forked from biopython/biopython
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Reduced.py
193 lines (166 loc) · 4.85 KB
/
Reduced.py
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
# Copyright 2004 by Iddo Friedberg.
# All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""Reduced alphabets which lump together several amino-acids into one letter.
Reduced (redundant or simplified) alphabets are used to represent protein sequences using an
alternative alphabet which lumps together several amino-acids into one letter, based
on physico-chemical traits. For example, all the aliphatics (I,L,V) are usually
quite interchangeable, so many sequence studies group them into one letter
Examples of reduced alphabets are available in:
http://viscose.ifg.uni-muenster.de/html/alphabets.html
The Murphy tables are from here:
Murphy L.R., Wallqvist A, Levy RM. (2000) Simplified amino acid
alphabets for protein fold recognition and implications for folding.
Protein Eng. 13(3):149-152
Bio.utils.reduce_sequence is used to take a Protein alphabet, and reduce it using one of
the tables here, or a user-defined table.
"""
from Bio import Alphabet
__docformat__ = "restructuredtext en"
murphy_15_tab = {"L": "L",
"V": "L",
"I": "L",
"M": "L",
"C": "C",
"A": "A",
"G": "G",
"S": "S",
"T": "T",
"P": "P",
"F": "F",
"Y": "F",
"W": "W",
"E": "E",
"D": "D",
"N": "N",
"Q": "Q",
"K": "K",
"R": "K",
"H": "H",
}
class Murphy15(Alphabet.ProteinAlphabet):
letters = "LCAGSTPFWEDNQKH"
size = 15
murphy_15 = Murphy15()
murphy_10_tab = {"L": "L",
"V": "L",
"I": "L",
"M": "L",
"C": "C",
"A": "A",
"G": "G",
"S": "S",
"T": "S",
"P": "P",
"F": "F",
"Y": "F",
"W": "F",
"E": "E",
"D": "E",
"N": "E",
"Q": "E",
"K": "K",
"R": "K",
"H": "H"}
class Murphy10(Alphabet.ProteinAlphabet):
letters = "LCAGSPFEKH"
size = 10
murphy_10 = Murphy10()
murphy_8_tab = {"L": "L",
"V": "L",
"I": "L",
"M": "L",
"C": "L",
"A": "A",
"G": "A",
"S": "S",
"T": "S",
"P": "P",
"F": "F",
"Y": "F",
"W": "F",
"E": "E",
"D": "E",
"N": "E",
"Q": "E",
"K": "K",
"R": "K",
"H": "H"}
class Murphy8(Alphabet.ProteinAlphabet):
letters = "LASPFEKH"
size = 8
murphy_8 = Murphy8()
murphy_4_tab = {"L": "L",
"V": "L",
"I": "L",
"M": "L",
"C": "L",
"A": "A",
"G": "A",
"S": "A",
"T": "A",
"P": "A",
"F": "F",
"Y": "F",
"W": "F",
"E": "E",
"D": "E",
"N": "E",
"Q": "E",
"K": "E",
"R": "E",
"H": "E"}
class Murphy4(Alphabet.ProteinAlphabet):
letters = "LAFE"
size = 4
murphy_4 = Murphy4()
hp_model_tab = {"A": "P", # Hydrophilic
"G": "P",
"T": "P",
"S": "P",
"N": "P",
"Q": "P",
"D": "P",
"E": "P",
"H": "P",
"R": "P",
"K": "P",
"P": "P",
"C": "H", # Hydrophobic
"M": "H",
"F": "H",
"I": "H",
"L": "H",
"V": "H",
"W": "H",
"Y": "H"}
class HPModel(Alphabet.ProteinAlphabet):
letters = "HP"
size = 2
hp_model = HPModel()
pc_5_table = {"I": "A", # Aliphatic
"V": "A",
"L": "A",
"F": "R", # Aromatic
"Y": "R",
"W": "R",
"H": "R",
"K": "C", # Charged
"R": "C",
"D": "C",
"E": "C",
"G": "T", # Tiny
"A": "T",
"C": "T",
"S": "T",
"T": "D", # Diverse
"M": "D",
"Q": "D",
"N": "D",
"P": "D"}
class PC5(Alphabet.ProteinAlphabet):
letters = "ARCTD"
size = 5
hp_model = HPModel()