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
|
from copy import deepcopy
from gffutils import merge_criteria as mc
from gffutils.test.synth_test_base import (
TestWithSynthDB,
num_synthetic_features,
num_synthetic_overlap,
)
class TestMerge(TestWithSynthDB):
def _merge_and_compare(self, ids, expected_merge_children, **kwargs):
features = [self.db[id] for id in ids]
features_backup = deepcopy(features)
merged = list(self.db.merge(features, **kwargs))
dump = self._dump_db()
m_dump = "\n".join(map(str, merged))
# Ensure db wasn't modified
self.assertEqual(num_synthetic_features, self.db.count_features_of_type(), dump)
for expected, actual in zip(features_backup, ids):
self.assertEqual(
expected,
self.db[actual],
"\n".join(map(str, [expected, self.db[actual]])) + "\n",
)
# Ensure input Features not modified
for expected, actual in zip(features_backup, features):
self.assertEqual(
expected, actual, "\n".join(map(str, [expected, actual])) + "\n"
)
# Ensure output matches expected
self.assertEqual(len(expected_merge_children), len(merged), m_dump)
for expected, actual in zip(expected_merge_children, merged):
c_dump = "\n".join(map(str, actual.children)) + "\n" + str(actual) + "\n"
self.assertEqual(
len(expected),
len(actual.children),
"\n".join(map(str, [expected, actual])) + "\n",
)
self.assertTrue(
all(child.id in expected for child in actual.children), c_dump
)
if actual.strand != ".":
self.assertTrue(
all(f.strand == actual.strand for f in actual.children), c_dump
)
if actual.frame != ".":
self.assertTrue(
all(f.frame == actual.frame for f in actual.children), c_dump
)
if expected:
self.assertEqual(
actual.start, min(f.start for f in actual.children), c_dump
)
self.assertEqual(
actual.end, max(f.end for f in actual.children), c_dump
)
if all(f.seqid == actual.children[0].seqid for f in actual.children):
self.assertEqual(actual.seqid, actual.children[0].seqid, c_dump)
else:
self.assertEqual(
set(f.seqid for f in actual.children),
set(actual.seqid.split(",")),
c_dump,
)
if all(
f.featuretype == actual.children[0].featuretype
for f in actual.children
):
self.assertTrue(
all(
f.featuretype == actual.featuretype for f in actual.children
),
c_dump,
)
else:
self.assertEqual("sequence_feature", actual.featuretype, c_dump)
return merged
def test_defaults(self):
merged = list(
self.db.merge(
self.db.all_features(
order_by=("seqid", "featuretype", "strand", "start")
)
)
)
dump = "\n".join(map(str, merged))
self.assertEqual(num_synthetic_features, self.db.count_features_of_type(), dump)
self.assertEqual(6, len(merged), dump)
merged_count = 0
for f in merged:
if f.children:
self.assertEqual(num_synthetic_overlap, len(f.children), dump)
merged_count += 1
self.assertEqual(1, merged_count)
def test_none(self):
merged = list(self.db.merge([]))
dump = self._dump_db()
self.assertEqual(num_synthetic_features, self.db.count_features_of_type(), dump)
self.assertEqual(0, len(merged))
def test_one(self):
self._merge_and_compare(["basic1"], [[]])
def test_no_overlap(self):
self._merge_and_compare(["basic1", "no_overlap1"], [[], []])
def test_perfect_overlap(self):
self._merge_and_compare(
["basic1", "perfect_overlap1"], [["basic1", "perfect_overlap1"]]
)
def test_overlap(self):
self._merge_and_compare(["basic1", "adjacent1"], [["basic1", "adjacent1"]])
def test_any_overlap(self):
self._merge_and_compare(
["basic1", "overlap_start1"],
[["basic1", "overlap_start1"]],
merge_criteria=(
mc.seqid,
mc.overlap_any_inclusive,
mc.strand,
mc.feature_type,
),
)
self._merge_and_compare(
["overlap_start1", "basic1"], [["basic1", "overlap_start1"]]
)
self._merge_and_compare(
["adjacent1", "basic1"],
[["basic1", "adjacent1"]],
merge_criteria=(
mc.seqid,
mc.overlap_any_inclusive,
mc.strand,
mc.feature_type,
),
)
self._merge_and_compare(
["adjacent4", "basic1"],
[["basic1", "adjacent4"]],
merge_criteria=(
mc.seqid,
mc.overlap_any_inclusive,
mc.strand,
mc.feature_type,
),
)
def test_adjacent_len1(self):
self._merge_and_compare(["basic1", "adjacent2"], [["basic1", "adjacent2"]])
self._merge_and_compare(
["adjacent2", "basic1"],
[["basic1", "adjacent2"]],
merge_criteria=(
mc.seqid,
mc.overlap_any_inclusive,
mc.strand,
mc.feature_type,
),
)
self._merge_and_compare(
["basic1", "adjacent3"],
[["basic1", "adjacent3"]],
merge_criteria=(
mc.seqid,
mc.overlap_any_inclusive,
mc.strand,
mc.feature_type,
),
)
self._merge_and_compare(["adjacent3", "basic1"], [["basic1", "adjacent3"]])
def test_end_overlap(self):
self._merge_and_compare(
["basic1", "overlap_end1"], [["basic1", "overlap_end1"]]
)
# TODO test various feature orders
# TODO test various merge criteria
# TODO test multiline, this doesn't really work until gffutils better supports multiline features
# TODO add test for PR #152
|
