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
|
#include "SequenceFuns.h"
#include <assert.h>
void complementSeqNumbers(char* ReadsIn, char* ReadsOut, uint Lread) {//complement the numeric sequences
for (uint jj=0;jj<Lread;jj++) {
switch (int(ReadsIn[jj])){
case (3): ReadsOut[jj]=char(0);break;
case (2): ReadsOut[jj]=char(1);break;
case (1): ReadsOut[jj]=char(2);break;
case (0): ReadsOut[jj]=char(3);break;
default: ReadsOut[jj]=ReadsIn[jj];
};
};
};
void revComplementNucleotides(char* ReadsIn, char* ReadsOut, uint Lread) {//complement the numeric sequences
for (uint jj=0;jj<Lread;jj++) {
switch (ReadsIn[Lread-1-jj]){
case ('A'): ReadsOut[jj]='T';break;
case ('C'): ReadsOut[jj]='G';break;
case ('G'): ReadsOut[jj]='C';break;
case ('T'): ReadsOut[jj]='A';break;
case ('N'): ReadsOut[jj]='N';break;
case ('R'): ReadsOut[jj]='Y';break;
case ('Y'): ReadsOut[jj]='R';break;
case ('K'): ReadsOut[jj]='M';break;
case ('M'): ReadsOut[jj]='K';break;
case ('S'): ReadsOut[jj]='S';break;
case ('W'): ReadsOut[jj]='W';break;
case ('B'): ReadsOut[jj]='V';break;
case ('D'): ReadsOut[jj]='H';break;
case ('V'): ReadsOut[jj]='B';break;
case ('H'): ReadsOut[jj]='D';break;
case ('a'): ReadsOut[jj]='t';break;
case ('c'): ReadsOut[jj]='g';break;
case ('g'): ReadsOut[jj]='c';break;
case ('t'): ReadsOut[jj]='a';break;
case ('n'): ReadsOut[jj]='n';break;
case ('r'): ReadsOut[jj]='y';break;
case ('y'): ReadsOut[jj]='r';break;
case ('k'): ReadsOut[jj]='m';break;
case ('m'): ReadsOut[jj]='k';break;
case ('s'): ReadsOut[jj]='s';break;
case ('w'): ReadsOut[jj]='w';break;
case ('b'): ReadsOut[jj]='v';break;
case ('d'): ReadsOut[jj]='h';break;
case ('v'): ReadsOut[jj]='b';break;
case ('h'): ReadsOut[jj]='d';break;
default: ReadsOut[jj]=ReadsIn[Lread-1-jj];
};
};
};
void revComplementNucleotides(string &seq) {//complement the numeric sequences
string seq1(seq);
for (uint jj=0;jj<seq.size();jj++) {
switch (seq1[seq.size()-1-jj]){
case ('A'): seq[jj]='T';break;
case ('C'): seq[jj]='G';break;
case ('G'): seq[jj]='C';break;
case ('T'): seq[jj]='A';break;
case ('N'): seq[jj]='N';break;
case ('R'): seq[jj]='Y';break;
case ('Y'): seq[jj]='R';break;
case ('K'): seq[jj]='M';break;
case ('M'): seq[jj]='K';break;
case ('S'): seq[jj]='S';break;
case ('W'): seq[jj]='W';break;
case ('B'): seq[jj]='V';break;
case ('D'): seq[jj]='H';break;
case ('V'): seq[jj]='B';break;
case ('H'): seq[jj]='D';break;
case ('a'): seq[jj]='t';break;
case ('c'): seq[jj]='g';break;
case ('g'): seq[jj]='c';break;
case ('t'): seq[jj]='a';break;
case ('n'): seq[jj]='n';break;
case ('r'): seq[jj]='y';break;
case ('y'): seq[jj]='r';break;
case ('k'): seq[jj]='m';break;
case ('m'): seq[jj]='k';break;
case ('s'): seq[jj]='s';break;
case ('w'): seq[jj]='w';break;
case ('b'): seq[jj]='v';break;
case ('d'): seq[jj]='h';break;
case ('v'): seq[jj]='b';break;
case ('h'): seq[jj]='d';break;
default: seq[jj]=seq1[seq.size()-1-jj];
};
};
};
char nuclToNumBAM(char cc){
switch (cc) {//=ACMGRSVTWYHKDBN
case ('='): cc=0;break;
case ('A'): case ('a'): cc=1;break;
case ('C'): case ('c'): cc=2;break;
case ('M'): case ('m'): cc=3;break;
case ('G'): case ('g'): cc=4;break;
case ('R'): case ('r'): cc=5;break;
case ('S'): case ('s'): cc=6;break;
case ('V'): case ('v'): cc=7;break;
case ('T'): case ('t'): cc=8;break;
case ('W'): case ('w'): cc=9;break;
case ('Y'): case ('y'): cc=10;break;
case ('H'): case ('h'): cc=11;break;
case ('K'): case ('k'): cc=12;break;
case ('D'): case ('d'): cc=13;break;
case ('B'): case ('b'): cc=14;break;
case ('N'): case ('n'): cc=15;break;
default: cc=15;
};
return cc;
};
void nuclPackBAM(char* ReadsIn, char* ReadsOut, uint Lread) {//pack nucleotides for BAM
for (uint jj=0;jj<Lread/2;jj++) {
ReadsOut[jj]=nuclToNumBAM(ReadsIn[2*jj])<<4 | nuclToNumBAM(ReadsIn[2*jj+1]);
};
if (Lread%2==1) {
ReadsOut[Lread/2]=nuclToNumBAM(ReadsIn[Lread-1])<<4;
};
};
void convertNucleotidesToNumbers(const char* R0, char* R1, const uint Lread) {//transform sequence from ACGT into 0-1-2-3 code
for (uint jj=0;jj<Lread;jj++) {
switch (int(R0[jj])){
case (65): case(97):
R1[jj]=char(0);break;//A
case (67): case(99):
R1[jj]=char(1);break;//C
case (71): case(103):
R1[jj]=char(2);break;//G
case (84): case(116):
R1[jj]=char(3);break;//T
default:
R1[jj]=char(4);//anything else is converted to N
};
};
};
void convertCapitalBasesToNum(uint8_t *rS, uint64_t N)
{//only capital bases are allowed
for (uint64_t ib=0; ib<N; ib++) {
switch (rS[ib]) {
case 'A':
rS[ib]=0;
break;
case 'C':
rS[ib]=1;
break;
case 'G':
rS[ib]=2;
break;
case 'T':
rS[ib]=3;
break;
default:
rS[ib]=4;
};
};
};
uint convertNucleotidesToNumbersRemoveControls(const char* R0, char* R1, const uint Lread) {//transform sequence from ACGT into 0-1-2-3 code
uint iR1=0;
for (uint jj=0;jj<Lread;jj++) {
switch (int(R0[jj])){
case (65): case(97):
R1[jj]=char(0);break;//A
case (67): case(99):
R1[jj]=char(1);break;//C
case (71): case(103):
R1[jj]=char(2);break;//G
case (84): case(116):
R1[jj]=char(3);break;//T
default:
if (int(R0[jj]) < 32) {//control characters are skipped
continue;
} else {//all non-control non-ACGT characters are convreted to N
R1[jj]=char(4);//anything else
};
};
++iR1;
};
return iR1;
};
char convertNt01234(const char R0) {//transform sequence from ACGT into 0-1-2-3 code
switch(R0)
{
case('a'):
case('A'):
return 0;
break;
case('c'):
case('C'):
return 1;
break;
case('g'):
case('G'):
return 2;
break;
case('t'):
case('T'):
return 3;
break;
default:
return 4;
};
};
int32 convertNuclStrToInt32(const string S, uint32 &intOut) {
intOut=0;
int32 posN=-1;
for (uint32 ii=0; ii<S.size(); ii++) {
uint32 nt = (uint32) convertNt01234(S.at(ii));
if (nt>3) {//N
if (posN>=0)
return -2; //two Ns
posN=ii;
nt=0;
};
intOut = intOut << 2;
intOut +=nt;
//intOut += nt<<(2*ii);
};
return posN;
};
string convertNuclInt32toString(uint32 nuclNum, const uint32 L) {
string nuclOut(L,'N');
string nuclChar="ACGT";
for (uint32 ii=1; ii<=L; ii++) {
nuclOut[L-ii] = nuclChar[nuclNum & 3];
nuclNum = nuclNum >> 2;
};
return nuclOut;
};
int64 convertNuclStrToInt64(const string S, uint64 &intOut) {
intOut=0;
int64 posN=-1;
for (uint64 ii=0; ii<S.size(); ii++) {
uint64 nt = (uint64) convertNt01234(S.at(ii));
if (nt>3) {//N
if (posN>=0)
return -2; //two Ns
posN=ii;
nt=0;
};
intOut = intOut << 2;
intOut +=nt;
//intOut += nt<<(2*ii);
};
return posN;
};
string convertNuclInt64toString(uint64 nuclNum, const uint32 L) {
string nuclOut(L,'N');
string nuclChar="ACGT";
for (uint64 ii=1; ii<=L; ii++) {
nuclOut[L-ii] = nuclChar[nuclNum & 3];
nuclNum = nuclNum >> 2;
};
return nuclOut;
};
uint chrFind(uint Start, uint i2, uint* chrStart) {// find chromosome from global locus
uint i1=0, i3;
while (i1+1<i2) {
i3=(i1+i2)/2;
if ( chrStart[i3] > Start ) {
i2=i3;
} else {
i1=i3;
};
};
return i1;
};
uint localSearch(const char *x, uint nx, const char *y, uint ny, double pMM){
//find the best alignment of two short sequences x and y
//pMM is the maximum percentage of mismatches
uint nMatch=0, nMM=0, nMatchBest=0, nMMbest=0, ixBest=nx;
for (uint ix=0;ix<nx;ix++) {
nMatch=0; nMM=0;
for (uint iy=0;iy<min(ny,nx-ix);iy++) {
if (x[ix+iy]>3) continue;
if (x[ix+iy]==y[iy]) {
nMatch++;
} else {
nMM++;
};
};
if ( ( nMatch>nMatchBest || (nMatch==nMatchBest && nMM<nMMbest) ) && double(nMM)/double(nMatch)<=pMM) {
ixBest=ix;
nMatchBest=nMatch;
nMMbest=nMM;
};
};
return ixBest;
};
uint localSearchNisMM(const char *x, uint nx, const char *y, uint ny, double pMM){
//find the best alignment of two short sequences x and y
//pMM is the maximum percentage of mismatches
//Ns in x OR y are considered mismatches
uint nMatch=0, nMM=0, nMatchBest=0, nMMbest=0, ixBest=nx;
for (uint ix=0;ix<nx;ix++) {
nMatch=0; nMM=0;
for (uint iy=0;iy<min(ny,nx-ix);iy++) {
if (x[ix+iy]==y[iy] && y[iy]<4) {
nMatch++;
} else {
nMM++;
};
};
if ( ( nMatch>nMatchBest || (nMatch==nMatchBest && nMM<nMMbest) ) && double(nMM)/double(nMatch)<=pMM) {
ixBest=ix;
nMatchBest=nMatch;
nMMbest=nMM;
};
};
return ixBest;
};
uint32 localAlignHammingDist(const string &text, const string &query, uint32 &pos)
{
uint32 distBest=query.size();
if (text.size()<query.size()) {//query is longer than text, no match
return text.size()+1;
};
for (uint32 ii=0; ii<text.size()-query.size()+1; ii++) {
uint32 dist1=0;
for (uint32 jj=0; jj<query.size(); jj++) {
if (query[jj]!='N' && text[jj+ii]!=query[jj]) {//N in query does not count as mismatch
++dist1;
};
};
if (dist1<distBest) {
distBest=dist1;
pos=ii;
};
};
return distBest;
};
////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
/*
uint32 localSearchGeneral(const char *text, const uint32 textLen, const vector<char> &query, const int32 textStart, const int32 textEnd, double pMM, vector <uint32> vecMM, uint32 &nMM)
{
assert(textEnd <= (int32)textLen);
assert(textStart + (int32)query.size() >= 0);
nMM=0;
uint32 nMatchBest=0;
int32 posBest=textLen;
uint32 clippedL = 0;
int32 dirSearch = (textStart <= textEnd ? 1 : -1); //search direction
for (int32 pos=textStart; pos!=textEnd; pos+=dirSearch) {
int32 qs = max(0, -pos);
int32 qe = min((uint32)query.size(), (uint32)(textLen-pos) );
uint32 nMatch1=0, nMM1=0;
for (uint32 iq=qs; iq<qe; iq++) {
if (text[pos+iq]>3)
continue; //Ns in the text are not counted as matches or mismatches
if (text[pos+iq]==query[iq]) {
nMatch1++;
} else {
nMM1++;
if ( nMM1 >= vecMM.size() ) {
nMatch1=0;
break; //too many mismatches
};
};
};
//if ( (nMatch1>nMatchBest || (nMatch1==nMatchBest && nMM1<nMM)) && double(nMM1)<=double(nMatch1)*pMM ) {
if ( (nMatch1>nMatchBest || (nMatch1==nMatchBest && nMM1<nMM)) && nMM1<vecMM.size() && (qe-qs)>=vecMM[nMM1]) {
posBest=pos;
nMatchBest=nMatch1;
nMM=nMM1;
clippedL = (uint32)(textStart <= textEnd ? posBest+(int32)query.size(): -posBest+(int32)textLen );
};
};
return clippedL;
};
*/
///////////////////////////////////////////////////////////////////////////////////////////////////////////////
uint qualitySplit(char* r,uint L, uint maxNsplit, uint minLsplit, uint** splitR) {
//splits the read r[L] by quality scores q[L], outputs in splitR - split coordinate/length - per base
//returns number of good split regions
uint iR=0,iS=0,iR1,LgoodMin=0, iFrag=0;
while ( (iR<L) & (iS<maxNsplit) ) { //main cycle
//find next good base
while ( iR<L && r[iR]>3 ) {
if (r[iR]==MARK_FRAG_SPACER_BASE)
iFrag++; //count read fragments
iR++;
};
if (iR==L) break; //exit when reached end of read
iR1=iR;
//find the next bad base
while ( iR<L && r[iR]<=3 ) {
iR++;
};
if ( (iR-iR1)>LgoodMin ) LgoodMin=iR-iR1;
if ( (iR-iR1)<minLsplit ) continue; //too short for a good region
splitR[0][iS]=iR1; //good region start
splitR[1][iS]=iR-iR1; //good region length
splitR[2][iS]=iFrag; //good region fragment
iS++;
};
if (iS==0) splitR[1][0]=LgoodMin; //output min good piece length
return iS;
};
|
