|
a |
|
b/tests/test_countTable.py |
|
|
1 |
#!/usr/bin/env python3 |
|
|
2 |
# -*- coding: utf-8 -*- |
|
|
3 |
import unittest |
|
|
4 |
from types import SimpleNamespace |
|
|
5 |
import singlecellmultiomics.bamProcessing.bamToCountTable |
|
|
6 |
|
|
|
7 |
from singlecellmultiomics.bamProcessing.bamBinCounts import range_contains_overlap,blacklisted_binning |
|
|
8 |
|
|
|
9 |
class TestIterables(unittest.TestCase): |
|
|
10 |
|
|
|
11 |
def test_blacklisted_binning(self): |
|
|
12 |
bin_size = 250 |
|
|
13 |
blacklist = [(450,1001),(1007,1019),(1550,1600),(2300,2510)] |
|
|
14 |
blacklist = sorted(blacklist) |
|
|
15 |
|
|
|
16 |
self.assertFalse( |
|
|
17 |
range_contains_overlap( list( blacklisted_binning(0,2000,bin_size,blacklist) ) + blacklist) |
|
|
18 |
) |
|
|
19 |
|
|
|
20 |
|
|
|
21 |
|
|
|
22 |
class TestCountTable(unittest.TestCase): |
|
|
23 |
|
|
|
24 |
def test_total_read_counting(self): |
|
|
25 |
""" Test if the amount of raw reads in a bam file is counted properly """ |
|
|
26 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
27 |
SimpleNamespace( |
|
|
28 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
29 |
head=None, |
|
|
30 |
o=None, |
|
|
31 |
bin=None, |
|
|
32 |
binTag='DS', |
|
|
33 |
sliding=None, |
|
|
34 |
bedfile=None, |
|
|
35 |
showtags=False, |
|
|
36 |
featureTags=None, |
|
|
37 |
joinedFeatureTags='reference_name', |
|
|
38 |
byValue=None, |
|
|
39 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
40 |
minMQ=0, |
|
|
41 |
filterXA=False, |
|
|
42 |
dedup=False, |
|
|
43 |
divideMultimapping=False, |
|
|
44 |
doNotDivideFragments=True, |
|
|
45 |
contig=None, |
|
|
46 |
blacklist=None, |
|
|
47 |
r1only=False, |
|
|
48 |
r2only=False, |
|
|
49 |
filterMP=False, |
|
|
50 |
splitFeatures=False, |
|
|
51 |
feature_delimiter=',', |
|
|
52 |
noNames=False) , return_df=True) |
|
|
53 |
# !samtools idxstats ./data/mini_nla_test.bam | head -n 1 | cut -f 3 |
|
|
54 |
self.assertEqual(df.loc['chr1'].sum(),563) |
|
|
55 |
|
|
|
56 |
|
|
|
57 |
def test_total_read1_counting(self): |
|
|
58 |
""" Test if the amount of valid deduped R1 reads in a bam file is counted properly |
|
|
59 |
samtools view ./data/mini_nla_test.bam -f 64 -F 3840 | grep DS | wc -l : 210 |
|
|
60 |
""" |
|
|
61 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
62 |
SimpleNamespace( |
|
|
63 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
64 |
head=None, |
|
|
65 |
o=None, |
|
|
66 |
bin=None, |
|
|
67 |
binTag='DS', |
|
|
68 |
sliding=None, |
|
|
69 |
bedfile=None, |
|
|
70 |
showtags=False, |
|
|
71 |
featureTags=None, |
|
|
72 |
joinedFeatureTags='reference_name', |
|
|
73 |
byValue=None, |
|
|
74 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
75 |
minMQ=0, |
|
|
76 |
filterXA=False, |
|
|
77 |
dedup=True, |
|
|
78 |
divideMultimapping=False, |
|
|
79 |
doNotDivideFragments=True, |
|
|
80 |
contig=None, |
|
|
81 |
blacklist=None, |
|
|
82 |
r1only=True, |
|
|
83 |
r2only=False, |
|
|
84 |
filterMP=False, |
|
|
85 |
splitFeatures=False, |
|
|
86 |
feature_delimiter=',', |
|
|
87 |
noNames=False) , return_df=True) |
|
|
88 |
# !samtools idxstats ./data/mini_nla_test.bam | head -n 1 | cut -f 3 |
|
|
89 |
self.assertEqual(df.loc['chr1'].sum(),210) |
|
|
90 |
|
|
|
91 |
|
|
|
92 |
|
|
|
93 |
def test_contig_selection(self): |
|
|
94 |
""" Test if a contig is selected properly""" |
|
|
95 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
96 |
SimpleNamespace( |
|
|
97 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
98 |
head=None, |
|
|
99 |
o=None, |
|
|
100 |
bin=None, |
|
|
101 |
binTag='DS', |
|
|
102 |
sliding=None, |
|
|
103 |
bedfile=None, |
|
|
104 |
showtags=False, |
|
|
105 |
featureTags=None, |
|
|
106 |
joinedFeatureTags='reference_name', |
|
|
107 |
byValue=None, |
|
|
108 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
109 |
contig='chr5', |
|
|
110 |
minMQ=0, |
|
|
111 |
filterXA=False, |
|
|
112 |
dedup=False, |
|
|
113 |
r1only=False, |
|
|
114 |
r2only=False, |
|
|
115 |
divideMultimapping=False, |
|
|
116 |
doNotDivideFragments=True, |
|
|
117 |
splitFeatures=False, |
|
|
118 |
blacklist=None, |
|
|
119 |
filterMP=False, |
|
|
120 |
feature_delimiter=',', |
|
|
121 |
noNames=False) , return_df=True) |
|
|
122 |
# !samtools idxstats ./data/mini_nla_test.bam | head -n 1 | cut -f 3 |
|
|
123 |
self.assertEqual(df.sum().sum(),0) |
|
|
124 |
|
|
|
125 |
def test_total_molecule_counting(self): |
|
|
126 |
""" Test if the amount of molecules in a bam file is counted properly """ |
|
|
127 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
128 |
SimpleNamespace( |
|
|
129 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
130 |
o=None, |
|
|
131 |
head=None, |
|
|
132 |
bin=None, |
|
|
133 |
binTag='DS', |
|
|
134 |
byValue=None, |
|
|
135 |
sliding=None, |
|
|
136 |
bedfile=None, |
|
|
137 |
showtags=False, |
|
|
138 |
featureTags=None, |
|
|
139 |
joinedFeatureTags='reference_name', |
|
|
140 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
141 |
minMQ=0, |
|
|
142 |
filterXA=False, |
|
|
143 |
dedup=True, |
|
|
144 |
divideMultimapping=False, |
|
|
145 |
doNotDivideFragments=True, |
|
|
146 |
contig=None, |
|
|
147 |
r1only=False, |
|
|
148 |
r2only=False, |
|
|
149 |
blacklist=None, |
|
|
150 |
filterMP=False, |
|
|
151 |
splitFeatures=False, |
|
|
152 |
feature_delimiter=',', |
|
|
153 |
noNames=False) , return_df=True) |
|
|
154 |
# !samtools view ./singlecellmultiomics/data/mini_nla_test.bam | grep 'RC:i:1' | wc -l |
|
|
155 |
self.assertEqual(df.loc['chr1'].sum(),383) |
|
|
156 |
|
|
|
157 |
def test_singleFeatureTags_molecule_counting(self): |
|
|
158 |
""" Test if the single feature counting feature works """ |
|
|
159 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
160 |
SimpleNamespace( |
|
|
161 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
162 |
o=None, |
|
|
163 |
head=None, |
|
|
164 |
bin=None, |
|
|
165 |
sliding=None, |
|
|
166 |
binTag=None, |
|
|
167 |
byValue=None, |
|
|
168 |
bedfile=None, |
|
|
169 |
showtags=False, |
|
|
170 |
featureTags='reference_name,RC', |
|
|
171 |
joinedFeatureTags=None, |
|
|
172 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
173 |
minMQ=0, |
|
|
174 |
filterXA=False, |
|
|
175 |
dedup=False, |
|
|
176 |
divideMultimapping=False, |
|
|
177 |
contig=None, |
|
|
178 |
r1only=False, |
|
|
179 |
r2only=False, |
|
|
180 |
keepOverBounds=False, |
|
|
181 |
doNotDivideFragments=True, |
|
|
182 |
blacklist=None, |
|
|
183 |
filterMP=False, |
|
|
184 |
splitFeatures=False, |
|
|
185 |
feature_delimiter=',', |
|
|
186 |
noNames=False) , return_df=True) |
|
|
187 |
# !samtools view ./singlecellmultiomics/data/mini_nla_test.bam | grep 'RC:i:1' | wc -l |
|
|
188 |
self.assertEqual(df.loc['chr1'].sum(),563) |
|
|
189 |
self.assertEqual(df.loc['1'].sum(),383) |
|
|
190 |
|
|
|
191 |
# Amount of RC:2 obs: |
|
|
192 |
self.assertEqual(df.loc['2'].sum(),97) |
|
|
193 |
|
|
|
194 |
|
|
|
195 |
def test_singleFeatureTags_molecule_counting_contig(self): |
|
|
196 |
""" Test if the single feature counting feature works with -contig """ |
|
|
197 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
198 |
SimpleNamespace( |
|
|
199 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
200 |
o=None, |
|
|
201 |
head=None, |
|
|
202 |
bin=None, |
|
|
203 |
sliding=None, |
|
|
204 |
binTag=None, |
|
|
205 |
byValue=None, |
|
|
206 |
bedfile=None, |
|
|
207 |
showtags=False, |
|
|
208 |
featureTags='reference_name,RC', |
|
|
209 |
joinedFeatureTags=None, |
|
|
210 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
211 |
minMQ=0, |
|
|
212 |
filterXA=False, |
|
|
213 |
dedup=False, |
|
|
214 |
divideMultimapping=False, |
|
|
215 |
contig='chr1', |
|
|
216 |
r1only=False, |
|
|
217 |
r2only=False, |
|
|
218 |
keepOverBounds=False, |
|
|
219 |
doNotDivideFragments=True, |
|
|
220 |
blacklist=None, |
|
|
221 |
filterMP=False, |
|
|
222 |
splitFeatures=False, |
|
|
223 |
feature_delimiter=',', |
|
|
224 |
noNames=False) , return_df=True) |
|
|
225 |
# !samtools view ./singlecellmultiomics/data/mini_nla_test.bam | grep 'RC:i:1' | wc -l |
|
|
226 |
self.assertEqual(df.loc['chr1'].sum(),563) |
|
|
227 |
self.assertEqual(df.loc['1'].sum(),383) |
|
|
228 |
|
|
|
229 |
# Amount of RC:2 obs: |
|
|
230 |
self.assertEqual(df.loc['2'].sum(),97) |
|
|
231 |
|
|
|
232 |
|
|
|
233 |
|
|
|
234 |
|
|
|
235 |
def test_bed_counting(self): |
|
|
236 |
""" Test if the bed feature counting feature works """ |
|
|
237 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
238 |
SimpleNamespace( |
|
|
239 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
240 |
o=None, |
|
|
241 |
head=None, |
|
|
242 |
bin=None, |
|
|
243 |
binTag='DS', |
|
|
244 |
byValue=None, |
|
|
245 |
sliding=None, |
|
|
246 |
bedfile='./data/mini_test.bed', |
|
|
247 |
showtags=False, |
|
|
248 |
featureTags=None, |
|
|
249 |
joinedFeatureTags='reference_name', |
|
|
250 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
251 |
minMQ=0, |
|
|
252 |
filterXA=False, |
|
|
253 |
dedup=True, |
|
|
254 |
divideMultimapping=False, |
|
|
255 |
doNotDivideFragments=True, |
|
|
256 |
contig=None, |
|
|
257 |
r1only=False, |
|
|
258 |
r2only=False, |
|
|
259 |
blacklist=None, |
|
|
260 |
filterMP=False, |
|
|
261 |
splitFeatures=False, |
|
|
262 |
feature_delimiter=',', |
|
|
263 |
noNames=False) , return_df=True) |
|
|
264 |
# !samtools view ./singlecellmultiomics/data/mini_nla_test.bam | grep 'RC:i:1' | wc -l |
|
|
265 |
self.assertEqual( df.xs( 'test4',level='bname', drop_level=False).iloc[0].sum() , 1) |
|
|
266 |
self.assertEqual( df.xs( 'test3',level='bname', drop_level=False).iloc[0].sum() , 383) |
|
|
267 |
|
|
|
268 |
def test_byValue(self): |
|
|
269 |
""" Test if the by value counting feature works, this counts the value of a feature instead of its presence""" |
|
|
270 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
271 |
SimpleNamespace( |
|
|
272 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
273 |
o=None, |
|
|
274 |
head=None, |
|
|
275 |
bin=30, |
|
|
276 |
sliding=None, |
|
|
277 |
binTag='DS', |
|
|
278 |
byValue='RC', |
|
|
279 |
bedfile=None, |
|
|
280 |
showtags=False, |
|
|
281 |
featureTags=None, |
|
|
282 |
joinedFeatureTags='reference_name,RC', |
|
|
283 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
284 |
minMQ=0, |
|
|
285 |
filterXA=False, |
|
|
286 |
dedup=False, |
|
|
287 |
divideMultimapping=False, |
|
|
288 |
contig=None, |
|
|
289 |
blacklist=None, |
|
|
290 |
r1only=False, |
|
|
291 |
r2only=False, |
|
|
292 |
filterMP=False, |
|
|
293 |
keepOverBounds=False, |
|
|
294 |
doNotDivideFragments=True, |
|
|
295 |
splitFeatures=False, |
|
|
296 |
feature_delimiter=',', |
|
|
297 |
noNames=False) , return_df=True) |
|
|
298 |
|
|
|
299 |
self.assertEqual( df.sum(1).sum(), 765 ) |
|
|
300 |
self.assertEqual( df.loc[:,['A3-P15-1-1_25']].sum(skipna=True).sum(skipna=True), 12.0 ) |
|
|
301 |
|
|
|
302 |
|
|
|
303 |
def test_byValue_binned_autofill_joined(self): |
|
|
304 |
""" Test if the by value counting feature works, this counts the value of a feature instead of its presence""" |
|
|
305 |
df = singlecellmultiomics.bamProcessing.bamToCountTable.create_count_table( |
|
|
306 |
SimpleNamespace( |
|
|
307 |
alignmentfiles=['./data/mini_nla_test.bam'], |
|
|
308 |
o=None, |
|
|
309 |
head=None, |
|
|
310 |
bin=30, |
|
|
311 |
sliding=None, |
|
|
312 |
binTag='DS', |
|
|
313 |
byValue='RC', |
|
|
314 |
bedfile=None, |
|
|
315 |
showtags=False, |
|
|
316 |
featureTags=None, |
|
|
317 |
joinedFeatureTags='reference_name,RC', |
|
|
318 |
sampleTags='SM', proper_pairs_only=False, no_indels=False, max_base_edits=None, no_softclips=False, |
|
|
319 |
minMQ=0, |
|
|
320 |
filterXA=False, |
|
|
321 |
dedup=False, |
|
|
322 |
divideMultimapping=False, |
|
|
323 |
contig=None, |
|
|
324 |
blacklist=None, |
|
|
325 |
r1only=False, |
|
|
326 |
r2only=False, |
|
|
327 |
filterMP=False, |
|
|
328 |
keepOverBounds=False, |
|
|
329 |
doNotDivideFragments=True, |
|
|
330 |
splitFeatures=False, |
|
|
331 |
feature_delimiter=',', |
|
|
332 |
noNames=False) , return_df=True) |
|
|
333 |
|
|
|
334 |
self.assertEqual( df.sum(1).sum(), 765 ) |
|
|
335 |
self.assertEqual( df.loc[:,['A3-P15-1-1_25']].sum(skipna=True).sum(skipna=True), 12.0 ) |
|
|
336 |
|
|
|
337 |
|
|
|
338 |
|
|
|
339 |
|
|
|
340 |
if __name__ == '__main__': |
|
|
341 |
unittest.main() |