forked from mhoopmann/hardklor
-
Notifications
You must be signed in to change notification settings - Fork 0
/
CHardklor.cpp
2320 lines (1872 loc) · 64.5 KB
/
CHardklor.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
/*
Copyright 2007-2016, Michael R. Hoopmann, Institute for Systems Biology
Michael J. MacCoss, University of Washington
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
/*
Hardklör - Thanks to Aaron Klammer (Klezmer) and
Greg Finney for the name suggestions.
This program scans through high resolution mass spectra,
predicts the monoisotopic mass and charge state of any potential
peptides (or proteins), generates predicted isotope distributions
of averagine and modified averagine molecules matching the mass
of each distribution, then correlates the various combinations of each
distribution with the spectrum data to find a best match.
This application was first designed to identify chlorinated peptides,
hence the name Hardklör. Due to the distinguishing characteristics of
a chlorinated distribution, this application makes it possible to predict
if the observed distribution is in fact chlorinated. The application
has since been extended to differentiate any measurable atomic or
enrichment modification.
The application utilizes an object model, so components may
be used in other applications. Furthermore, the design was made
to be extended, or possibly embedded in other software.
Version 1.0 is the first public release.
*/
#include "CHardklor.h"
#include "CAveragine.h"
#include "CMercury8.h"
#include "CSpecAnalyze.h"
#include "Smooth.h"
#include <iomanip>
#include <cstdio>
#include <io.h>
using namespace std;
using namespace MSToolkit;
SSObject::SSObject(){
pepVar = new vector<sInt>;
corr=0;
}
SSObject::SSObject(const SSObject& c){
corr = c.corr;
pepVar = new vector<sInt>;
for(unsigned int i=0;i<c.pepVar->size();i++) pepVar->push_back(c.pepVar->at(i));
}
SSObject::~SSObject(){
delete pepVar;
}
SSObject& SSObject::operator=(const SSObject& c){
if (this != &c) {
corr = c.corr;
delete pepVar;
pepVar = new vector<sInt>;
for(unsigned int i=0;i<c.pepVar->size();i++) pepVar->push_back(c.pepVar->at(i));
}
return *this;
}
void SSObject::addVar(int a, int b){
sInt s;
s.iLower = a;
s.iUpper = b;
pepVar->push_back(s);
}
void SSObject::clear(){
delete pepVar;
pepVar = new vector<sInt>;
corr = 0;
}
CHardklor::CHardklor(){
averagine=NULL;
mercury=NULL;
bEcho=true;
bMem=false;
}
CHardklor::CHardklor(CAveragine *a, CMercury8 *m){
averagine=a;
mercury=m;
sa.setAveragine(averagine);
sa.setMercury(mercury);
bEcho=true;
bMem=false;
}
CHardklor::~CHardklor(){
averagine=NULL;
mercury=NULL;
}
void CHardklor::Echo(bool b){
bEcho=b;
}
void CHardklor::SetAveragine(CAveragine *a){
averagine=a;
sa.setAveragine(averagine);
}
void CHardklor::SetMercury(CMercury8 *m){
mercury=m;
sa.setMercury(mercury);
}
int CHardklor::GoHardklor(CHardklorSetting sett, Spectrum* s){
cs = sett;
Analyze(s);
return 0;
}
//sorts vector of Results from high to low
int CHardklor::compareData(const void *p1, const void *p2){
const Result d1 = *(Result *)p1;
const Result d2 = *(Result *)p2;
if(d1.data<d2.data) return 1;
else if(d1.data>d2.data) return -1;
else return 0;
}
void CHardklor::Analyze(Spectrum* s) {
//Objects
MSReader r;
CNoiseReduction nr(&r,cs);
PT=averagine->getPT();
//iterators
unsigned int k; //counters for loops
int TotalIterations=0;
int TotalScans=0;
int i;
//Variables for file and clock management
int minutes, seconds;
loadTime=0;
analysisTime=0;
splitTime=0;
//placeholders for data output to file
//int pepID;
//int varID;
//Variables for some basic information output.
int iPercent;
int zeroPep=0; //Stores the number of spectra from which no potential peptides could be identified
int manyPep=0; //Stores the number of spectra from which the number of potential peptides
//exceeds the user-defined threshold.
int lowSigPep=0; //Stores the number of spectra whose max intensity was below the user defined threshold.
//Build variants (modifications) used in the analysis
pepVariants.clear();
if(!cs.noBase) {
CHardklorVariant hkv;
pepVariants.push_back(hkv);
}
for(k=0;k<cs.variant->size();k++) pepVariants.push_back(cs.variant->at(k));
//Our temporary spectrum
Spectrum curSpec;
Spectrum cutSpec;
//These are for splitting large spectra
bool bCutMe=false;
bool ReadScan=false;
bool bFirst=true;
CSplitSpectrum* cSS;
int winCount=0;
vResults.clear();
//Ouput file info to user
if(bEcho){
if(s==NULL) cout << "Reading from file: " << cs.inFile << endl;
if(!bMem) cout << "Writing to file: " << cs.outFile << endl;
}
if(cs.fileFormat==dunno) {
cout << "Unknown file format or bad extension." << endl;
return;
}
//Start of algorithm here.
getTimerFrequency(timerFrequency);
getExactTime(startTime);
//Read in the initial spectrum
r.setFilter(cs.mzXMLFilter);
r.setRawFilter(cs.rawFilter);
if(s!=NULL){
curSpec=*s;
} else {
if(cs.boxcar==0){
//if((cs.scan.iLower>0) && (cs.scan.iLower==cs.scan.iUpper)) r.readFile(&cs.inFile[0],curSpec,cs.scan.iLower);
//else if(cs.scan.iLower>0) r.readFile(&cs.inFile[0],curSpec,cs.scan.iLower);
if(cs.scan.iLower>0){
int scn= cs.scan.iLower;
r.readFile(&cs.inFile[0], curSpec, scn);
while(curSpec.getScanNumber()==0){
scn++;
if(cs.scan.iUpper>0){
if(scn>cs.scan.iUpper) break;
} else {
if(scn>r.getLastScan()) break;
}
r.readFile(NULL, curSpec, scn);
}
} else r.readFile(&cs.inFile[0],curSpec);
//this is the command to filter by persistence without boxcar averaging
// if(!nr.DeNoise(curSpec)) curSpec.setScanNumber(0);
} else {
if(cs.boxcarFilter>0){
if(!nr.DeNoiseC(curSpec)) curSpec.setScanNumber(0);
} else {
if(!nr.DeNoiseD(curSpec)) curSpec.setScanNumber(0);
}
}
}
TotalScans++;
getExactTime(stopTime);
tmpTime1=toMicroSec(stopTime);
tmpTime2=toMicroSec(startTime);
loadTime=tmpTime1-tmpTime2;
//Check that file was read
if(curSpec.getScanNumber()==0) {
if(s!=NULL) {
cout << "Spectrum is invalid." << endl;
return;
}
if(cs.scan.iLower>0) cout << cs.inFile << " is invalid, or requested scan number is of incorrect format." << endl;
else cout << cs.inFile << " is invalid, or contains no spectrum." << endl;
return;
}
currentScanNumber = curSpec.getScanNumber();
//Open a file for output. Results will be written on the fly as they come out of the algorithm.
if(!bMem){
fptr.open(&cs.outFile[0],ios::out|ios::app);
if(!fptr.good()) cout << "Output file error" << endl;
fptr << setiosflags(ios::fixed) << setprecision(4);
}
if(!bMem && cs.xml){
fptr << "<Hardklor>" << endl;
fptr << "<File InputFilename=\"" << cs.inFile << "\" OutputFilename=\"" << cs.outFile << "\">" << endl;
WriteParams(fptr,1);
}
//Reset some basic stat counters
manyPep=0;
zeroPep=0;
lowSigPep=0;
//Set and display on screen percentage counter
iPercent=0;
if(bEcho) cout << iPercent;
//While there is still data to read in the file.
while(true){
//Load next spectrum to analyze
if(!bFirst){
//close out xml tag for previous spectrum
if(!bMem && cs.xml) fptr << "</Spectrum>" << endl;
if(s!=NULL) break;
//track load time
getExactTime(startTime);
if(cs.boxcar==0){
r.readFile(NULL,curSpec);
//case 1: nr.DeNoise(curSpec); break;
} else {
if(cs.boxcarFilter>0) nr.DeNoiseC(curSpec);
else nr.DeNoiseD(curSpec);
}
getExactTime(stopTime);
tmpTime1=toMicroSec(stopTime);
tmpTime2=toMicroSec(startTime);
loadTime+=tmpTime1-tmpTime2;
} else {
bFirst=false; //mark that the first scan has been processed
}
//Write scan information to output file.
if(curSpec.getScanNumber()!=0){
if(!bMem){
if(cs.scan.iUpper>0 && curSpec.getScanNumber()>cs.scan.iUpper) break;
if(cs.reducedOutput) WriteScanLine(curSpec,fptr,2);
else if(cs.xml) WriteScanLine(curSpec,fptr,1);
else WriteScanLine(curSpec,fptr,0);
} else {
currentScanNumber = curSpec.getScanNumber();
}
} else {
break; //exit if there is no spectrum left to analyze
}
TotalScans++;
//Preprocess spectrum
//If we have an empty spectrum, go on to the next one
if(curSpec.size()==0) continue;
getExactTime(startTime);
if(cs.smooth>0) SG_Smooth(curSpec,cs.smooth,4);
//if(curSpec.getScanNumber()==1999){
// for(int xx=0;xx<curSpec.size();xx++) cout << curSpec[xx].mz << "\t" << curSpec[xx].intensity << endl;
//}
//Check our spectrum for file type. Zoom and UltraZoom scans do not
//need splitting.
if(cs.fileFormat==zs || cs.fileFormat==uzs){
sa.clear();
sa.setParams(cs);
sa.setSpectrum(curSpec);
sa.FindPeaks();
sa.PredictPeptides();
//do not analyze spectrum with 0 predicted peaks; Keep count of these occurrances.
if(sa.predPeak->size()==0){
zeroPep++;
continue;
}
AnalyzePeaks(sa);
} else {
//Reinitialize our split spectrum
cSS=new CSplitSpectrum(&curSpec,cs);
cSS->SetAveragine(averagine);
cSS->SetMercury(mercury);
//Check if data already centroided
if(cs.centroid) {
if(cs.chargeMode=='F' || cs.chargeMode=='P' || cs.chargeMode=='S'){
cout << "-cdm settings of F, P, and S (FFT, Patterson, Senko) only work on profile data." << endl;
cout << "Please choose settings of Q or C (QuickCharge, Complete)" << endl;
exit(5);
}
//This function directly copies the already centroided spectra to the CSS object
cSS->Centroid(curSpec);
//if not, process the data here (ultimately includes centroiding)
} else {
if(cs.boxcarFilter>0){ //TODO: Figure out how filtering interferes here
cs.sn=0;
cSS->Centroid(curSpec);
} else if(cs.staticSN) {
if(cs.sn==0) cSS->NoSplitAnalysis();
else cSS->NewSNPass(cs.snWindow);
} else {
cSS->OverlappingAnalysis(cs.snWindow);
if(cs.iAnalysis) cSS->IntersectionAnalysis();
else cSS->UnionAnalysis();
}
}
//Split the spectrum
cSS->MakeAnalysis(cs.winSize);
//Analyze each window
for(winCount=0;winCount<cSS->getNumWindows();winCount++){
sa = cSS->getWindow(winCount);
sa.setParams(cs);
sa.PredictPeptides();
//do not analyze spectrum with 0 predicted peaks; Keep count of these occurrances.
if(sa.predPeak->size()==0){
zeroPep++;
continue;
}
AnalyzePeaks(sa);
}
//clean up cSS object
delete cSS;
}
//Update the percentage indicator
if(bEcho){
if (r.getPercent() > iPercent){
if(iPercent<10) cout << "\b";
else cout << "\b\b";
cout.flush();
iPercent=r.getPercent();
cout << iPercent;
cout.flush();
}
}
if(!bMem && cs.xml) {
fptr << "</Spectrum>" << endl;
fptr << "</File>" << endl;
fptr << "</Hardklor>" << endl;
}
} //loop to next spectrum (while)
//Close the output file and clear it so it can be reused.
if(!bMem){
fptr.close();
fptr.clear();
}
if(bEcho) {
cout << "\n" << endl;
switch(cs.algorithm){
case SemiComplete:
cout << "SemiComplete analysis:" << endl;
break;
case SemiCompleteFast:
cout << "SemiCompleteFast analysis:" << endl;
break;
case Dynamic:
cout << "Dynamic analysis:" << endl;
break;
case DynamicSemiComplete:
cout << "DynamicSemiComplete analysis:" << endl;
break;
case SemiSubtractive:
cout << "SemiSubtractive analysis:" << endl;
break;
case FewestPeptides:
cout << "FewestPeptides analysis:" << endl;
break;
case FewestPeptidesChoice:
cout << "FewestPeptidesChoice analysis:" << endl;
break;
case FastFewestPeptides:
cout << "FastFewestPeptides analysis:" << endl;
break;
case FastFewestPeptidesChoice:
cout << "FastFewestPeptidesChoice analysis:" << endl;
break;
case Basic:
default:
cout << "Basic analysis:" << endl;
break;
}
}
//Output the simple statistics
if(bEcho) cout << " Total number of scans analyzed: " << TotalScans << endl;
//cout << " Number of (sub)scans not analyzed:" << endl;
//cout << " No Peptides Predicted: " << zeroPep << endl;
//cout << " Intensity Below Limit: " << lowSigPep << endl;
//cout << " Number of scans with more predicted peptides than were analyzed: " << manyPep << endl;
//cout << " Total Correlations Made: " << TotalIterations << endl;
//Output the time to analyze this file.
if(bEcho){
i=(int)timeToSec(loadTime,timerFrequency);
minutes = (int)(i/60);
seconds = i - (60*minutes);
cout << "\nFile access time: " << minutes << " minutes, " << seconds << " seconds." << endl;
i=(int)timeToSec(splitTime,timerFrequency);
minutes = (int)(i/60);
seconds = i - (60*minutes);
cout << "Split Time: " << minutes << " minutes, " << seconds << " seconds." << endl;
i=(int)timeToSec(analysisTime,timerFrequency);
minutes = (int)(i/60);
seconds = i - (60*minutes);
cout << "Analysis Time: " << minutes << " minutes, " << seconds << " seconds." << endl;
if (minutes==0 && seconds==0){
cout << "IMPOSSIBLE!!!" << endl;
} else if(minutes <=2){
cout << "HOLY FRIJOLE!!" << endl;
} else if(minutes<=5) {
cout << "Like lightning!" << endl;
} else if(minutes<=10){
cout << "That's pretty damn fast!" << endl;
} else if(minutes<=20){
cout << "Monkeys calculate faster than that!" << endl;
} else if(minutes<=30){
cout << "You should have taken a lunch break." << endl;
} else if(minutes<=40){
cout << "Oi! Too freakin' slow!!" << endl;
} else {
cout << "You might be able to eek out some better performance by adjusting your parameters." << endl;
}
}
PT=NULL;
}
bool CHardklor::AnalyzePeaks(CSpecAnalyze& sa){
int i;
SSObject bsso;
//Arrays for combinatorial analysis
float *match;
float *mismatch;
//Track analysis times
getExactTime(startTime);
//Make an averagine distribution for every variant specified in the conf file.
sa.MakePredictions(pepVariants);
//if there are no possible peptides, stop the analysis here.
if(sa.predPep->size()==0) {
getExactTime(stopTime);
tmpTime1=toMicroSec(stopTime);
tmpTime2=toMicroSec(startTime);
analysisTime+=tmpTime1-tmpTime2;
return false;
}
//Restructure mismatch arrays for faster correlation analysis
sa.BuildMismatchArrays();
//Send the distributions, and the observed data points from the spectrum to a recursive
//algorithm that will sum up every combination of every peptide in each of its chlorinated
//forms to find the combination that best fits the data.
//Dimension our arrays
match = new float[sa.peaks.size()];
for(i=0;i<sa.peaks.size();i++) match[i]=0;
if(sa.mismatchSize>0){
mismatch = new float[sa.mismatchSize];
for(i=0;i<sa.mismatchSize;i++) mismatch[i]=0;
} else {
mismatch = new float[1];
mismatch[0] = 0;
}
//clear prior data and select analysis algorithm
bsso.clear();
switch(cs.algorithm){
case SemiComplete:
SemiCompleteMethod(match,mismatch,&bsso,1,cs.depth,0);
break;
case SemiCompleteFast:
SemiCompleteFastMethod(match,mismatch,&bsso,1,cs.depth,0);
break;
case Dynamic:
DynamicMethod(match,mismatch,&bsso,1,cs.depth,0,0);
break;
case DynamicSemiComplete:
DynamicSemiCompleteMethod(match,mismatch,&bsso,1,cs.depth,0,0);
break;
case SemiSubtractive:
SemiSubtractiveMethod(&bsso,cs.depth);
break;
case FewestPeptides:
FewestPeptidesMethod(&bsso,cs.depth);
break;
case FewestPeptidesChoice:
FewestPeptidesChoiceMethod(&bsso,cs.depth);
break;
case FastFewestPeptides:
FastFewestPeptidesMethod(&bsso,cs.depth);
break;
case FastFewestPeptidesChoice:
FastFewestPeptidesChoiceMethod(&bsso,cs.depth);
break;
case Basic:
default:
BasicMethod(match,mismatch,&bsso,1,cs.depth,(int)sa.predPep->size()-1);
break;
}
//Clean up memory
delete [] match;
delete [] mismatch;
//Track analysis times
getExactTime(stopTime);
tmpTime1=toMicroSec(stopTime);
tmpTime2=toMicroSec(startTime);
analysisTime+=tmpTime1-tmpTime2;
//if we exceeded our threshold, output the data to file or store it in memoryt
if(bsso.corr > cs.corr) {
if(!bMem){
if(cs.reducedOutput) WritePepLine(bsso,PT,fptr,2);
else if(cs.xml) WritePepLine(bsso,PT,fptr,1);
else WritePepLine(bsso,PT,fptr,0);
} else {
ResultToMem(bsso,PT);
}
}
return true;
}
double CHardklor::LinReg(float *match, float *mismatch){
int i,sz;
double sxx=0,syy=0,sxy=0;
vector<sFloat> v;
sFloat tmp;
//Correlate matches
for(i=0;i<sa.peaks.size();i++){
tmp.fLower = sa.peaks.at(i).intensity;
tmp.fUpper = match[i];
v.push_back(tmp);
}
//Correlate mismatches with 0
for(i=0;i<sa.mismatchSize;i++){
if(mismatch[i]>0){
tmp.fLower = 0;
tmp.fUpper = mismatch[i];
v.push_back(tmp);
}
}
//Cosine angle correlation
sxy=0;
sxx=0;
syy=0;
sz=(int)v.size();
for(i=0;i<sz;i++){
sxy += (v.at(i).fLower*v.at(i).fUpper);
sxx += (v.at(i).fLower*v.at(i).fLower);
syy += (v.at(i).fUpper*v.at(i).fUpper);
}
if (sxx > 0 && syy > 0 && sxy > 0)
{
if (cs.reportAveragineAndMassOffset)
{
// Skyline usage - prefer normalized contrast angle
double angle = sxy / sqrt(sxx * syy);
return 1.0 - (acos(min(angle, 1.0)) * 2 / PI);
}
return sxy / sqrt(sxx * syy);
}
else return 0;
}
void CHardklor::BasicMethod(float *match, float *mismatch,SSObject *combo,
int depth, int maxDepth, int start){
SSObject bestCombo = *combo;
SSObject recCombo;
double RCorr;
double bestRCorr = combo->corr;
int a,k,n;
float intensity;
float *sumMatch;
float *sumMismatch;
sumMatch = new float[sa.peaks.size()];
if(sa.mismatchSize>0){
sumMismatch = new float[sa.mismatchSize];
} else {
sumMismatch = new float[1];
};
//Iterate through all predicted peptides
for(k=start; k>-1; k--) {
//check each variant
for(n=0; n<sa.predPep->at(k).VariantListSize(); n++){
intensity = sa.predPep->at(k).GetIntensity() - match[sa.predPep->at(k).GetMaxPeakIndex()];
if(intensity<0) {
//This predicted peptide cannot contribute to the analysis, so don't go
//any deeper
delete [] sumMatch;
delete [] sumMismatch;
return;
};
//Add the variant to the distribution being analyzed
//Do matches first
for(a=0;a<sa.peaks.size();a++){
sumMatch[a]=sa.predPep->at(k).GetVariant(n).GetMatch(a).intensity*intensity + match[a];
};
//Now add mismatches
for(a=0;a<sa.mismatchSize;a++){
sumMismatch[a]=sa.predPep->at(k).GetVariant(n).GetMismatch(a).intensity*intensity + mismatch[a];
};
//Correlate this combined distribution with the mass spec data.
//SSIterations++;
RCorr = LinReg(sumMatch,sumMismatch);
//cout << RCorr << endl;
recCombo = *combo;
recCombo.addVar(k,n);
recCombo.corr = RCorr;
//Check if it is the best, if so, mark it
if(recCombo.corr>bestCombo.corr) bestCombo = recCombo;
//Check recursions
if(depth<maxDepth){
BasicMethod(sumMatch,sumMismatch,&recCombo,depth+1,maxDepth,k-1);
};
//Check if it is the best, if so, mark it
if(recCombo.corr>bestCombo.corr) bestCombo = recCombo;
};
};
delete [] sumMatch;
delete [] sumMismatch;
*combo = bestCombo;
};
void CHardklor::SemiCompleteMethod(float *match, float *mismatch,SSObject *combo,
int depth, int maxDepth, int start){
SSObject bestCombo = *combo;
SSObject recCombo;
double RCorr;
double bestRCorr = combo->corr;
int a,n;
unsigned int k;
float *sumMatch;
float *sumMismatch;
sumMatch = new float[sa.peaks.size()];
if(sa.mismatchSize>0){
sumMismatch = new float[sa.mismatchSize];
} else {
sumMismatch = new float[1];
};
//Iterate through all predicted peptides
for(k=start; k<sa.predPep->size(); k++) {
//check each variant
for(n=0; n<sa.predPep->at(k).VariantListSize(); n++){
//Add the variant to the distribution being analyzed
//Do matches first
for(a=0;a<sa.peaks.size();a++){
sumMatch[a]=sa.predPep->at(k).GetVariant(n).GetMatch(a).intensity + match[a];
};
//Now add mismatches
for(a=0;a<sa.mismatchSize;a++){
sumMismatch[a]=sa.predPep->at(k).GetVariant(n).GetMismatch(a).intensity + mismatch[a];
};
//Correlate this combined distribution with the mass spec data.
//SSIterations++;
RCorr = LinReg(sumMatch,sumMismatch);
recCombo = *combo;
recCombo.addVar(k,n);
recCombo.corr = RCorr;
//Check if it is the best, if so, mark it
if(recCombo.corr>bestCombo.corr) bestCombo = recCombo;
}
}
//If we reached threshold, stop here without recursion
if(bestCombo.corr>cs.corr) {
delete [] sumMatch;
delete [] sumMismatch;
*combo = bestCombo;
return;
}
if(depth<maxDepth){
//Iterate through all predicted peptides
for(k=start; k<sa.predPep->size(); k++) {
//check each variant
for(n=0; n<sa.predPep->at(k).VariantListSize(); n++){
//Add the variant to the distribution being analyzed
//Do matches first
for(a=0;a<sa.peaks.size();a++){
sumMatch[a]=sa.predPep->at(k).GetVariant(n).GetMatch(a).intensity + match[a];
}
//Now add mismatches
for(a=0;a<sa.mismatchSize;a++){
sumMismatch[a]=sa.predPep->at(k).GetVariant(n).GetMismatch(a).intensity + mismatch[a];
}
recCombo = *combo;
recCombo.addVar(k,n);
recCombo.corr = RCorr;
//Check recursions
SemiCompleteMethod(sumMatch,sumMismatch,&recCombo,depth+1,maxDepth,k+1);
//Check if it is the best, if so, mark it
if(recCombo.corr>bestCombo.corr) bestCombo = recCombo;
}
}
}
delete [] sumMatch;
delete [] sumMismatch;
*combo = bestCombo;
}
void CHardklor::SemiCompleteFastMethod(float *match, float *mismatch,SSObject *combo,
int depth, int maxDepth, int start){
SSObject bestCombo = *combo;
SSObject recCombo;
double RCorr;
double bestRCorr = combo->corr;
int a,b,n;
unsigned int k;
int numArrays=0;
for(k=start;k<sa.predPep->size();k++){
numArrays+=sa.predPep->at(k).VariantListSize();
}
float **sumMatch;
float **sumMismatch;
sumMatch = new float* [numArrays];
sumMismatch = new float* [numArrays];
for(n=0;n<numArrays;n++){
sumMatch[n] = new float[sa.peaks.size()];
if(sa.mismatchSize>0){
sumMismatch[n] = new float[sa.mismatchSize];
} else {
sumMismatch[n] = new float[1];
}
}
b=0;
//Iterate through all predicted peptides
for(k=start; k<sa.predPep->size(); k++) {
//check each variant
for(n=0; n<sa.predPep->at(k).VariantListSize(); n++){
//Add the variant to the distribution being analyzed
//Do matches first
for(a=0;a<sa.peaks.size();a++){
sumMatch[b][a]=sa.predPep->at(k).GetVariant(n).GetMatch(a).intensity + match[a];
}
//Now add mismatches
for(a=0;a<sa.mismatchSize;a++){
sumMismatch[b][a]=sa.predPep->at(k).GetVariant(n).GetMismatch(a).intensity + mismatch[a];
}
//Correlate this combined distribution with the mass spec data.
//SSIterations++;
RCorr = LinReg(sumMatch[b],sumMismatch[b]);
recCombo = *combo;
recCombo.addVar(k,n);
recCombo.corr = RCorr;
//Check if it is the best, if so, mark it
if(recCombo.corr>bestCombo.corr) bestCombo = recCombo;
b++;
}
}
//If we reached threshold, stop here without recursion
if(bestCombo.corr>cs.corr) {
for(n=0;n<numArrays;n++) {
delete [] sumMatch[n];
delete [] sumMismatch[n];
};
delete [] sumMatch;
delete [] sumMismatch;
*combo = bestCombo;
return;
}
if(depth<maxDepth){
//Iterate through all predicted peptides
b=0;
for(k=start; k<sa.predPep->size(); k++) {
//check each variant
for(n=0; n<sa.predPep->at(k).VariantListSize(); n++){
recCombo = *combo;
recCombo.addVar(k,n);
recCombo.corr = RCorr;
//Check recursions
SemiCompleteFastMethod(sumMatch[b],sumMismatch[b],&recCombo,depth+1,maxDepth,k+1);
//Check if it is the best, if so, mark it
if(recCombo.corr>bestCombo.corr) bestCombo = recCombo;
b++;
}
}
}
for(n=0;n<numArrays;n++) {
delete [] sumMatch[n];
delete [] sumMismatch[n];
}
delete [] sumMatch;
delete [] sumMismatch;
*combo = bestCombo;
}
void CHardklor::DynamicMethod(float *match, float *mismatch,SSObject *combo,
int depth, int maxDepth, int start, double corr){
SSObject bestCombo = *combo;
SSObject recCombo;
double RCorr;
double bestRCorr = combo->corr;
int a,n;
unsigned int k;
float *sumMatch;
float *sumMismatch;
sumMatch = new float[sa.peaks.size()];
if(sa.mismatchSize>0){
sumMismatch = new float[sa.mismatchSize];
} else {
sumMismatch = new float[1];
};
//Iterate through all predicted peptides
for(k=start; k<sa.predPep->size(); k++) {
//check each variant
for(n=0; n<sa.predPep->at(k).VariantListSize(); n++){
//Add the variant to the distribution being analyzed
//Do matches first
for(a=0;a<sa.peaks.size();a++){
sumMatch[a]=sa.predPep->at(k).GetVariant(n).GetMatch(a).intensity + match[a];
};