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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
|
.. _dna-rna-seqs:
``Sequence``
============
The ``Sequence`` object contains classes that represent biological sequence data. These provide generic biological sequence manipulation functions, plus functions that are critical for the ``evolve`` module calculations.
.. warning:: Do not import sequence classes directly! It is expected that you will access them through ``MolType`` objects. The molecular types can be accessed via the ``cogent3.get_moltype()`` function. Sequence classes depend on information from the ``MolType`` that is **only** available after ``MolType`` has been imported. Sequences are intended to be immutable. This is not enforced by the code for performance reasons, but don't alter the ``MolType`` or the sequence data after creation.
DNA and RNA sequences
---------------------
.. authors, Gavin Huttley, Kristian Rother, Patrick Yannul, Tom Elliott, Tony Walters, Meg Pirrung
Creating a DNA sequence from a string
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
All sequence and alignment objects have a molecular type, or ``MolType`` which provides key properties for validating sequence characters. Here we use the ``DNA`` ``MolType`` to create a DNA sequence.
.. jupyter-execute::
from cogent3 import DNA
my_seq = DNA.make_seq("AGTACACTGGT")
my_seq
print(my_seq)
str(my_seq)
Creating a RNA sequence from a string
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import RNA
rnaseq = RNA.make_seq("ACGUACGUACGUACGU")
Converting to FASTA format
^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import DNA
my_seq = DNA.make_seq("AGTACACTGGT")
print(my_seq.to_fasta())
Convert a RNA sequence to FASTA format
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import RNA
rnaseq = RNA.make_seq("ACGUACGUACGUACGU")
rnaseq.to_fasta()
Creating a named sequence
^^^^^^^^^^^^^^^^^^^^^^^^^
You can also use a convenience ``make_seq()`` function, providing the moltype as a string.
.. jupyter-execute::
from cogent3 import make_seq
my_seq = make_seq("AGTACACTGGT", "my_gene", moltype="dna")
my_seq
type(my_seq)
Setting or changing the name of a sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import make_seq
my_seq = make_seq("AGTACACTGGT", moltype="dna")
my_seq.name = "my_gene"
print(my_seq.to_fasta())
Complementing a DNA sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import DNA
my_seq = DNA.make_seq("AGTACACTGGT")
print(my_seq.complement())
Reverse complementing a DNA sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
print(my_seq.rc())
The ``rc`` method name is easier to type
.. jupyter-execute::
print(my_seq.rc())
.. _translation:
Translate a ``DnaSequence`` to protein
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import DNA
my_seq = DNA.make_seq("GCTTGGGAAAGTCAAATGGAA", "protein-X")
pep = my_seq.get_translation()
type(pep)
print(pep.to_fasta())
Converting a DNA sequence to RNA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import DNA
my_seq = DNA.make_seq("ACGTACGTACGTACGT")
print(my_seq.to_rna())
Convert an RNA sequence to DNA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import RNA
rnaseq = RNA.make_seq("ACGUACGUACGUACGU")
print(rnaseq.to_dna())
Testing complementarity
^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import DNA
a = DNA.make_seq("AGTACACTGGT")
a.can_pair(a.complement())
a.can_pair(a.rc())
Joining two DNA sequences
^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import DNA
my_seq = DNA.make_seq("AGTACACTGGT")
extra_seq = DNA.make_seq("CTGAC")
long_seq = my_seq + extra_seq
long_seq
str(long_seq)
Slicing DNA sequences
^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
my_seq[1:6]
Getting 3rd positions from codons
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The easiest approach is to work off the ``cogent3`` ``ArrayAlignment`` object.
We'll do this by specifying the position indices of interest, creating a sequence ``Feature`` and using that to extract the positions.
.. jupyter-execute::
from cogent3 import DNA
seq = DNA.make_array_seq("ATGATGATGATG")
pos3 = seq[2::3]
assert str(pos3) == "GGGG"
Getting 1st and 2nd positions from codons
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
In this instance we can use the annotatable sequence classes.
.. jupyter-execute::
from cogent3 import DNA
seq = DNA.make_seq("ATGATGATGATG")
indices = [(i, i + 2) for i in range(len(seq))[::3]]
pos12 = seq.add_feature("pos12", "pos12", indices)
pos12 = pos12.get_slice()
assert str(pos12) == "ATATATAT"
Return a randomized version of the sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
::
print rnaseq.shuffle()
ACAACUGGCUCUGAUG
Remove gaps from a sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. jupyter-execute::
from cogent3 import RNA
s = RNA.make_seq("--AUUAUGCUAU-UAu--")
print(s.degap())
|
