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
|
#include <string>
#include <cstdio>
#include <cstdlib>
#include <algorithm>
#include "Utils.h"
using namespace std;
char complement(char b)
{
switch(b)
{
case 'A': return 'T';
case 'T': return 'A';
case 'G': return 'C';
case 'C': return 'G';
case 'a': return 't';
case 't': return 'a';
case 'g': return 'c';
case 'c': return 'g';
case 'N': return 'N';
case '*': return '*';
}
return '?';
}
string reverse_complement(string seq)
{
string s(seq.begin(),seq.end());
string::iterator pos;
for (pos = s.begin(); pos != s.end(); ++pos) {
// cout << *pos;
}
// cout << endl;
reverse(s.begin(), s.end());
for(pos=s.begin();pos!=s.end();++pos)
*pos=complement(*pos);
return s;
}
char reverse_dir(char dir)
{
return dir == 'F' ? 'R' : 'F';
}
int edit_distance(const void *s1, size_t l1, const void *s2, size_t l2, size_t nmemb, int (*comp)(const void*, const void*))
{
unsigned int i;
unsigned int j;
size_t len = (l1 + 1) * (l2 + 1);
char *p1;
char *p2;
unsigned int d1;
unsigned int d2;
unsigned int d3;
unsigned int *d;
unsigned int *dp;
unsigned int res;
if (l1 == 0)
return l2;
else if (l2 == 0)
return l1;
d = (unsigned int*)malloc(len * sizeof(unsigned int));
*d = 0;
for(i = 1, dp = d + l2 + 1; i < l1 + 1; ++i, dp += l2 + 1)
{
*dp = (unsigned) i;
}
for(j = 1, dp = d + 1; j < l2 + 1; ++j, ++dp)
{
*dp = (unsigned) j;
}
for(i = 1, p1 = (char*) s1, dp = d + l2 + 2; i < l1 + 1; ++i, p1 += nmemb, ++dp)
{
for(j = 1, p2 = (char*) s2; j < l2 + 1; ++j, p2 += nmemb, ++dp)
{
if(!comp(p1, p2))
{
*dp = *(dp - l2 - 2);// same base
}
else
{
d1 = *(dp - 1) + 1;// insertion
d2 = *(dp - l2 - 1) + 1;// deletion
d3 = *(dp - l2 - 2) + 1;// substitution
*dp = std::min(d1, std::min(d2, d3));
}
}
}
res = *(dp - 2);
dp = NULL;
free(d);
return res;
}
int hamming_distance(const void *s1, size_t l1, const void *s2, size_t l2, size_t nmemb, int (*comp)(const void*, const void*))
{
char *p1, *p2;
unsigned int i, res = 0;
for (i = 0, p1 = (char *)s1, p2 = (char *)s2; i < l1; i++, p1 += nmemb, p2 += nmemb)
if (comp(p1,p2))
res++;
return res;
}
int comp(const void *a, const void *b)
{
return *(char *)a != *(char *)b;
}
FILE* open_file( char* filename )
{
FILE* file = fopen( filename, "r" );
if ( file == NULL )
{
fprintf( stderr, "\nERROR: cannot open file %s\n", filename );
exit( EXIT_FAILURE );
}
return file;
}
/*!
* \brief Modify the sequence to put context in lowercase
* \param sequence: the sequence to modify
* \param contextFirst: size of the context on the left
* \param contextLast: size of the context on the rigth
* return the modified sequence (with contexts in lower case, and the middle in upper
* used in BubbleEnumeration & NGraph methods
*/
string toLowerContext( const string &sequence, const int contextFirst, const int contextLast)
{
string contextL = sequence.substr(0, contextFirst);
string contextR = sequence.substr( sequence.size() - contextLast, contextLast);
string varS = sequence.substr(contextFirst, sequence.size() - (contextFirst + contextLast));
transform( contextL.begin(), contextL.end(), contextL.begin(), ::tolower);
transform( contextR.begin(), contextR.end(), contextR.begin(), ::tolower);
return contextL + varS + contextR;
}
File File::open_path(const char* path, const char* mode) {
auto ptr = std::unique_ptr<std::FILE, Deleter>{std::fopen(path, mode), Deleter{}};
if(ptr == nullptr) {
std::fprintf(stderr, "Error: could not open file %s (mode=%s)\n", path, mode);
std::exit(EXIT_FAILURE);
}
return File{std::move(ptr)};
}
|
