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
|
# Copyright 2000-2001 by Andrew Dalke.
# Revisions copyright 2008 by Peter Cock.
#
# This file is part of the Biopython distribution and governed by your
# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
# Please see the LICENSE file that should have been included as part of this
# package.
"""Standard nucleotide and protein alphabets defined by IUPAC."""
from Bio import Alphabet
from Bio.Data import IUPACData
# #################### Protein
# From the IUPAC definition at:
# http://www.chem.qmw.ac.uk/iupac/AminoAcid/A2021.html#AA21
assert (IUPACData.extended_protein_letters ==
IUPACData.extended_protein_letters.upper())
class ExtendedIUPACProtein(Alphabet.ProteinAlphabet):
"""Extended uppercase IUPAC protein single letter alphabet including X etc.
In addition to the standard 20 single letter protein codes, this includes:
- `B` = "Asx"; Aspartic acid (R) or Asparagine (N)
- `X` = "Xxx"; Unknown or 'other' amino acid
- `Z` = "Glx"; Glutamic acid (E) or Glutamine (Q)
- `J` = "Xle"; Leucine (L) or Isoleucine (I), used in mass-spec (NMR)
- `U` = "Sec"; Selenocysteine
- `O` = "Pyl"; Pyrrolysine
This alphabet is not intended to be used with `X` for Selenocysteine
(an ad-hoc standard prior to the IUPAC adoption of `U` instead).
"""
letters = IUPACData.extended_protein_letters
extended_protein = ExtendedIUPACProtein()
assert IUPACData.protein_letters == IUPACData.protein_letters.upper()
class IUPACProtein(ExtendedIUPACProtein):
"""IUPAC protein alphabet of the 20 standard amino acids.
Uppercase and single letter.
"""
letters = IUPACData.protein_letters
protein = IUPACProtein()
# #################### DNA
# The next two are the IUPAC definitions, from:
# http://www.chem.qmw.ac.uk/iubmb/misc/naseq.html
class IUPACAmbiguousDNA(Alphabet.DNAAlphabet):
"""Uppercase IUPAC ambiguous DNA."""
letters = IUPACData.ambiguous_dna_letters
ambiguous_dna = IUPACAmbiguousDNA()
class IUPACUnambiguousDNA(IUPACAmbiguousDNA):
"""Uppercase IUPAC unambiguous DNA (letters GATC only)."""
letters = IUPACData.unambiguous_dna_letters
unambiguous_dna = IUPACUnambiguousDNA()
# Also from the URL, but not part of the standard
class ExtendedIUPACDNA(Alphabet.DNAAlphabet):
"""Extended IUPAC DNA alphabet.
In addition to the standard letter codes GATC, this includes:
- `B` = 5-bromouridine
- `D` = 5,6-dihydrouridine
- `S` = thiouridine
- `W` = wyosine
"""
letters = IUPACData.extended_dna_letters
extended_dna = ExtendedIUPACDNA()
# #################### RNA
class IUPACAmbiguousRNA(Alphabet.RNAAlphabet):
"""Uppercase IUPAC ambiguous RNA."""
letters = IUPACData.ambiguous_rna_letters
ambiguous_rna = IUPACAmbiguousRNA()
class IUPACUnambiguousRNA(IUPACAmbiguousRNA):
"""Uppercase IUPAC unambiguous RNA (letters GAUC only)."""
letters = IUPACData.unambiguous_rna_letters
unambiguous_rna = IUPACUnambiguousRNA()
# are there extended forms?
# class ExtendedIUPACRNA(Alphabet.RNAAlphabet):
# letters = extended_rna_letters
# # B == 5-bromouridine
# # D == 5,6-dihydrouridine
# # S == thiouridine
# # W == wyosine
|
