|
1
|
|
|
# -*- coding: utf-8 -*- |
|
2
|
|
|
|
|
3
|
|
|
# Copyright 2014-2018 by Christopher C. Little. |
|
4
|
|
|
# This file is part of Abydos. |
|
5
|
|
|
# |
|
6
|
|
|
# Abydos is free software: you can redistribute it and/or modify |
|
7
|
|
|
# it under the terms of the GNU General Public License as published by |
|
8
|
|
|
# the Free Software Foundation, either version 3 of the License, or |
|
9
|
|
|
# (at your option) any later version. |
|
10
|
|
|
# |
|
11
|
|
|
# Abydos is distributed in the hope that it will be useful, |
|
12
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
13
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
14
|
|
|
# GNU General Public License for more details. |
|
15
|
|
|
# |
|
16
|
|
|
# You should have received a copy of the GNU General Public License |
|
17
|
|
|
# along with Abydos. If not, see <http://www.gnu.org/licenses/>. |
|
18
|
|
|
|
|
19
|
1 |
|
"""abydos.distance._gotoh. |
|
20
|
|
|
|
|
21
|
|
|
Gotoh score |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from numpy import float32 as np_float32 |
|
32
|
1 |
|
from numpy import zeros as np_zeros |
|
33
|
|
|
|
|
34
|
1 |
|
from six.moves import range |
|
35
|
|
|
|
|
36
|
1 |
|
from ._ident import sim_ident |
|
37
|
1 |
|
from ._needleman_wunsch import NeedlemanWunsch |
|
38
|
|
|
|
|
39
|
1 |
|
__all__ = ['Gotoh', 'gotoh'] |
|
40
|
|
|
|
|
41
|
|
|
|
|
42
|
1 |
|
class Gotoh(NeedlemanWunsch): |
|
|
|
|
|
|
43
|
|
|
"""Gotoh score. |
|
44
|
|
|
|
|
45
|
|
|
The Gotoh score :cite:`Gotoh:1982` is essentially Needleman-Wunsch with |
|
46
|
|
|
affine gap penalties. |
|
47
|
|
|
""" |
|
48
|
|
|
|
|
49
|
1 |
|
def dist_abs(self, src, tar, gap_open=1, gap_ext=0.4, sim_func=sim_ident): |
|
|
|
|
|
|
50
|
|
|
"""Return the Gotoh score of two strings. |
|
51
|
|
|
|
|
52
|
|
|
Parameters |
|
53
|
|
|
---------- |
|
54
|
|
|
src : str |
|
55
|
|
|
Source string for comparison |
|
56
|
|
|
tar : str |
|
57
|
|
|
Target string for comparison |
|
58
|
|
|
gap_open : float |
|
59
|
|
|
The cost of an open alignment gap (1 by default) |
|
60
|
|
|
gap_ext : float |
|
61
|
|
|
The cost of an alignment gap extension (0.4 by default) |
|
62
|
|
|
sim_func : function |
|
63
|
|
|
A function that returns the similarity of two characters (identity |
|
64
|
|
|
similarity by default) |
|
65
|
|
|
|
|
66
|
|
|
Returns |
|
67
|
|
|
------- |
|
68
|
|
|
float |
|
69
|
|
|
Gotoh score |
|
70
|
|
|
|
|
71
|
|
|
Examples |
|
72
|
|
|
-------- |
|
73
|
|
|
>>> cmp = Gotoh() |
|
74
|
|
|
>>> cmp.dist_abs('cat', 'hat') |
|
75
|
|
|
2.0 |
|
76
|
|
|
>>> cmp.dist_abs('Niall', 'Neil') |
|
77
|
|
|
1.0 |
|
78
|
|
|
>>> round(cmp.dist_abs('aluminum', 'Catalan'), 12) |
|
79
|
|
|
-0.4 |
|
80
|
|
|
>>> cmp.dist_abs('cat', 'hat') |
|
81
|
|
|
2.0 |
|
82
|
|
|
|
|
83
|
|
|
""" |
|
84
|
1 |
|
d_mat = np_zeros((len(src) + 1, len(tar) + 1), dtype=np_float32) |
|
85
|
1 |
|
p_mat = np_zeros((len(src) + 1, len(tar) + 1), dtype=np_float32) |
|
86
|
1 |
|
q_mat = np_zeros((len(src) + 1, len(tar) + 1), dtype=np_float32) |
|
87
|
|
|
|
|
88
|
1 |
|
d_mat[0, 0] = 0 |
|
89
|
1 |
|
p_mat[0, 0] = float('-inf') |
|
90
|
1 |
|
q_mat[0, 0] = float('-inf') |
|
91
|
1 |
|
for i in range(1, len(src) + 1): |
|
92
|
1 |
|
d_mat[i, 0] = float('-inf') |
|
93
|
1 |
|
p_mat[i, 0] = -gap_open - gap_ext * (i - 1) |
|
94
|
1 |
|
q_mat[i, 0] = float('-inf') |
|
95
|
1 |
|
q_mat[i, 1] = -gap_open |
|
96
|
1 |
|
for j in range(1, len(tar) + 1): |
|
97
|
1 |
|
d_mat[0, j] = float('-inf') |
|
98
|
1 |
|
p_mat[0, j] = float('-inf') |
|
99
|
1 |
|
p_mat[1, j] = -gap_open |
|
100
|
1 |
|
q_mat[0, j] = -gap_open - gap_ext * (j - 1) |
|
101
|
|
|
|
|
102
|
1 |
|
for i in range(1, len(src) + 1): |
|
103
|
1 |
|
for j in range(1, len(tar) + 1): |
|
104
|
1 |
|
sim_val = sim_func(src[i - 1], tar[j - 1]) |
|
105
|
1 |
|
d_mat[i, j] = max( |
|
106
|
|
|
d_mat[i - 1, j - 1] + sim_val, |
|
107
|
|
|
p_mat[i - 1, j - 1] + sim_val, |
|
108
|
|
|
q_mat[i - 1, j - 1] + sim_val, |
|
109
|
|
|
) |
|
110
|
|
|
|
|
111
|
1 |
|
p_mat[i, j] = max( |
|
112
|
|
|
d_mat[i - 1, j] - gap_open, p_mat[i - 1, j] - gap_ext |
|
113
|
|
|
) |
|
114
|
|
|
|
|
115
|
1 |
|
q_mat[i, j] = max( |
|
116
|
|
|
d_mat[i, j - 1] - gap_open, q_mat[i, j - 1] - gap_ext |
|
117
|
|
|
) |
|
118
|
|
|
|
|
119
|
1 |
|
i, j = (n - 1 for n in d_mat.shape) |
|
|
|
|
|
|
120
|
1 |
|
return max(d_mat[i, j], p_mat[i, j], q_mat[i, j]) |
|
121
|
|
|
|
|
122
|
|
|
|
|
123
|
1 |
|
def gotoh(src, tar, gap_open=1, gap_ext=0.4, sim_func=sim_ident): |
|
124
|
|
|
"""Return the Gotoh score of two strings. |
|
125
|
|
|
|
|
126
|
|
|
This is a wrapper for :py:meth:`Gotoh.dist_abs`. |
|
127
|
|
|
|
|
128
|
|
|
Parameters |
|
129
|
|
|
---------- |
|
130
|
|
|
src : str |
|
131
|
|
|
Source string for comparison |
|
132
|
|
|
tar : str |
|
133
|
|
|
Target string for comparison |
|
134
|
|
|
gap_open : float |
|
135
|
|
|
The cost of an open alignment gap (1 by default) |
|
136
|
|
|
gap_ext : float |
|
137
|
|
|
The cost of an alignment gap extension (0.4 by default) |
|
138
|
|
|
sim_func : function |
|
139
|
|
|
A function that returns the similarity of two characters (identity |
|
140
|
|
|
similarity by default) |
|
141
|
|
|
|
|
142
|
|
|
Returns |
|
143
|
|
|
------- |
|
144
|
|
|
float |
|
145
|
|
|
Gotoh score |
|
146
|
|
|
|
|
147
|
|
|
Examples |
|
148
|
|
|
-------- |
|
149
|
|
|
>>> gotoh('cat', 'hat') |
|
150
|
|
|
2.0 |
|
151
|
|
|
>>> gotoh('Niall', 'Neil') |
|
152
|
|
|
1.0 |
|
153
|
|
|
>>> round(gotoh('aluminum', 'Catalan'), 12) |
|
154
|
|
|
-0.4 |
|
155
|
|
|
>>> gotoh('cat', 'hat') |
|
156
|
|
|
2.0 |
|
157
|
|
|
|
|
158
|
|
|
""" |
|
159
|
1 |
|
return Gotoh().dist_abs(src, tar, gap_open, gap_ext, sim_func) |
|
160
|
|
|
|
|
161
|
|
|
|
|
162
|
|
|
if __name__ == '__main__': |
|
163
|
|
|
import doctest |
|
164
|
|
|
|
|
165
|
|
|
doctest.testmod() |
|
166
|
|
|
|
chrislit /
abydos
Loading history...