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
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
|
# Copyright (C) 2013 by Yanbo Ye (yeyanbo289@gmail.com)
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""Unit tests for the Bio.Phylo.TreeConstruction module."""
import unittest
from Bio._py3k import StringIO
from Bio import AlignIO
from Bio import Phylo
from Bio.Phylo import BaseTree
from Bio.Phylo import TreeConstruction
from Bio.Phylo import Consensus
from Bio.Phylo.TreeConstruction import _Matrix
from Bio.Phylo.TreeConstruction import _DistanceMatrix
from Bio.Phylo.TreeConstruction import DistanceCalculator
from Bio.Phylo.TreeConstruction import DistanceTreeConstructor
from Bio.Phylo.TreeConstruction import ParsimonyScorer
from Bio.Phylo.TreeConstruction import NNITreeSearcher
from Bio.Phylo.TreeConstruction import ParsimonyTreeConstructor
class DistanceMatrixTest(unittest.TestCase):
"""Test for _DistanceMatrix construction and manipulation"""
def setUp(self):
self.names = ['Alpha', 'Beta', 'Gamma', 'Delta']
self.matrix = [[0], [1, 0], [2, 3, 0], [4, 5, 6, 0]]
def test_good_construction(self):
dm = _DistanceMatrix(self.names, self.matrix)
self.assertTrue(isinstance(dm, TreeConstruction._DistanceMatrix))
self.assertEqual(dm.names[0], 'Alpha')
self.assertEqual(dm.matrix[2][1], 3)
self.assertEqual(len(dm), 4)
self.assertEqual(repr(dm), "_DistanceMatrix(names=['Alpha', 'Beta', 'Gamma', 'Delta'], matrix=[[0], [1, 0], [2, 3, 0], [4, 5, 6, 0]])")
def test_bad_construction(self):
self.assertRaises(TypeError, _DistanceMatrix, ['Alpha', 100, 'Gamma', 'Delta'], [[0], [0.1, 0], [0.2, 0.3, 0], [0.4, 0.5, 0.6, 0]])
self.assertRaises(TypeError, _DistanceMatrix, ['Alpha', 'Beta', 'Gamma', 'Delta'], [[0], ['a'], [0.2, 0.3], [0.4, 0.5, 0.6]])
self.assertRaises(ValueError, _DistanceMatrix, ['Alpha', 'Alpha', 'Gamma', 'Delta'], [[0], [0.1], [0.2, 0.3], [0.4, 0.5, 0.6]])
self.assertRaises(ValueError, _DistanceMatrix, ['Alpha', 'Beta', 'Gamma', 'Delta'], [[0], [0.2, 0], [0.4, 0.5, 0.6]])
self.assertRaises(ValueError, _DistanceMatrix, ['Alpha', 'Beta', 'Gamma', 'Delta'], [[0], [0.1], [0.2, 0.3, 0.4], [0.4, 0.5, 0.6]])
def test_good_manipulation(self):
dm = _DistanceMatrix(self.names, self.matrix)
# getitem
self.assertEqual(dm[1], [1, 0, 3, 5])
self.assertEqual(dm[2, 1], 3)
self.assertEqual(dm[2][1], 3)
self.assertEqual(dm[1, 2], 3)
self.assertEqual(dm[1][2], 3)
self.assertEqual(dm['Alpha'], [0, 1, 2, 4])
self.assertEqual(dm['Gamma', 'Delta'], 6)
# setitem
dm['Alpha'] = [0, 10, 20, 40]
self.assertEqual(dm['Alpha'], [0, 10, 20, 40])
# delitem insert item
del dm[1]
self.assertEqual(dm.names, ['Alpha', 'Gamma', 'Delta'])
self.assertEqual(dm.matrix, [[0], [20, 0], [40, 6, 0]])
dm.insert('Beta', [1, 0, 3, 5], 1)
self.assertEqual(dm.names, self.names)
self.assertEqual(dm.matrix, [[0], [1, 0], [20, 3, 0], [40, 5, 6, 0]])
del dm['Alpha']
self.assertEqual(dm.names, ['Beta', 'Gamma', 'Delta'])
self.assertEqual(dm.matrix, [[0], [3, 0], [5, 6, 0]])
dm.insert('Alpha', [1, 2, 4, 0])
self.assertEqual(dm.names, ['Beta', 'Gamma', 'Delta', 'Alpha'])
self.assertEqual(dm.matrix, [[0], [3, 0], [5, 6, 0], [1, 2, 4, 0]])
def test_bad_manipulation(self):
dm = _DistanceMatrix(self.names, self.matrix)
# getitem
self.assertRaises(ValueError, dm.__getitem__, 'A')
self.assertRaises(ValueError, dm.__getitem__, ('Alpha', 'A'))
self.assertRaises(TypeError, dm.__getitem__, (1, 'A'))
self.assertRaises(TypeError, dm.__getitem__, (1, 1.2))
self.assertRaises(IndexError, dm.__getitem__, 6)
self.assertRaises(IndexError, dm.__getitem__, (10, 10))
# setitem: item or index test
self.assertRaises(ValueError, dm.__setitem__, 'A', [1, 3, 4])
self.assertRaises(ValueError, dm.__setitem__, ('Alpha', 'A'), 4)
self.assertRaises(TypeError, dm.__setitem__, (1, 'A'), 3)
self.assertRaises(TypeError, dm.__setitem__, (1, 1.2), 2)
self.assertRaises(IndexError, dm.__setitem__, 6, [1, 3, 4])
self.assertRaises(IndexError, dm.__setitem__, (10, 10), 1)
# setitem: value test
self.assertRaises(ValueError, dm.__setitem__, 0, [1, 2])
self.assertRaises(TypeError, dm.__setitem__, ('Alpha', 'Beta'), 'a')
self.assertRaises(TypeError, dm.__setitem__, 'Alpha', ['a', 'b', 'c'])
class DistanceCalculatorTest(unittest.TestCase):
"""Test DistanceCalculator"""
def test_known_matrices(self):
aln = AlignIO.read('TreeConstruction/msa.phy', 'phylip')
calculator = DistanceCalculator('identity')
dm = calculator.get_distance(aln)
self.assertEqual(dm['Alpha', 'Beta'], 1 - (10 * 1.0 / 13))
calculator = DistanceCalculator('blastn')
dm = calculator.get_distance(aln)
self.assertEqual(dm['Alpha', 'Beta'], 1 - (38 * 1.0 / 65))
calculator = DistanceCalculator('trans')
dm = calculator.get_distance(aln)
self.assertEqual(dm['Alpha', 'Beta'], 1 - (49 * 1.0 / 78))
calculator = DistanceCalculator('blosum62')
dm = calculator.get_distance(aln)
self.assertEqual(dm['Alpha', 'Beta'], 1 - (53 * 1.0 / 84))
def test_nonmatching_seqs(self):
aln = AlignIO.read(
StringIO('\n'.join(
[">Alpha", "A-A--",
">Gamma", "-Y-Y-"])),
"fasta")
# With a proper scoring matrix -- no matches
dmat = DistanceCalculator('blosum62').get_distance(aln)
self.assertEqual(dmat['Alpha', 'Alpha'], 0.)
self.assertEqual(dmat['Alpha', 'Gamma'], 1.)
# Comparing characters only -- 4 misses, 1 match
dmat = DistanceCalculator().get_distance(aln)
self.assertEqual(dmat['Alpha', 'Alpha'], 0.)
self.assertAlmostEqual(dmat['Alpha', 'Gamma'], 4. / 5.)
class DistanceTreeConstructorTest(unittest.TestCase):
"""Test DistanceTreeConstructor"""
def setUp(self):
self.aln = AlignIO.read('TreeConstruction/msa.phy', 'phylip')
calculator = DistanceCalculator('blosum62')
self.dm = calculator.get_distance(self.aln)
self.constructor = DistanceTreeConstructor(calculator)
def test_upgma(self):
tree = self.constructor.upgma(self.dm)
self.assertTrue(isinstance(tree, BaseTree.Tree))
# tree_file = StringIO()
# Phylo.write(tree, tree_file, 'newick')
ref_tree = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
self.assertTrue(Consensus._equal_topology(tree, ref_tree))
# ref_tree.close()
def test_nj(self):
tree = self.constructor.nj(self.dm)
self.assertTrue(isinstance(tree, BaseTree.Tree))
# tree_file = StringIO()
# Phylo.write(tree, tree_file, 'newick')
ref_tree = Phylo.read('./TreeConstruction/nj.tre', 'newick')
self.assertTrue(Consensus._equal_topology(tree, ref_tree))
# ref_tree.close()
def test_built_tree(self):
tree = self.constructor.build_tree(self.aln)
self.assertTrue(isinstance(tree, BaseTree.Tree))
# tree_file = StringIO()
# Phylo.write(tree, tree_file, 'newick')
ref_tree = Phylo.read('./TreeConstruction/nj.tre', 'newick')
self.assertTrue(Consensus._equal_topology(tree, ref_tree))
# ref_tree.close()
class ParsimonyScorerTest(unittest.TestCase):
"""Test ParsimonyScorer"""
def test_get_score(self):
aln = AlignIO.read('TreeConstruction/msa.phy', 'phylip')
tree = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
scorer = ParsimonyScorer()
score = scorer.get_score(tree, aln)
self.assertEqual(score, 2 + 1 + 2 + 2 + 1 + 1 + 1 + 3)
alphabet = ['A', 'T', 'C', 'G']
step_matrix = [[0],
[2.5, 0],
[2.5, 1, 0],
[1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3.5 + 2.5 + 3.5 + 3.5 + 2.5 + 1 + 2.5 + 4.5)
alphabet = ['A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', '1', '2', 'T', 'V', 'W', 'Y', '*', '-']
step_matrix = [[0],
[2, 0],
[1, 2, 0],
[1, 2, 1, 0],
[2, 1, 2, 2, 0],
[1, 1, 1, 1, 2, 0],
[2, 2, 1, 2, 2, 2, 0],
[2, 2, 2, 2, 1, 2, 2, 0],
[2, 2, 2, 1, 2, 2, 2, 1, 0],
[2, 2, 2, 2, 1, 2, 1, 1, 2, 0],
[2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 0],
[2, 2, 1, 2, 2, 2, 1, 1, 1, 2, 2, 0],
[1, 2, 2, 2, 2, 2, 1, 2, 2, 1, 2, 2, 0],
[2, 2, 2, 1, 2, 2, 1, 2, 1, 1, 2, 2, 1, 0],
[2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 0],
[1, 1, 2, 2, 1, 2, 2, 2, 2, 1, 2, 2, 1, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 1, 2, 2, 2, 1, 2, 2, 1, 2, 0],
[1, 2, 2, 2, 2, 2, 2, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 0],
[1, 2, 1, 1, 1, 1, 2, 1, 2, 1, 1, 2, 2, 2, 2, 2, 2, 2, 0],
[2, 1, 2, 2, 2, 1, 2, 2, 2, 1, 2, 3, 2, 2, 1, 1, 2, 2, 2, 0],
[2, 1, 1, 2, 1, 2, 1, 2, 2, 2, 3, 1, 2, 2, 2, 1, 2, 2, 2, 2, 0],
[2, 1, 2, 1, 2, 1, 2, 2, 1, 1, 2, 2, 2, 1, 1, 1, 2, 2, 2, 1, 1, 0],
[3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
score = scorer.get_score(tree, aln)
self.assertEqual(score, 3 + 1 + 3 + 3 + 2 + 1 + 2 + 5)
class NNITreeSearcherTest(unittest.TestCase):
"""Test NNITreeSearcher"""
def test_get_neighbors(self):
tree = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
alphabet = ['A', 'T', 'C', 'G']
step_matrix = [[0],
[2.5, 0],
[2.5, 1, 0],
[1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
searcher = NNITreeSearcher(scorer)
trees = searcher._get_neighbors(tree)
self.assertEqual(len(trees), 2 * (5 - 3))
Phylo.write(trees, './TreeConstruction/neighbor_trees.tre', 'newick')
class ParsimonyTreeConstructorTest(unittest.TestCase):
"""Test ParsimonyTreeConstructor"""
def test_build_tree(self):
aln = AlignIO.read('TreeConstruction/msa.phy', 'phylip')
tree1 = Phylo.read('./TreeConstruction/upgma.tre', 'newick')
tree2 = Phylo.read('./TreeConstruction/nj.tre', 'newick')
alphabet = ['A', 'T', 'C', 'G']
step_matrix = [[0],
[2.5, 0],
[2.5, 1, 0],
[1, 2.5, 2.5, 0]]
matrix = _Matrix(alphabet, step_matrix)
scorer = ParsimonyScorer(matrix)
searcher = NNITreeSearcher(scorer)
constructor = ParsimonyTreeConstructor(searcher, tree1)
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, './TreeConstruction/pars1.tre', 'newick')
constructor.starting_tree = tree2
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, './TreeConstruction/pars2.tre', 'newick')
constructor.starting_tree = None
best_tree = constructor.build_tree(aln)
Phylo.write(best_tree, './TreeConstruction/pars3.tre', 'newick')
if __name__ == '__main__':
runner = unittest.TextTestRunner(verbosity=2)
unittest.main(testRunner=runner)
|
