-
Notifications
You must be signed in to change notification settings - Fork 12
/
Autopcr.cpp
450 lines (384 loc) · 10.8 KB
/
Autopcr.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
/*
GeneDoc: Multiple Sequence Alignment Editing Utility
Copyright (C) 2000, Karl Nicholas
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include "stdafx.h"
void
CGenedocDoc::AutoShadePCR(
ShadeSegStc *pSegArr,
int RowCount,
int ShadeLevel,
CDisplayVars *DisplayVars,
ShadeSegStc *pConsensusRow
)
{
TRY {
int i;
int MatchArr[2][26];
ShadePairStruct tSPS;
int tRC = pGSFiller->SegDataList.GetCount(); // Subtract 1 for comment row. here
ShadeSegStc *pOSegArr = new ShadeSegStc[tRC]; // Gonna need access to comment row here
if ( pOSegArr == 0 ) {
AfxMessageBox("AutoShadeQuantify:New Fail 1");
return;
}
int GrpNum = 0;
POSITION tPos = m_UserVars.m_DisplayVars.GetHeadPosition();
while ( tPos != NULL ) {
CDisplayVars* pDV = (CDisplayVars *)m_UserVars.m_DisplayVars.GetNext(tPos);
GrpNum++;
if ( pDV->GetGroupName() == DisplayVars->GetGroupName() ) break;
}
int pSegCount = 0;
tPos = pGSFiller->SegDataList.GetHeadPosition();
while (tPos != NULL ) {
CGeneSegment *tCGSeg = (CGeneSegment *)pGSFiller->SegDataList.GetNext(tPos);
if ( tCGSeg->GetStyle() == LINESEQUENCE && tCGSeg->m_DisplayGroup != GrpNum ) {
HANDLE tSegHandle = tCGSeg->GetTextHandle();
pOSegArr[pSegCount].pGeneStor = (GeneStor *) GlobalLock( tSegHandle );
pOSegArr[pSegCount].pCGSeg = tCGSeg;
if ( pOSegArr[pSegCount].pGeneStor == NULL) {
AfxMessageBox("AutoShade:GlobalLock:Fail:1");
delete pOSegArr;
return;
}
pSegCount++;
}
}
DWORD OuterCount = pSegArr[0].pCGSeg->GetTextLength();
// init locations
for ( DWORD tCount = 0L; tCount < OuterCount; ++tCount ) {
for ( i = 0; i < RowCount; ++i ) {
// Lets Clear out old shades while here.
GetLevelColors( DisplayVars, 0,
&(pSegArr[i].pGeneStor)[tCount].TextColor,
&(pSegArr[i].pGeneStor)[tCount].BackColor
);
char tChar = (pSegArr[i].pGeneStor)[tCount].CharGene;
// Reset Display Char while here.
if ( DisplayVars->GetResidueMode() == 0 ) {
if ( m_UserVars.m_ResidueUpper == 1 ) {
(pSegArr[i].pGeneStor)[tCount].CharDisplay = toupper(tChar);
} else if ( m_UserVars.m_ResidueUpper == 2 ) {
(pSegArr[i].pGeneStor)[tCount].CharDisplay = tolower(tChar);
} else {
(pSegArr[i].pGeneStor)[tCount].CharDisplay = tChar;
}
}
if ( m_UserVars.m_TransTilde ) {
if ( tChar == '~' ) (pSegArr[i].pGeneStor)[tCount].CharDisplay = ' ';
}
}
// Inner Loop
memset ( MatchArr, 0, sizeof(MatchArr) );
// init locations
for ( i = 0; i < 26; ++i ) {
MatchArr[1][i] = i;
}
int GotSomething = 0;
for ( i = 0; i < RowCount; ++i ) {
char tChar = (pSegArr[i].pGeneStor)[tCount].CharGene;
// if ( (tChar == '-') || (tChar == '.') ) {
tChar = toupper(tChar);
if ( !(tChar >= 'A' && tChar <= 'Z') ) {
continue;
}
GotSomething = 1;
tChar -= 'A';
MatchArr[0][tChar]++;
}
// Clear out old comments on bottom comment row
if ( !GotSomething ) continue;
int MaxMatchCount;
if ( m_UserVars.m_ProjectType > 1 && m_UserVars.m_DNAAmbEn ) {
GetDNAAmbiguous( &tSPS, pSegArr, RowCount, &MaxMatchCount, tCount, 1 );
} else {
PCRMatchArr ( MatchArr, &tSPS, &MaxMatchCount );
// SortMatchArr ( DisplayVars, MatchArr, &tSPS, &MaxMatchCount, 1 );
}
if ( !(MaxMatchCount >= (int)((double)RowCount * (m_UserVars.m_GroupConsLevel / 100.0) + 0.5) ) ) {
// Nothing here
continue;
}
// Do it for other sequences ...
// Inner Loop
memset ( MatchArr, 0, sizeof(MatchArr) );
// init locations
for ( i = 0; i < 26; ++i ) {
MatchArr[1][i] = i;
}
GotSomething = 0;
for ( i = 0; i < pSegCount; ++i ) {
int tChar = (pOSegArr[i].pGeneStor)[tCount].CharGene;
// if ( (tChar == '-') || (tChar == '.') ) {
tChar = toupper(tChar);
if ( !(tChar >= 'A' && tChar <= 'Z') ) {
continue;
}
GotSomething = 1;
if ( m_UserVars.m_ProjectType > 1 && m_UserVars.m_DNAAmbEn ) {
switch( tChar ) {
case 'A':
MatchArr[0]['A'-'A']++;
break;
case 'G':
MatchArr[0]['G'-'A']++;
break;
case 'C':
MatchArr[0]['C'-'A']++;
break;
case 'T':
MatchArr[0]['T'-'A']++;
break;
case 'U':
MatchArr[0]['T'-'A']++;
break;
case 'Y':
MatchArr[0]['C'-'A']++;
MatchArr[0]['T'-'A']++;
MatchArr[0]['Y'-'A']++;
break;
case 'R':
MatchArr[0]['A'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['R'-'A']++;
break;
case 'W':
MatchArr[0]['A'-'A']++;
MatchArr[0]['T'-'A']++;
MatchArr[0]['W'-'A']++;
break;
case 'S':
MatchArr[0]['C'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['S'-'A']++;
break;
case 'K':
MatchArr[0]['T'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['K'-'A']++;
break;
case 'M':
MatchArr[0]['C'-'A']++;
MatchArr[0]['A'-'A']++;
MatchArr[0]['M'-'A']++;
break;
case 'B':
MatchArr[0]['C'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['T'-'A']++;
MatchArr[0]['B'-'A']++;
break;
case 'D':
MatchArr[0]['A'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['T'-'A']++;
MatchArr[0]['D'-'A']++;
break;
case 'H':
MatchArr[0]['A'-'A']++;
MatchArr[0]['C'-'A']++;
MatchArr[0]['T'-'A']++;
MatchArr[0]['H'-'A']++;
break;
case 'V':
MatchArr[0]['A'-'A']++;
MatchArr[0]['C'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['V'-'A']++;
break;
case 'N':
MatchArr[0]['A'-'A']++;
MatchArr[0]['C'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['T'-'A']++;
MatchArr[0]['N'-'A']++;
MatchArr[0]['X'-'A']++;
break;
case 'X':
MatchArr[0]['A'-'A']++;
MatchArr[0]['C'-'A']++;
MatchArr[0]['G'-'A']++;
MatchArr[0]['T'-'A']++;
MatchArr[0]['N'-'A']++;
MatchArr[0]['X'-'A']++;
break;
}
} else {
tChar -= 'A';
MatchArr[0][tChar]++;
}
}
int tMaxC;
// Now Check to Other Groups to see if the max found residue(s) are in there
if ( GotSomething ) {
if ( m_UsePCRSim && tSPS.RowNum == '1' && !1 ) {
int tLen = m_UserVars.m_PCRSimilarities.GetLength();
tMaxC = 0;
int GroupMatches = 0;
// Sum up counts for this group
for ( int j=0; j < tLen; ++j ) {
char tChar = m_UserVars.m_PCRSimilarities[j];
tChar = toupper(tChar);
tChar -= 'A';
if ( MatchArr[0][tChar] != 0 ) {
GroupMatches++;
}
tMaxC += MatchArr[0][tChar];
}
} else {
// And its length
tMaxC = 0;
int tLen = strlen ( tSPS.Group );
for ( int j=0; j < tLen; ++j ) {
tMaxC += MatchArr[0][tSPS.Group[j] - 'A'];
}
}
} else {
tMaxC = 0;
}
if ( tMaxC > (int)((double)RowCount * (m_UserVars.m_PCRLevel / 100.0) + 0.5) ) {
// Nothing here
continue;
}
// And its length
int tLen = strlen ( tSPS.Group );
// Mark GeneStors
for ( i = 0; i < RowCount; ++i ) {
char tChar = (pSegArr[i].pGeneStor)[tCount].CharGene;
tChar = toupper(tChar);
// Test for any char in group.
for ( int j=0; j < tLen; ++j ) {
char tCharG = tSPS.Group[j];
tCharG = toupper(tCharG);
if ( tChar == tCharG ) {
// (pSegArr[i].pGeneStor)[tCount].CharShade = tShade;
DisplayVars->GetTitleColors(
&(pSegArr[i].pGeneStor)[tCount].TextColor,
&(pSegArr[i].pGeneStor)[tCount].BackColor
);
// No need to test further
break;
}
}
}
}
tPos = pGSFiller->SegDataList.GetHeadPosition();
while (tPos != NULL ) {
CGeneSegment *tCGSeg = (CGeneSegment *)pGSFiller->SegDataList.GetNext(tPos);
if ( tCGSeg->GetStyle() == LINESEQUENCE && tCGSeg->m_DisplayGroup != GrpNum ) {
HANDLE tSegHandle = tCGSeg->GetTextHandle();
GlobalUnlock( tSegHandle );
}
}
delete pOSegArr;
}
CATCH (CMemoryException, e ) {
AfxMessageBox( "Memory Exception" );
return;
}
END_CATCH
}
// The char for the comment string is returned in rSPS[n].RowNum
void
CGenedocDoc::PCRMatchArr( int MatchArr[2][26], ShadePairStruct* rSPS, int *Count )
{
// Code to include
int i, j;
typedef struct {
int Label;
int Count; // Number of Matches
char Data[MAXSHADEGROUP + 1]; // The chars
} ScoreStruct;
int tMaxC;
ScoreStruct *Scores;
ScoreStruct tSc;
int TotalCount;
if ( m_UsePCRSim ) {
int DupArr[26];
int GroupCount = 1;
// Lets see if any of the Group Sets add up to a Higher Count.
TotalCount = 1 + 26;
Scores = new ScoreStruct[TotalCount];
// Clear out DupArr
memset ( DupArr, 0, sizeof(DupArr) );
int tLen = m_UserVars.m_PCRSimilarities.GetLength();
tMaxC = 0;
int GroupMatches = 0;
// Sum up counts for this group
for ( j=0; j < tLen; ++j ) {
char tChar = m_UserVars.m_PCRSimilarities[j];
tChar = toupper(tChar);
tChar -= 'A';
if ( MatchArr[0][tChar] != 0 ) {
GroupMatches++;
}
tMaxC += MatchArr[0][tChar];
}
// If a good group, set entries in DupArr
if ( GroupMatches > 1 ) {
for ( j=0; j < tLen; ++j ) {
char tChar = m_UserVars.m_PCRSimilarities[j];
tChar = toupper(tChar);
tChar -= 'A';
DupArr[tChar] = 1;
}
} else {
tMaxC = 0;
}
strcpy ( Scores[26].Data, m_UserVars.m_PCRSimilarities );
char *pc = Scores[26].Data;
while ( *pc != 0 ) *pc++ = toupper( *pc );
Scores[26].Count = tMaxC;
Scores[26].Label = 1 + '0';
// Searched the similarity array
// Now do the single Chars
for ( i = 0; i < 26; ++i ) {
Scores[i].Label = Scores[i].Data[0] = MatchArr[1][i] + 'A';
Scores[i].Data[1] = 0;
if ( DupArr[i] == 0 ) {
Scores[i].Count = MatchArr[0][i];
} else {
Scores[i].Count = 0;
}
}
} else {
// Do only single chars
TotalCount = 26;
Scores = new ScoreStruct[TotalCount];
// Now do the single Chars
for ( i = 0; i < 26; ++i ) {
Scores[i].Label = Scores[i].Data[0] = MatchArr[1][i] + 'A';
Scores[i].Data[1] = 0;
Scores[i].Count = MatchArr[0][i];
}
}
// do all the sorting now ...
// Sort blindly now by Number of matches
for ( i = 0; i < (TotalCount - 1); ++i ) {
for ( j = 0; j < (TotalCount - 1); ++j ) {
if ( Scores[j].Count < Scores[j+1].Count ) {
tSc = Scores[j];
Scores[j] = Scores[j+1];
Scores[j+1] = tSc;
}
}
}
// Return First answers.
strcpy ( rSPS->Group, Scores[0].Data );
rSPS->RowNum = Scores[0].Label;
// This too if he wants it.
*Count = Scores[0].Count;
delete Scores;
}