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
217
218
219
220
221
222
223
224
225
226
|
.. _dna-rna-seqs:
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.
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence("AGTACACTGGT")
>>> my_seq
DnaSequence(AGTACAC... 11)
>>> print my_seq
AGTACACTGGT
>>> str(my_seq)
'AGTACACTGGT'
Creating a RNA sequence from a string
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import RNA
>>> rnaseq = RNA.makeSequence('ACGUACGUACGUACGU')
Converting to FASTA format
^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence('AGTACACTGGT')
>>> print my_seq.toFasta()
>0
AGTACACTGGT
Convert a RNA sequence to FASTA format
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import RNA
>>> rnaseq = RNA.makeSequence('ACGUACGUACGUACGU')
>>> rnaseq.toFasta()
'>0\nACGUACGUACGUACGU'
Creating a named sequence
^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence('AGTACACTGGT','my_gene')
>>> my_seq
DnaSequence(AGTACAC... 11)
>>> type(my_seq)
<class 'cogent.core.sequence.DnaSequence'>
Setting or changing the name of a sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence('AGTACACTGGT')
>>> my_seq.Name = 'my_gene'
>>> print my_seq.toFasta()
>my_gene
AGTACACTGGT
Complementing a DNA sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence("AGTACACTGGT")
>>> print my_seq.complement()
TCATGTGACCA
Reverse complementing a DNA sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> print my_seq.reversecomplement()
ACCAGTGTACT
The ``rc`` method name is easier to type
.. doctest::
>>> print my_seq.rc()
ACCAGTGTACT
.. _translation:
Translate a ``DnaSequence`` to protein
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence('GCTTGGGAAAGTCAAATGGAA','protein-X')
>>> pep = my_seq.getTranslation()
>>> type(pep)
<class 'cogent.core.sequence.ProteinSequence'>
>>> print pep.toFasta()
>protein-X
AWESQME
Converting a DNA sequence to RNA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence('ACGTACGTACGTACGT')
>>> print my_seq.toRna()
ACGUACGUACGUACGU
Convert an RNA sequence to DNA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import RNA
>>> rnaseq = RNA.makeSequence('ACGUACGUACGUACGU')
>>> print rnaseq.toDna()
ACGTACGTACGTACGT
Testing complementarity
^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> a = DNA.makeSequence("AGTACACTGGT")
>>> a.canPair(a.complement())
False
>>> a.canPair(a.reversecomplement())
True
Joining two DNA sequences
^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import DNA
>>> my_seq = DNA.makeSequence("AGTACACTGGT")
>>> extra_seq = DNA.makeSequence("CTGAC")
>>> long_seq = my_seq + extra_seq
>>> long_seq
DnaSequence(AGTACAC... 16)
>>> str(long_seq)
'AGTACACTGGTCTGAC'
Slicing DNA sequences
^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> my_seq[1:6]
DnaSequence(GTACA)
Getting 3rd positions from codons
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
We'll do this by specifying the position indices of interest, creating a sequence ``Feature`` and using that to extract the positions.
.. doctest::
>>> from cogent import DNA
>>> seq = DNA.makeSequence('ATGATGATGATG')
Creating the position indices, note that we start at the 2nd index (the 'first' codon's 3rd position) indicate each position as a *span* (``i -- i+1``).
.. doctest::
>>> indices = [(i, i+1) for i in range(len(seq))[2::3]]
Create the sequence feature and use it to slice the sequence.
.. doctest::
>>> pos3 = seq.addFeature('pos3', 'pos3', indices)
>>> pos3 = pos3.getSlice()
>>> assert str(pos3) == 'GGGG'
Getting 1st and 2nd positions from codons
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The only difference here to above is that our spans cover 2 positions.
.. doctest::
>>> from cogent import DNA
>>> seq = DNA.makeSequence('ATGATGATGATG')
>>> indices = [(i, i+2) for i in range(len(seq))[::3]]
>>> pos12 = seq.addFeature('pos12', 'pos12', indices)
>>> pos12 = pos12.getSlice()
>>> assert str(pos12) == 'ATATATAT'
Return a randomized version of the sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
::
print rnaseq.shuffle()
ACAACUGGCUCUGAUG
Remove gaps from a sequence
^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. doctest::
>>> from cogent import RNA
>>> s = RNA.makeSequence('--AUUAUGCUAU-UAu--')
>>> print s.degap()
AUUAUGCUAUUAU
|
