not match that in the first population" << std::endl;
return 1;
}
}
}
return 0;
}
////////////////////////////
// parse input parameters //
////////////////////////////
bool checkInputValues(struct parms *sp,char * inputFilename,char * vtCogName, char* propFile, char* weightFile) {
bool tmpvalid = 1;
// check mode
if (sp->programme != "f" && sp->programme != "s" && sp->programme != "b" && sp->programme != "x") {
std::cerr << "Must select a programme: 'f' for fitting, 's' for simulating ('x' for extended output), 'b' for both" << std::endl;
tmpvalid = 0;
}
if (propFile != 0 && weightFile != 0) {
std::cerr << "You can't use a proportion file and a weight file. You just can't, stop it." << std::endl;
tmpvalid = 0;
}
// check values for parameters
if (sp->fSelection < 0 || sp->fSelection > 1000) {
std::cerr << "Invalid frequency dependent selection value: " << sp->fSelection << "; should be between 0 and 1" << std::endl;
tmpvalid = 0;
}
if (sp->vSelection < 0 || sp->vSelection > 1) {
std::cerr << "Invalid vaccine selection value: " << sp->vSelection << "; should be between 0 and 1" << std::endl;
tmpvalid = 0;
}
if (sp->immigrationRate < 0 || sp->immigrationRate > 1) {
std::cerr << "Invalid immigration rate value: " << sp->immigrationRate << "; should be between 0 and 1" << std::endl;
tmpvalid = 0;
}
if (sp->immigrationRate > 0) {
if (sp->immigrationType != 0 && sp->immigrationType != 1 && sp->immigrationType != 2 && sp->immigrationType != 3) {
std::cerr << "Invalid immigration type: " << sp->immigrationType << "; should be either '0' (by isolate), '1' (by sc), or '2' (by time)" << std::endl;
tmpvalid = 0;
}
}
if (sp->upperLimit < 0 || sp->upperLimit > 1) {
std::cerr << "Invalid upper limit value: " << sp->upperLimit << "; should be between 0 and 1" << std::endl;
tmpvalid = 0;
}
if (sp->lowerLimit < 0 || sp->lowerLimit > 1 || sp->lowerLimit >= sp->upperLimit) {
std::cerr << "Invalid lower limit value: " << sp->lowerLimit << "; should be between 0 and 1 and lower than the upper limit of " << sp->upperLimit << std::endl;
tmpvalid = 0;
}
if (sp->selectedProp < 0 || sp->selectedProp > 1) {
std::cerr << "Proportion of intermediate-frequency COGs under frequency dependent selection: " << sp->selectedProp << "; needs to be between zero and one" << std::endl;
tmpvalid = 0;
} else if (sp->selectedProp < 1 && propFile == 0) {
std::cerr << "You are limiting the proportion of COGs under frequency-dependent selection in a nonsensical manner - please stop" << std::endl;
}
if (sp->popSize < 0) {
std::cerr << "Invalid population size value: " << sp->popSize << "; needs to be greater than zero" << std::endl;
tmpvalid = 0;
}
if (sp->numGen < 0) {
std::cerr << "Invalid number of generations: " << sp->numGen << "; needs to be greater than zero" << std::endl;
tmpvalid = 0;
}
if (vtCogName == 0 && (sp->programme != "s" && sp->programme != "x")) {
std::cerr << "Need a COG name: currently not defined" << std::endl;
tmpvalid = 0;
}
// check recombination parameters
if (sp->transformationProportion*sp->transformationRate == 0 && sp->transformationProportion+sp->transformationRate > 0) {
std::cerr << "Warning! Need to set transformation proportion (z) and transformation rate (e) both greater than zero for recombination to occur" << std::endl;
tmpvalid = 0;
} else if (sp->transformationProportion+sp->transformationRate > 0) {
if (sp->transformationAsymmetryLoci < 0) {
std::cerr << "Transformation asymmetry needs to be be greater than 0" << std::endl;
tmpvalid = 0;
}
if (!(sp->transformationAsymmetryMarker >= 0 && sp->transformationAsymmetryMarker <= 1)) {
std::cerr << "Transformation asymmetry needs to be between 0 and 1" << std::endl;
tmpvalid = 0;
}
}
// check input file exists
if (inputFilename != 0) {
std::ifstream infile(inputFilename);
if (!infile) {
tmpvalid = 0;
std::cerr << "Problem with input file: " << strerror(errno) << std::endl;
}
infile.close();
} else {
std::cerr << "No input file name provided!" << std::endl;
tmpvalid = 0;
}
// return value
return tmpvalid;
}
///////////////////////////////////////////////////
// parse COG frequency file for pure simulations //
///////////////////////////////////////////////////
int parseFrequencyFile(char *frequencyFilename,std::vector<cog*> *accessoryLoci) {
// sc output
std::ifstream fFile;
fFile.open(frequencyFilename,std::ifstream::in);
// parse frequency file line-by-line
if (fFile.is_open()) {
std::string line;
while (std::getline(fFile, line)) {
std::istringstream iss(line);
int sIndex = 0;
std::string cname;
double frac = -1;
while (iss) {
std::string temp;
while (getline(iss, temp, '\t')) {
if (sIndex == 0) {
cname = temp;
} else if (sIndex == 1) {
frac = std::stod(temp);
}
sIndex++;
}
// replace calculated equilibrium frequency with that specified by separate input file
// only retain loci included by previous criteria, and included in this second file
if (frac >= 0 && frac <= 1) {
std::vector<cog*>::iterator cit;
for (cit = accessoryLoci->begin(), accessoryLoci->end(); cit != accessoryLoci->end(); ++cit) {
if ((*cit)->id.compare(cname) == 0) {
(*cit)->eqFreq = frac;
}
}
} else {
std::cerr << "Fraction needs to be between 0 and 1: " << frac << std::endl;
return 1;
}
}
}
fFile.close();
} else {
std::cerr << "Unable to read file " << frequencyFilename << std::endl;
return 1;
}
return 0;
}
//////////////////////////////
// parse COG weighting file //
//////////////////////////////
int parseWeightingFile(char* weightingFilename,std::vector<cog*> *accessoryLoci) {
// open weighting file
std::ifstream wFile;
wFile.open(weightingFilename,std::ifstream::in);
// parse weighting file
if (wFile.is_open()) {
std::string line;
while (std::getline(wFile, line)) {
// parse values from line
std::istringstream iss(line);
int index = 0;
std::string cname;
double weight = 1.0;
while (iss) {
std::string temp;
while (getline(iss, temp, '\t')) {
if (index == 0) {
cname = temp;
} else {
weight = std::stof(temp);
}
std::vector<cog*>::iterator cit;
for (cit = accessoryLoci->begin(), accessoryLoci->end(); cit != accessoryLoci->end(); ++cit) {
if ((*cit)->id.compare(cname) == 0) {
(*cit)->weight = weight;
}
}
index++;
}
}
}
wFile.close();
} else {
std::cerr << "Unable to read file " << weightingFilename << std::endl;
return 1;
}
return 0;
}
/////////////////////////////
// parse COG ordering file //
/////////////////////////////
int parseOrderingFile(char* orderingFilename,std::vector<cog*> *accessoryLoci,struct parms *sp) {
// reordered list
std::vector<std::string> orderedAccessoryLoci;
std::vector<cog*>::iterator cit;
// open ordering file
std::ifstream oFile;
oFile.open(orderingFilename,std::ifstream::in);
// parse weighting file
if (oFile.is_open()) {
std::string line;
while (std::getline(oFile, line)) {
// parse values from line
std::istringstream iss(line);
while (iss) {
std::string cogName;
while (getline(iss, cogName)) {
orderedAccessoryLoci.push_back(cogName);
}
}
}
oFile.close();
} else {
std::cerr << "Unable to read file " << orderingFilename << std::endl;
return 1;
}
// check no loci have been duplicated, or lost, during reordering
if (accessoryLoci->size() != orderedAccessoryLoci.size()) {
std::cerr << "Duplicate or missing COGs found in COG reordering file: expecting " << accessoryLoci->size() << ", found " << orderedAccessoryLoci.size() << "; beneath the lists are compared:" << std::endl;
for (unsigned int j = 0; j < orderedAccessoryLoci.size(); j++) {
std::cerr << orderedAccessoryLoci[j] << "\t";
for (unsigned int i = 0; i < accessoryLoci->size(); i++) {
if ((*accessoryLoci)[i]->id == orderedAccessoryLoci[j]) {
std::cerr << (*accessoryLoci)[i]->id;
}
}
std::cerr << std::endl;
}
std::cerr << "Alternative ordering:" << std::endl;
for (unsigned int i = 0; i < accessoryLoci->size(); i++) {
std::cerr << (*accessoryLoci)[i]->id << "\t";
for (unsigned int j = 0; j < orderedAccessoryLoci.size(); j++) {
if ((*accessoryLoci)[i]->id == orderedAccessoryLoci[j]) {
std::cerr << orderedAccessoryLoci[j] << std::endl;
}
}
}
return 1;
}
// assign weights appropriately - most conserved frequencies are at the END of the list
unsigned int cindex = 0;
if (sp->het_mode == "l") { // logistic
double max_value = sp->lowerSelection + 1.0 / (1.0 + exp(-1.0 * sp->decayRate * (float(accessoryLoci->size()) - (1 - sp->selectedProp) * float(accessoryLoci->size()))));
for (unsigned int cindex = 0; cindex < orderedAccessoryLoci.size(); cindex++) {
for (cit = accessoryLoci->begin(), accessoryLoci->end(); cit != accessoryLoci->end(); ++cit) {
if ((*cit)->id.compare(orderedAccessoryLoci[cindex]) == 0) {
double relative_weight_from_order = (sp->lowerSelection + 1.0 / (1.0 + exp(-1.0 * sp->decayRate * (float(cindex) + 1.0 - (1 - sp->selectedProp) * float(accessoryLoci->size()))))) * (1 / max_value);
(*cit)->weight = sp->higherSelection * relative_weight_from_order;
break;
}
}
}
} else if (sp->het_mode == "e") { // exponential
double max_value = sp->lowerSelection + exp(-1 * sp->decayRate * 0.0);
for (unsigned int cindex = 0; cindex < orderedAccessoryLoci.size(); cindex++) {
for (cit = accessoryLoci->begin(), accessoryLoci->end(); cit != accessoryLoci->end(); ++cit) {
if ((*cit)->id.compare(orderedAccessoryLoci[cindex]) == 0) {
double relative_weight_from_order = (sp->lowerSelection + exp(-1 * sp->decayRate * float(accessoryLoci->size() - cindex - 1))) * (1 / max_value);
(*cit)->weight = sp->higherSelection * relative_weight_from_order;
break;
}
}
}
} else if (sp->het_mode == "r") { // linear
double max_value = sp->lowerSelection + 1;
for (unsigned int cindex = 0; cindex < orderedAccessoryLoci.size(); cindex++) {
for (cit = accessoryLoci->begin(), accessoryLoci->end(); cit != accessoryLoci->end(); ++cit) {
if ((*cit)->id.compare(orderedAccessoryLoci[cindex]) == 0) {
double relative_weight_from_order = sp->lowerSelection + 1 - (float(accessoryLoci->size() - cindex - 1) * sp->decayRate);
relative_weight_from_order = relative_weight_from_order * (1 / max_value);
if (relative_weight_from_order < 0.0) {
relative_weight_from_order = 0.0;
}
(*cit)->weight = sp->higherSelection * relative_weight_from_order;
break;
}
}
}
} else if (sp->het_mode == "s") { // step
for (unsigned int cindex = 0; cindex < orderedAccessoryLoci.size(); cindex++) {
for (cit = accessoryLoci->begin(), accessoryLoci->end(); cit != accessoryLoci->end(); ++cit) {
if ((*cit)->id.compare(orderedAccessoryLoci[cindex]) == 0) {
if ((float(cindex)/float(orderedAccessoryLoci.size())) <= (1.0-sp->selectedProp)) {
(*cit)->weight = sp->lowerSelection;
} else {
(*cit)->weight = sp->higherSelection;
}
break;
}
}
}
} else {
std::cerr << "Allowed heterogeneous functions are (l)ogistic, (e)xponential, linea(r) and (s)tep" << std::endl;
exit(1);
}
return 0;
}
////////////////////////////////
// Pre-processing information //
////////////////////////////////
///////////////////////////
// Generate migrant pool //
///////////////////////////
int generateMigrantPool(std::vector<std::vector<std::vector<isolate*> > > *migrantPool, std::vector<isolate*> *population, std::vector<isolate*> *migrant_population, char* migrantFilename, std::vector<int> *scList, int maxScNum, int minGen,struct parms *p) {
// Split population for immigration by SC
if (p->immigrationType == 1) {
int divCheck = 1;
std::vector<std::vector<isolate*> > *populationBySc = new std::vector<std::vector<isolate*> >;
if (migrantFilename != NULL) {
divCheck = dividePopulationForImmigration(migrant_population,scList,populationBySc,maxScNum);
} else {
divCheck = dividePopulationForImmigration(population,scList,populationBySc,maxScNum);
}
if (divCheck != 0) {
std::cerr << "Unable to split population into sequence clusters" << std::endl;
return 1;
}
migrantPool->push_back(*populationBySc);
// Split by time
} else if (p->immigrationType == 2) {
// split population for immigration by time
int divCheck = 1;
std::vector<std::vector<isolate*> > *populationByTime = new std::vector<std::vector<isolate*> >;
if (migrantFilename != NULL) {
divCheck = dividePopulationForImmigrationByTime(migrant_population,minGen,p->numGen,populationByTime);
} else {
divCheck = dividePopulationForImmigrationByTime(population,minGen,p->numGen,populationByTime);
}
if (divCheck != 0) {
std::cerr << "Unable to split population by isolation times" << std::endl;
return 1;
}
migrantPool->push_back(*populationByTime);
// Split by time and strain
} else if (p->immigrationType == 3) {
// split population for immigration by time
int divCheck = 1;
std::vector<std::vector<isolate*> > *populationByTime = new std::vector<std::vector<isolate*> > (p->numGen+1, std::vector<isolate*>());
if (migrantFilename != NULL) {
divCheck = dividePopulationForImmigrationByTime(migrant_population,minGen,p->numGen,populationByTime);
} else {
divCheck = dividePopulationForImmigrationByTime(population,minGen,p->numGen,populationByTime);
}
if (divCheck != 0) {
std::cerr << "Unable to split population by isolation times" << std::endl;
return 1;
}
// then split each time point by strain
for (int g = 0; g <= p->numGen; g++) {
std::vector<std::vector<isolate*> > *populationByTimeAndSc = new std::vector<std::vector<isolate*> >;
if ((*populationByTime)[g].size() >= 1) {
std::vector<isolate*> *tmpStrains = new std::vector<isolate*>;
tmpStrains = &(*populationByTime)[g]; // needs fixing
divCheck = dividePopulationForImmigration(tmpStrains,scList,populationByTimeAndSc,maxScNum);
if (divCheck != 0) {
std::cerr << "Unable to split population by SC for time " << g << std::endl;
return 1;
} else {
migrantPool->push_back(*populationByTimeAndSc);
}
} else {
migrantPool->push_back(*populationByTimeAndSc);
}
}
// Do not split, just sample at random
} else {
std::vector<std::vector<isolate*> > *tmpStrains = new std::vector<std::vector<isolate*> >;
if (migrantFilename != NULL) {
tmpStrains->push_back(*migrant_population);
} else {
tmpStrains->push_back(*population);
}
migrantPool->push_back(*tmpStrains);
}
return 0;
}
///////////////////////////////////////////
// divide isolates by SC for immigration //
///////////////////////////////////////////
int dividePopulationForImmigration(std::vector<isolate*> *pop,std::vector <int> *scList,std::vector<std::vector<isolate*> > *popBySc, int maxScNum) {
// check there are > 0 sequence clusters
if (maxScNum == 0) {
std::cerr << "Cannot find any sequence clusters" << std::endl;
}
std::vector<std::vector<isolate*> > tmpStrains(scList->size());
for (unsigned int s = 0; s < scList->size(); s++) {
std::vector<isolate*>::iterator cit;
for (cit = pop->begin(), pop->end(); cit != pop->end(); ++cit) {
if ((*cit)->sc == (*scList)[s]) {
tmpStrains[s].push_back((*cit));
}
}
}
(*popBySc) = tmpStrains;
return 0;
}
/////////////////////////////////////////////
// divide isolates by time for immigration //
/////////////////////////////////////////////
int dividePopulationForImmigrationByTime(std::vector<isolate*> *pop, int minGen, int numGen,std::vector<std::vector<isolate*> > *popByTime) {
std::vector<std::vector<isolate*> > tmpStrains(numGen+1);
std::vector<isolate*>::iterator cit;
for (cit = pop->begin(), pop->end(); cit != pop->end(); ++cit) {
for (int t = 0; t <= numGen; t++) {
if (((*cit)->year)-minGen <= numGen) { // && ((*cit)->year)-minGen >= 0) {
if (((*cit)->year)-minGen == t) {
tmpStrains[t].push_back((*cit));
}
}
}
}
(*popByTime) = tmpStrains;
return 0;
}
///////////////////////////
// get first year sample //
///////////////////////////
int getStartingIsolates(std::vector<isolate*> *pop,struct parms *sp,std::vector<isolate*> *first,std::vector<cog*> *accessoryLoci,int psize,std::vector<double> &eqFreq,std::vector<double> &cogWeights,std::vector<double> &cogDeviations,std::vector<int> &startingVtScFrequencies,std::vector<int> &startingNvtScFrequencies,std::vector<int> *scList, int minGen, float seedStartingPopulation, char* migrantFilename, std::vector<isolate*> *migrant_population, int maxScNum) {
// get all isolates observed in the pre- or peri-vaccine samples
std::vector<isolate*> *possibleFirst = new std::vector<isolate*>;
std::vector<isolate*> *possibleFirst_unsampled = new std::vector<isolate*>;
std::vector<isolate*>::iterator iter;
std::vector<int> observedVtSc;
std::vector<int> observedNvtSc;
int first_sample_size = 0;
for (iter = pop->begin(), pop->end() ; iter != pop->end(); ++iter) {
if (minGen < 0) {
// Use pre-vaccine population if possible
if ((*iter)->year < 0) {
possibleFirst->push_back(*iter);
first_sample_size++;
} else {
possibleFirst_unsampled->push_back(*iter);
}
} else {
// if no pre-vaccine population, use the peri-vaccination population
if ((*iter)->year == 0) {
possibleFirst->push_back(*iter);
first_sample_size++;
} else {
possibleFirst_unsampled->push_back(*iter);
}
}
}
// add in genotypes not detected in first sample if seeding unsampled genotypes
if (seedStartingPopulation > 1e-6) {
// data structure for the seeding genotypes
std::vector< std::vector<isolate*> > *isolates_for_seeding = new std::vector<std::vector<isolate*> >(scList->size(),std::vector<isolate*>());
// calculate the number of unsampled bacteria to add
// seedStartingPopulation is the probability of not sampling each undetected genotype
float upper_freq = 1.0 - exp(log(seedStartingPopulation)/float(first_sample_size));
int number_of_unsampled_bacteria = round(upper_freq*psize);
std::vector< int > unseen_sc;
// if simplest migration type, select isolates from later generations
if (sp->immigrationType == 0) {
(*isolates_for_seeding)[0] = *possibleFirst_unsampled;
// isolates_for_seeding[0] = possibleFirst_unsampled;
// unseen_sc.push_back(0);
} else {
// migrationType == 1 - divide by strain and seed from any later timeperiod
// works with and without migration file
if (sp->immigrationType == 1) {
// divide population by strain
int divCheck = 1;
std::vector<std::vector<isolate*> > *isolatesBySc = new std::vector<std::vector<isolate*> >;
if (migrantFilename != NULL) {
divCheck = dividePopulationForImmigration(migrant_population,scList,isolatesBySc,maxScNum);
} else {
divCheck = dividePopulationForImmigration(pop,scList,isolatesBySc,maxScNum);
}
isolates_for_seeding = isolatesBySc;
if (divCheck != 0) {
std::cerr << "Unable to split population into sequence clusters" << std::endl;
return 1;
}
// Split by time
} else if (sp->immigrationType == 2) {
// split population for immigration by time
std::vector<std::vector<isolate*> > *isolatesByTime = new std::vector<std::vector<isolate*> >;
int divCheck = 1;
if (migrantFilename == NULL) {
std::cerr << "Need a separate migration file when seeding the initial population with migration mode 2" << std::endl;
return 1;
} else {
divCheck = dividePopulationForImmigrationByTime(migrant_population,minGen,sp->numGen,isolatesByTime);
}
if (divCheck != 0) {
std::cerr << "Unable to split population by isolation times" << std::endl;
return 1;
}
// add to main data structure here
if (minGen < 0) {
for (int gen = 0; gen < (0-minGen); gen++) {
if ((*isolatesByTime)[gen].size() > 0) {
for (int x = 0; x < (*isolatesByTime)[gen].size(); x++) {
(*isolates_for_seeding)[0].push_back((*isolatesByTime)[gen][x]);
}
}
}
} else {
(*isolates_for_seeding)[0] = (*isolatesByTime)[0];
}
// Check possible seed isolates were found
if ((*isolates_for_seeding)[0].size() == 0) {
std::cerr << "No possible seed isolates found" << std::endl;
return 1;