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
|
#!/usr/bin/env python
import unittest
from cogent import DNA, LoadSeqs
from cogent.core.annotation import Feature, Variable, _Feature
from cogent.core.location import Map, Span, as_map
__author__ = "Gavin Huttley"
__copyright__ = "Copyright 2007-2016, The Cogent Project"
__credits__ = ["Gavin Huttley"]
__license__ = "GPL"
__version__ = "1.9"
__maintainer__ = "Gavin Huttley"
__email__ = "gavin.huttley@anu.edu.au"
__status__ = "Production"
def makeSampleSequence(with_gaps=False):
raw_seq = 'AACCCAAAATTTTTTGGGGGGGGGGCCCC'
cds = (15, 25)
utr = (12, 15)
if with_gaps:
raw_seq = raw_seq[:5] + '-----' +raw_seq[10:-2] + '--'
seq = DNA.makeSequence(raw_seq)
seq.addAnnotation(Feature, 'CDS', 'CDS', [cds])
seq.addAnnotation(Feature, "5'UTR", "5' UTR", [utr])
return seq
def makeSampleAlignment():
seq1 = makeSampleSequence()
seq2 = makeSampleSequence(with_gaps=True)
seqs = {'FAKE01': seq1, 'FAKE02': seq2}
aln = LoadSeqs(data = seqs)
aln.addAnnotation(Feature, 'misc_feature', 'misc', [(12,25)])
aln.addAnnotation(Feature, 'CDS', 'blue', [(15, 25)])
aln.addAnnotation(Feature, "5'UTR", 'red', [(2, 4)])
aln.addAnnotation(Feature, "LTR", "fake", [(2,15)])
return aln
class TestAnnotations(unittest.TestCase):
def setUp(self):
self.seq = makeSampleSequence()
self.aln = makeSampleAlignment()
def test_inherit_feature(self):
"""should be able to subclass and extend _Feature"""
class NewFeat(_Feature):
def __init__(self, *args, **kwargs):
super(NewFeat, self).__init__(*args, **kwargs)
def newMethod(self):
if len(self.map.spans) > 1:
as_one = self.asOneSpan() # should create new instance of NewFeat
return as_one.newMethod()
return True
seq = DNA.makeSequence('ACGTACGTACGT')
f = seq.addAnnotation(NewFeat, as_map([(1,3), (5,7)], len(seq)),
type='gene', Name='abcd')
self.assertEqual(type(f.asOneSpan()), NewFeat)
self.assertEqual(type(f.getShadow()), NewFeat)
f2 = seq.addAnnotation(NewFeat, as_map([(3,5)], len(seq)),
type='gene', Name='def')
self.assertEqual(type(seq.getRegionCoveringAll([f, f2],
feature_class=NewFeat)),
NewFeat)
# now use the new method
f.newMethod()
def test_slice_seq_with_annotations(self):
newseq = self.seq[:5] + self.seq[10:]
for annot_type in ["CDS", "5'UTR"]:
orig = str(list(self.seq.getByAnnotation(annot_type))[0])
new = str(list(newseq.getByAnnotation(annot_type))[0])
assert orig == new, (annot_type, orig, new)
def test_aln_annotations(self):
"""test that annotations to alignment and its' sequences"""
aln_expecteds = {"misc_feature":{'FAKE01': 'TTTGGGGGGGGGG',
'FAKE02': 'TTTGGGGGGGGGG'},
"CDS": {'FAKE01': 'GGGGGGGGGG', 'FAKE02': 'GGGGGGGGGG'},
"5'UTR": {'FAKE01': 'CC', 'FAKE02': 'CC'},
"LTR" : {"FAKE01": "CCCAAAATTTTTT",
"FAKE02": "CCC-----TTTTT"}
}
seq_expecteds = {"CDS": {"FAKE01": "GGGGGGGGGG",
"FAKE02": "GGGGGGGGGG"},
"5'UTR": {"FAKE01": "TTT",
"FAKE02": "TTT"}}
for annot_type in ["misc_feature", "CDS", "5'UTR", "LTR"]:
observed = list(self.aln.getByAnnotation(annot_type))[0].todict()
expected = aln_expecteds[annot_type]
assert observed == expected, (annot_type, expected, observed)
if annot_type in ["misc_feature", "LTR"]:
continue # because seqs haven't been annotated with it
for name in self.aln.Names:
observed = list(self.aln.NamedSeqs[name].data.\
getByAnnotation(annot_type))[0]
observed = str(observed)
expected = seq_expecteds[annot_type][name]
assert str(observed) == expected, (annot_type, name, expected,
observed)
def test_slice_aln_with_annotations(self):
"""test that annotations of sequences and alignments survive alignment
slicing."""
aln_expecteds = {"misc_feature":{'FAKE01': 'TTTGGGGGGGGGG',
'FAKE02': 'TTTGGGGGGGGGG'},
"CDS": {'FAKE01': 'GGGGGGGGGG', 'FAKE02': 'GGGGGGGGGG'},
"5'UTR": {'FAKE01': 'CC', 'FAKE02': 'CC'},
"LTR" : {"FAKE01": "CCCTTTTT",
"FAKE02": "CCCTTTTT"}}
newaln = self.aln[:5]+self.aln[10:]
feature_list = newaln.getAnnotationsMatching("LTR")
for annot_type in ["LTR", "misc_feature", "CDS", "5'UTR"]:
feature_list = newaln.getAnnotationsMatching(annot_type)
new = newaln.getRegionCoveringAll(feature_list).getSlice().todict()
expected = aln_expecteds[annot_type]
assert expected == new, (annot_type, expected, new)
if annot_type in ["misc_feature", "LTR"]:
continue # because seqs haven't been annotated with it
for name in self.aln.Names:
orig = str(list(self.aln.getAnnotationsFromSequence(name,
annot_type))[0].getSlice())
new = str(list(newaln.getAnnotationsFromSequence(name,
annot_type))[0].getSlice())
assert orig == new, (name, annot_type, orig, new)
def test_feature_projection(self):
expecteds = {"FAKE01": "CCCAAAATTTTTT", "FAKE02": "CCC-----TTTTT"}
aln_ltr = self.aln.getAnnotationsMatching('LTR')[0]
for seq_name in ['FAKE01', 'FAKE02']:
expected = expecteds[seq_name]
seq_ltr = self.aln.projectAnnotation(seq_name, aln_ltr)
if '-' in expected:
self.assertRaises(ValueError, seq_ltr.getSlice)
seq_ltr = seq_ltr.withoutLostSpans()
expected = expected.replace('-', '')
self.assertEqual(seq_ltr.getSlice(), expected)
def test_reversecomplement(self):
"""test correct translation of annotations on reverse complement."""
aln_expecteds = {"misc_feature":{'FAKE01': 'TTTGGGGGGGGGG',
'FAKE02': 'TTTGGGGGGGGGG'},
"CDS": {'FAKE01': 'GGGGGGGGGG', 'FAKE02': 'GGGGGGGGGG'},
"5'UTR": {'FAKE01': 'CC', 'FAKE02': 'CC'},
"LTR" : {"FAKE01": "CCCAAAATTTTTT",
"FAKE02": "CCC-----TTTTT"}
}
seq_expecteds = {"CDS": {"FAKE01": "GGGGGGGGGG",
"FAKE02": "GGGGGGGGGG"},
"5'UTR": {"FAKE01": "TTT",
"FAKE02": "TTT"}}
rc = self.aln.rc()
# rc'ing an Alignment or Sequence rc's their annotations too. This means
# slicing returns the same sequence as the non-rc'd alignment/seq
for annot_type in ["misc_feature", "CDS", "5'UTR", "LTR"]:
observed = list(self.aln.getByAnnotation(annot_type))[0].todict()
expected = aln_expecteds[annot_type]
assert observed == expected, ("+", annot_type, expected, observed)
observed = list(rc.getByAnnotation(annot_type))[0].todict()
expected = aln_expecteds[annot_type]
assert observed == expected, ("-", annot_type, expected, observed)
if annot_type in ["misc_feature", "LTR"]:
continue # because seqs haven't been annotated with it
for name in self.aln.Names:
observed = list(self.aln.NamedSeqs[name].data.\
getByAnnotation(annot_type))[0]
observed = str(observed)
expected = seq_expecteds[annot_type][name]
assert str(observed) == expected, ("+", annot_type, name, expected,
observed)
observed = list(rc.NamedSeqs[name].data.\
getByAnnotation(annot_type))[0]
observed = str(observed)
expected = seq_expecteds[annot_type][name]
assert str(observed) == expected, ("-", annot_type, name, expected,
observed)
class TestMapSpans(unittest.TestCase):
"""Test attributes of Map & Spans classes critical to annotation
manipulation."""
def test_span(self):
length = 100
forward = Span(20, 30)
reverse = Span(70, 80, Reverse=True)
assert forward.reversedRelativeTo(100) == reverse
assert reverse.reversedRelativeTo(100) == forward
def test_map(self):
"""reversing a map with multiple spans should preserve span relative
order"""
forward = [Span(20,30), Span(40,50)]
fmap = Map(spans=forward, parent_length=100)
fmap_reversed = fmap.nucleicReversed()
reverse = [Span(70,80, Reverse=True), Span(50,60, Reverse=True)]
rmap = Map(spans=reverse, parent_length=100)
for i in range(2):
self.assertEquals(fmap_reversed.spans[i], rmap.spans[i])
if __name__ == '__main__':
unittest.main()
|
