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
|
Getting a genetic code
----------------------
The standard genetic code.
.. doctest::
>>> from cogent.core.genetic_code import GeneticCodes
>>> standard_code = GeneticCodes[1]
The vertebrate mt genetic code.
.. doctest::
>>> from cogent.core.genetic_code import GeneticCodes
>>> mt_gc = GeneticCodes[2]
>>> print mt_gc.Name
Vertebrate Mitochondrial
To see the key -> genetic code mapping, use a loop.
.. doctest::
>>> for key, code in GeneticCodes.items():
... print key, code.Name
1 Standard Nuclear
2 Vertebrate Mitochondrial
3 Yeast Mitochondrial...
Translate DNA sequences
-----------------------
.. doctest::
>>> from cogent.core.genetic_code import DEFAULT as standard_code
>>> standard_code.translate('TTTGCAAAC')
'FAN'
Conversion to a ``ProteinSequence`` from a ``DnaSequence`` is shown in :ref:`translation`.
Translate a codon
-----------------
.. doctest::
>>> from cogent.core.genetic_code import DEFAULT as standard_code
>>> standard_code['TTT']
'F'
or get the codons for a single amino acid
.. doctest::
>>> standard_code['A']
['GCT', 'GCC', 'GCA', 'GCG']
Look up the amino acid corresponding to a single codon
------------------------------------------------------
.. doctest::
>>> from cogent.core.genetic_code import DEFAULT as standard_code
>>> standard_code['TTT']
'F'
Or get all the codons for one amino acid
----------------------------------------
.. doctest::
>>> standard_code['A']
['GCT', 'GCC', 'GCA', 'GCG']
For a group of amino acids
--------------------------
.. doctest::
>>> targets = ['A','C']
>>> codons = [standard_code[aa] for aa in targets]
>>> codons
[['GCT', 'GCC', 'GCA', 'GCG'], ['TGT', 'TGC']]
>>> flat_list = sum(codons,[])
>>> flat_list
['GCT', 'GCC', 'GCA', 'GCG', 'TGT', 'TGC']
Converting the ``CodonAlphabet`` to codon series
------------------------------------------------
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence("AGTACACTGGTT")
>>> sorted(my_seq.CodonAlphabet())
['AAA', 'AAC', 'AAG', 'AAT'...
>>> len(my_seq.CodonAlphabet())
61
Obtaining the codons from a ``DnaSequence`` object
--------------------------------------------------
Use the method ``getInMotifSize``
.. doctest::
>>> from cogent import LoadSeqs,DNA
>>> my_seq = DNA.makeSequence('ATGCACTGGTAA','my_gene')
>>> codons = my_seq.getInMotifSize(3)
>>> print codons
['ATG', 'CAC', 'TGG', 'TAA']
You can't translate a sequence that contains a stop codon.
.. doctest::
>>> pep = my_seq.getTranslation()
Traceback (most recent call last):
AlphabetError: TAA
Remove the stop codon first
^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import LoadSeqs,DNA
>>> my_seq = DNA.makeSequence('ATGCACTGGTAA','my_gene')
>>> seq = my_seq.withoutTerminalStopCodon()
>>> pep = seq.getTranslation()
>>> print pep.toFasta()
>my_gene
MHW
>>> print type(pep)
<class 'cogent.core.sequence.ProteinSequence'>
Or we can just grab the correct slice from the ``DnaSequence`` object
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import LoadSeqs,DNA
>>> my_seq = DNA.makeSequence('CAAATGTATTAA','my_gene')
>>> pep = my_seq[:-3].getTranslation().toFasta()
>>> print pep
>my_gene
QMY
|