1 /* The MIT License
2
3 Copyright (c) 2015 Manuel Holtgrewe <manuel.holtgrewe@bihealth.de>
4
5 Permission is hereby granted, free of charge, to any person obtaining a copy
6 of this software and associated documentation files (the "Software"), to deal
7 in the Software without restriction, including without limitation the rights
8 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9 copies of the Software, and to permit persons to whom the Software is
10 furnished to do so, subject to the following conditions:
11
12 The above copyright notice and this permission notice shall be included in
13 all copies or substantial portions of the Software.
14
15 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21 THE SOFTWARE.
22 */
23
24 #include "needle.h"
25
26 #include <algorithm>
27 #include <iostream>
28 #include <fstream>
29 #include <string>
30
NeedlemanWunsch(bool debug)31 NeedlemanWunsch::NeedlemanWunsch(bool debug)
32 {
33 this->debug = debug;
34 }
35
align(const char * ref,const char * read)36 void NeedlemanWunsch::align(const char* ref, const char* read)
37 {
38 this->ref = ref;
39 this->read = read;
40 this->len_ref = strlen(ref);
41 this->len_read = strlen(read);
42
43 matrix.clear();
44 matrix.resize((len_ref + 1) * (len_read + 1), EMPTY);
45
46 // fill first column and row
47 scores.resize(len_read + 1);
48 for (unsigned i = 0; i <= len_ref; ++i)
49 matrix.at(i * (len_read + 1)) = CIGAR_D;
50 for (unsigned i = 0; i <= len_read; ++i)
51 {
52 matrix.at(i) = CIGAR_I;
53 scores.at(i) = i * params.score_gap;
54 }
55 matrix.at(0) = CIGAR_M;
56
57 // fill remainder of the matrix
58 int offset = 0;
59 int score_n = 0;
60 for (unsigned i = 1; i <= len_ref; ++i)
61 {
62 offset += len_read + 1;
63 score_n += params.score_gap;
64 int best_score = 0;
65 for (unsigned j = 1; j <= len_read; ++j)
66 {
67 int score_nw = scores.at(j - 1);
68 int score_w = scores.at(j);
69
70 int score_diag = score_nw;
71 Traceback best_dir;
72 if (ref[i - 1] == read[j - 1])
73 {
74 best_dir = CIGAR_M;
75 score_diag += params.score_match;
76 }
77 else
78 {
79 best_dir = CIGAR_X;
80 score_diag += params.score_mismatch;
81 }
82
83 best_score = score_diag;
84
85 if (score_w + params.score_gap > best_score)
86 {
87 best_score = score_w + params.score_gap;
88 best_dir = CIGAR_D;
89 }
90 else if (score_n + params.score_gap > best_score)
91 {
92 best_score = score_n + params.score_gap;
93 best_dir = CIGAR_I;
94 }
95
96 scores.at(j - 1) = score_n;
97 score_n = best_score;
98 matrix.at(offset + j) = best_dir;
99 }
100 scores.back() = best_score;
101 }
102
103 }
104
trace_path()105 void NeedlemanWunsch::trace_path()
106 {
107 int i = len_ref;
108 int j = len_read;
109 int k = (len_read + 1) * (len_ref + 1) - 1;
110
111 trace.clear();
112
113 while (i>0 || j>0)
114 {
115 trace.push_back(matrix.at(k));
116 switch ((int32_t) matrix.at(k))
117 {
118 case CIGAR_X:
119 case CIGAR_M:
120 --i;
121 --j;
122 k -= len_read + 2;
123 break;
124 case CIGAR_I:
125 --j;
126 --k;
127 break;
128 case CIGAR_D:
129 --i;
130 k -= len_read + 1;
131 break;
132 }
133 }
134
135 std::reverse(trace.begin(), trace.end());
136 }
137
print_alignment(std::string const & pad)138 void NeedlemanWunsch::print_alignment(std::string const & pad)
139 {
140 // print reference
141 std::cerr << pad;
142 for (unsigned i = 0, j = 0; i < trace.size(); ++i)
143 {
144 if (trace.at(i) == CIGAR_X || trace[i] == CIGAR_M || trace.at(i) == CIGAR_D)
145 std::cerr << ref[j++];
146 else
147 std::cerr << "-";
148 }
149 std::cerr << "\n";
150
151 // print trace
152 std::cerr << pad;
153 for (unsigned i = 0, j = 0, k = 0; i < trace.size(); ++i)
154 {
155 if (trace[i] == CIGAR_X || trace[i] == CIGAR_M)
156 std::cerr << ((ref[j++] == read[k++]) ? '|' : ' ');
157 else if (trace[i] == CIGAR_D)
158 {
159 j++;
160 std::cerr << " ";
161 }
162 else // trace[i] == CIGAR_I
163 {
164 k++;
165 std::cerr << " ";
166 }
167 }
168 std::cerr << "\n";
169
170 // print read
171 std::cerr << pad;
172 for (unsigned i = 0, j = 0; i < trace.size(); ++i)
173 {
174 if (trace[i] == CIGAR_X || trace[i] == CIGAR_M || trace[i] == CIGAR_I)
175 std::cerr << read[j++];
176 else
177 std::cerr << "-";
178 }
179 std::cerr << "\n";
180 }
181