-
Notifications
You must be signed in to change notification settings - Fork 17
/
Copy pathDNASequence.java
375 lines (305 loc) · 9.12 KB
/
DNASequence.java
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
import java.io.*;
import java.util.*;
import java.util.regex.*;
public class DNASequence
{
public static String seq;
private String name;
private String desc;
private String errorLog = "";
private Pattern notDnaRe = Pattern.compile("([^ACGT])");
private IntervalSearchTree mask = new IntervalSearchTree();
public DNASequence(String sequence)
{
seq = sequence.toUpperCase();
name = "";
desc = "";
}
public DNASequence(String sequence, String _name)
{
seq = sequence.toUpperCase();
name = _name;
desc = "";
}
public DNASequence(String sequence, String _name, String _desc)
{
seq = sequence.toUpperCase();
name = _name;
desc = _desc;
}
public int length()
{
return seq.length();
}
public String getName()
{
return name;
}
public String getDesc()
{
return desc;
}
public String toString()
{
return seq;
}
public boolean isDNASequence()
{
int length = seq.length();
if (length == 0)
{
errorLog = "Not a valid DNA sequence. Sequence contains no characters.";
return false;
}
Matcher m = notDnaRe.matcher(seq);
boolean isNotDNA = m.find();
if ( isNotDNA )
{
errorLog = "Not a valid DNA sequence. Invalid character '" + m.group() + "' found at position " + m.start() + ". ";
return false;
}
else
{
return true;
}
}
/*
//method has not been tested
//may contain alphabetic characters other than acgt
public boolean isSequence()
{
int i = 0;
int length = seq.length();
if (length == 0)
{ errorLog = "Not a valid sequence. Sequence contains no characters.";
return false;
}
while (i < length)
{
if (Character.isLetter(seq.charAt(i)))
{ System.out.println(seq.charAt(i) + " " + Character.isLetter(seq.charAt(i)));
i++;
}
else
{ errorLog = "Not a valid sequence. Error found at position " + i + " scanning a non-alphabetic character " + seq.charAt(i);
return false;
}
}
return true;
}
*/
public String getErrorLog()
{ return errorLog;
}
public String substring(int beginIndex, int endIndex)
{
return seq.substring(beginIndex, endIndex);
}
public void toUpperCase()
{
seq = seq.toUpperCase();
}
public static int getHammingDistance(String seq1, String seq2)
{
int length = seq1.length();
int hammingDistance = 0;
if (seq1.length() != seq2.length())
{
length = min(seq1.length(), seq2.length());
hammingDistance = Math.abs(seq1.length() - seq2.length());
}
for (int i =0; i < length; i++)
{
if ( seq1.charAt(i) != seq2.charAt(i))
{
hammingDistance++;
}
}
return hammingDistance;
}
//*****************************
// Compute Levenshtein distance Michael Gilleland, Merriam Park Software www.merriampark.com/ld.htm
//*****************************
public static int getLevenshteinDistance1 (String s, String t)
{
int d[][]; // matrix
int n; // length of s
int m; // length of t
int i; // iterates through s
int j; // iterates through t
char s_i; // ith character of s
char t_j; // jth character of t
int cost; // cost
// Step 1
n = s.length ();
m = t.length ();
if (n == 0) {
return m;
}
if (m == 0) {
return n;
}
d = new int[n+1][m+1];
// Step 2
for (i = 0; i <= n; i++) {
d[i][0] = i;
}
for (j = 0; j <= m; j++) {
d[0][j] = j;
}
// Step 3
for (i = 1; i <= n; i++) {
s_i = s.charAt (i - 1);
// Step 4
for (j = 1; j <= m; j++) {
t_j = t.charAt (j - 1);
// Step 5
if (s_i == t_j) {
cost = 0;
}
else {
cost = 1;
}
// Step 6
d[i][j] = Minimum (d[i-1][j]+1, d[i][j-1]+1, d[i-1][j-1] + cost);
}
}
// Step 7
return d[n][m];
}
//Chas Emerick http://www.merriampark.com/ldjava.htm
public static int getLevenshteinDistance2 (String s, String t) {
if (s == null || t == null)
{
throw new IllegalArgumentException("Strings must not be null");
}
/*
The difference between this impl. and the previous is that, rather
than creating and retaining a matrix of size s.length()+1 by t.length()+1,
we maintain two single-dimensional arrays of length s.length()+1. The first, d,
is the 'current working' distance array that maintains the newest distance cost
counts as we iterate through the characters of String s. Each time we increment
the index of String t we are comparing, d is copied to p, the second int[]. Doing so
allows us to retain the previous cost counts as required by the algorithm (taking
the minimum of the cost count to the left, up one, and diagonally up and to the left
of the current cost count being calculated). (Note that the arrays aren't really
copied anymore, just switched...this is clearly much better than cloning an array
or doing a System.arraycopy() each time through the outer loop.)
Effectively, the difference between the two implementations is this one does not
cause an out of memory condition when calculating the LD over two very large strings.
*/
int n = s.length(); // length of s
int m = t.length(); // length of t
if (n == 0) {
return m;
} else if (m == 0) {
return n;
}
int p[] = new int[n+1]; //'previous' cost array, horizontally
int d[] = new int[n+1]; // cost array, horizontally
int _d[]; //placeholder to assist in swapping p and d
// indexes into strings s and t
int i; // iterates through s
int j; // iterates through t
char t_j; // jth character of t
int cost; // cost
for (i = 0; i<=n; i++) {
p[i] = i;
}
for (j = 1; j<=m; j++) {
t_j = t.charAt(j-1);
d[0] = j;
for (i=1; i<=n; i++) {
cost = s.charAt(i-1)==t_j ? 0 : 1;
// minimum of cell to the left+1, to the top+1, diagonally left and up +cost
d[i] = Math.min(Math.min(d[i-1]+1, p[i]+1), p[i-1]+cost);
}
// copy current distance counts to 'previous row' distance counts
_d = p;
p = d;
d = _d;
}
// our last action in the above loop was to switch d and p, so p now
// actually has the most recent cost counts
return p[n];
}
public static double getSimilarity(String s1, String s2)
{ int maxLength = max(s1.length(), s2.length());
double similarity = 1.0 - (double)getLevenshteinDistance1(s1, s2)/maxLength;
return similarity;
}
private static boolean patternMatches(String pattern1, String pattern2, double confidence)
{ double patternSimilarity = getSimilarity(pattern1, pattern2);
if (patternSimilarity >= confidence)
return true;
else
return false;
}
private static int min (int[] array)
{ int min = array[0];
int minIndex = 0;
for (int i = 0; i < array.length; i++)
{ if (array[i] < min)
{ min = array[i];
minIndex = i;
}
}
return minIndex;
}
private static int max (int[] array)
{ int max = array[0];
int maxIndex = 0;
for (int i = 0; i < array.length; i++)
{ if (array[i] > max)
{ max = array[i];
maxIndex = i;
}
}
return maxIndex;
}
private static int min(int n1, int n2)
{ if (n1 < n2)
return n1;
else
return n2;
}
private static int max(int n1, int n2)
{ if (n1 < n2)
return n2;
else
return n1;
}
private static int Minimum (int a, int b, int c)
{
int mi;
mi = a;
if (b < mi)
mi = b;
if (c < mi)
mi = c;
return mi;
}
public void mask(int minimum)
{
for(int i = 0; i < seq.length(); i++)
{
int n = 0;
int j = i + 1;
while(j < seq.length() && seq.charAt(i) == seq.charAt(j))
{
++n;
++j;
}
if(n >= minimum)
{
// add in the interval and save the end location as the data
mask.add(i, j);
}
i = j;
}
}
public int masked(int start, int end)
{
return mask.overlapEnd(start, end);
}
}