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
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
|
from io import StringIO
import pandas as pd
import numpy as np
import pytest
from bioframe.core.checks import *
from bioframe.ops import sort_bedframe
def test_is_cataloged():
### chr2q is not in view
view_df = pd.DataFrame(
[
["chr1", 0, 12, "chr1p"],
["chr1", 13, 26, "chr1q"],
["chrX", 1, 8, "chrX_0"],
],
columns=["chrom", "start", "end", "name"],
)
df = pd.DataFrame(
[
["chr1", 0, 12, "chr1p"],
["chr1", 5, 15, "chr1p"],
["chr2", 13, 26, "chr2q"],
["chrX", 1, 8, "chrX_0"],
],
columns=["chrom", "start", "end", "view_region"],
)
assert not is_cataloged(df, view_df)
### chr1q is in view, df_view_col and view_name_col have funny labels.
view_df = pd.DataFrame(
[
["chr1", 0, 12, "chr1p"],
["chr1", 13, 26, "chr1q"],
["chrX", 1, 8, "chrX_0"],
],
columns=["chrom", "start", "end", "funny_name"],
)
df = pd.DataFrame(
[
["chr1", 0, 12, "chr1p"],
["chr2", 13, 26, "chr1q"],
["chrX", 1, 8, "chrX_0"],
],
columns=["chrom", "start", "end", "funny_view_region"],
)
assert is_cataloged(
df, view_df, df_view_col="funny_view_region", view_name_col="funny_name"
)
def test_is_contained():
view_df = pd.DataFrame(
[
["chr1", 0, 20, "chr1p"],
["chr1", 21, 30, "chr1q"],
["chrX", 1, 10, "chrX_0"],
],
columns=["chrom", "start", "end", "name"],
)
### not contained because chr2q is not cataloged
df = pd.DataFrame(
[
["chr1", 0, 12, "chr1p"],
["chr2", 13, 26, "chr2q"],
["chrX", 1, 8, "chrX_0"],
],
columns=["chrom", "start", "end", "view_region"],
)
assert not is_contained(df, view_df, df_view_col="view_region")
### not contained because second interval falls outside the view regions
df = pd.DataFrame(
[
["chr1", 14, 15, "chr1p"],
["chr1", -1, 1, "chr1q"],
["chrX", 1, 8, "chrX_0"],
],
columns=["chrom", "start", "end", "view_region"],
)
assert not is_contained(df, view_df)
df = pd.DataFrame(
[
["chr1", 12, 12, "chr1p"],
["chr1", 13, 14, "chr1q"],
["chrX", 1, 8, "chrX_0"],
],
columns=["chrom", "start", "end", "view_region"],
)
# is contained, because assignments are inferred
assert is_contained(df, view_df)
# is not contained, because assignments are not inferred
assert not is_contained(df, view_df, df_view_col="view_region")
### second interval falls completely out of the view
df = pd.DataFrame(
[
["chr1", 12, 12, "chr1p"],
["chr1", 100, 101, "chr1q"],
],
columns=["chrom", "start", "end", "view_region"],
)
# fails due to NAs after overlap to infer the regions
with pytest.raises(AssertionError):
is_contained(df, view_df, raise_errors=True)
# fails due to some of the intervals being trimmed
with pytest.raises(ValueError):
is_contained(df, view_df, df_view_col="view_region", raise_errors=True)
def test_is_overlapping():
### interval on chr1 overlaps
d = """chrom start end
0 chr1 3 6
1 chr1 5 10
2 chr2 5 10"""
df = pd.read_csv(StringIO(d), sep=r"\s+")
assert is_overlapping(df) is True
### adjacent intervals do not overlap
d = """chrom start end
0 chr1 3 6
1 chr1 6 10
2 chr2 5 10"""
df = pd.read_csv(StringIO(d), sep=r"\s+")
assert is_overlapping(df) is False
def test_is_covering():
### test is_covering where an interval from df completely overlaps
### two different regions from view
df1 = pd.DataFrame(
[
["chr1", -5, 25],
],
columns=["chrom", "start", "end"],
)
chromsizes = [("chr1", 0, 9, "chr1p"), ("chr1", 11, 20, "chr1q")]
assert is_covering(df1, chromsizes) is True
### test is_covering where two intervals from df overlap
### two different regions from view
df1 = pd.DataFrame(
[
["chr1", -5, 10],
["chr1", 11, 12],
["chr1", 12, 20],
],
columns=["chrom", "start", "end"],
)
chromsizes = [("chr1", 0, 9, "chr1p"), ("chr1", 11, 20, "chr1q")]
assert is_covering(df1, chromsizes) is True
### test is_covering where two intervals from df overlap
### two different regions from view
df1 = pd.DataFrame(
[
["chr1", -5, 10, "chr1q"],
["chr1", 11, 12, "chr1q"],
["chr1", 12, 20, "chr1q"],
],
columns=["chrom", "start", "end", "view_region"],
)
chromsizes = [("chr1", 0, 9, "chr1p"), ("chr1", 11, 20, "chr1q")]
assert is_covering(df1, chromsizes) is True
def test_is_tiling():
### view region chr1p is tiled by one interval, chr1q is tiled by two
df1 = pd.DataFrame(
[
["chr1", 0, 9, "chr1p"],
["chr1", 11, 12, "chr1q"],
["chr1", 12, 20, "chr1q"],
],
columns=["chrom", "start", "end", "view_region"],
)
chromsizes = [("chr1", 0, 9, "chr1p"), ("chr1", 11, 20, "chr1q")]
assert is_tiling(df1, chromsizes) is True
### not tiling, since (chr1,0,9) is associated with chr1q
df1 = pd.DataFrame(
[
["chr1", 0, 9, "chr1q"],
["chr1", 11, 12, "chr1q"],
["chr1", 12, 20, "chr1q"],
],
columns=["chrom", "start", "end", "view_region"],
)
chromsizes = [("chr1", 0, 9, "chr1p"), ("chr1", 11, 20, "chr1q")]
assert is_tiling(df1, chromsizes) is False
### not tiling, contains overlaps
df1 = pd.DataFrame(
[
["chr1", 0, 9, "chr1p"],
["chr1", 11, 13, "chr1q"],
["chr1", 12, 20, "chr1q"],
],
columns=["chrom", "start", "end", "view_region"],
)
chromsizes = [("chr1", 0, 9, "chr1p"), ("chr1", 11, 20, "chr1q")]
assert is_tiling(df1, chromsizes) is False
### not tiling, since it doesn't cover
df1 = pd.DataFrame(
[
["chr1", 11, 12, "chr1q"],
["chr1", 12, 20, "chr1q"],
],
columns=["chrom", "start", "end", "view_region"],
)
chromsizes = [("chr1", 0, 9, "chr1p"), ("chr1", 11, 20, "chr1q")]
assert is_tiling(df1, chromsizes) is False
def test_is_bedframe():
##missing a column
df1 = pd.DataFrame(
[
["chr1", 11],
["chr1", 12],
],
columns=["chrom", "start"],
)
assert is_bedframe(df1) is False
### end column has invalid dtype
df1 = pd.DataFrame(
[
["chr1", 10, "20"],
["chr1", 10, "12"],
],
columns=["chrom", "start", "end"],
)
assert is_bedframe(df1) is False
### second interval start > ends.
df1 = pd.DataFrame(
[
["chr1", 10, 20],
["chr1", 15, 10],
],
columns=["chrom", "start", "end"],
)
assert is_bedframe(df1) is False
### third interval has a null in one column
df1 = pd.DataFrame(
[
["chr1", 10, 20, "first"],
["chr1", 10, 15, "second"],
["chr1", pd.NA, 15, "third"],
],
columns=["chrom", "start", "end", "name"],
)
# should raise a TypeError if the second column is an object
with pytest.raises(TypeError):
is_bedframe(df1, raise_errors=True)
# should raise a ValueError after recasting to pd.Int64Dtype
df1 = df1.astype({"start": pd.Int64Dtype(), "end": pd.Int64Dtype()})
with pytest.raises(ValueError):
is_bedframe(df1, raise_errors=True)
### first interval is completely NA
df1 = pd.DataFrame(
[
[pd.NA, pd.NA, pd.NA, "first"],
["chr1", 10, 15, "second"],
["chr1", 10, 15, "third"],
],
columns=["chrom", "start", "end", "name"],
)
df1 = df1.astype({"start": pd.Int64Dtype(), "end": pd.Int64Dtype()})
assert is_bedframe(df1) is True
def test_is_viewframe():
# not a bedframe
df1 = pd.DataFrame(
[
["chr1", 10, 20, "chr1p"],
["chr1", 15, 10, "chr1q"],
],
columns=["chrom", "start", "end", "name"],
)
assert is_viewframe(df1) is False
# no column for region name
df1 = pd.DataFrame(
[
["chr1", 10, 20],
["chr1", 30, 40],
],
columns=["chrom", "start", "end"],
)
assert is_viewframe(df1) is False
# contains null values
df1 = pd.DataFrame(
[
["chr1", 10, 20, "chr1p"],
["chr1", pd.NA, np.nan, "chr1q"],
],
columns=["chrom", "start", "end", "name"],
)
assert is_viewframe(df1) is False
# overlapping intervals
df1 = pd.DataFrame(
[
["chr1", 10, 20, "chr1p"],
["chr1", 15, 25, "chr1q"],
],
columns=["chrom", "start", "end", "name"],
)
assert is_viewframe(df1) is False
# valid view
df1 = pd.DataFrame(
[
["chr1", 10, 20, "chr1p"],
["chr1", 20, 25, "chr1q"],
["chr2", 20, 25, "chrTEST_2p"],
],
columns=["chrom", "start", "end", "name"],
)
assert is_viewframe(df1) is True
def test_is_sorted():
view_df = pd.DataFrame(
[
["chrX", 1, 8, "oranges"],
["chrX", 8, 20, "grapefruit"],
["chr1", 0, 10, "apples"],
],
columns=["chrom", "start", "end", "fruit"],
)
df_view_cat = pd.CategoricalDtype(
categories=["oranges", "grapefruit", "apples"], ordered=True
)
view_df = view_df.astype({"fruit": df_view_cat})
assert is_sorted(
view_df, view_df=view_df, view_name_col="fruit", df_view_col="fruit"
)
df = pd.DataFrame(
[
["chr1", 0, 10, "+"],
["chrX", 5, 10, "+"],
["chrX", 0, 5, "+"],
["chr2", 5, 10, "+"],
],
columns=["chrom", "start", "end", "strand"],
)
assert not is_sorted(df)
bfs = sort_bedframe(df, view_df=view_df, view_name_col="fruit")
assert is_sorted(bfs, view_df=view_df, view_name_col="fruit")
# view_df specifies a different ordering, so should not be sorted
assert not is_sorted(bfs)
|
