varsim 1.0.5__py3-none-any.whl → 1.0.7__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- varsim/__init__.py +16 -424
- varsim/core.py +432 -0
- {varsim-1.0.5.dist-info → varsim-1.0.7.dist-info}/METADATA +1 -1
- varsim-1.0.7.dist-info/RECORD +7 -0
- varsim-1.0.5.dist-info/RECORD +0 -6
- {varsim-1.0.5.dist-info → varsim-1.0.7.dist-info}/WHEEL +0 -0
- {varsim-1.0.5.dist-info → varsim-1.0.7.dist-info}/licenses/LICENSE +0 -0
- {varsim-1.0.5.dist-info → varsim-1.0.7.dist-info}/top_level.txt +0 -0
varsim/__init__.py
CHANGED
|
@@ -1,433 +1,25 @@
|
|
|
1
|
-
import
|
|
2
|
-
|
|
3
|
-
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
1
|
+
from .core import (
|
|
2
|
+
cds,
|
|
3
|
+
utr5,
|
|
4
|
+
utr3,
|
|
5
|
+
splicing,
|
|
6
|
+
inframe_del,
|
|
7
|
+
inframe_dup,
|
|
8
|
+
frameshift_del,
|
|
9
|
+
frameshift_dup,
|
|
10
|
+
aa_sub,
|
|
11
|
+
missense,
|
|
10
12
|
)
|
|
11
|
-
from Bio.Seq import Seq
|
|
12
|
-
from Bio.SeqFeature import SimpleLocation
|
|
13
|
-
from Bio.SeqUtils import seq3
|
|
14
|
-
|
|
15
|
-
Entrez.email = os.environ["EMAIL"]
|
|
16
|
-
Entrez.api_key = os.environ["API_KEY"]
|
|
17
|
-
codons = standard_dna_table.forward_table.keys()
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
def cds(gene: str) -> list:
|
|
21
|
-
variants = []
|
|
22
|
-
stream = Entrez.esearch(
|
|
23
|
-
db="nucleotide",
|
|
24
|
-
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
25
|
-
)
|
|
26
|
-
record = Entrez.read(stream)
|
|
27
|
-
stream = Entrez.efetch(
|
|
28
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
29
|
-
)
|
|
30
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
31
|
-
for feature in seqrecord.features:
|
|
32
|
-
if feature.type == "CDS":
|
|
33
|
-
protein = "".join(feature.qualifiers.get("translation"))
|
|
34
|
-
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
35
|
-
cds = feature.extract(seqrecord).seq
|
|
36
|
-
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
37
|
-
for base in unambiguous_dna_letters:
|
|
38
|
-
if base != cds[codon]:
|
|
39
|
-
seq = Seq(base) + cds[codon + 1 : codon + 3]
|
|
40
|
-
if protein[index] != seq.translate():
|
|
41
|
-
variants.append(
|
|
42
|
-
(
|
|
43
|
-
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
|
|
44
|
-
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
45
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
46
|
-
)
|
|
47
|
-
)
|
|
48
|
-
else:
|
|
49
|
-
variants.append(
|
|
50
|
-
(
|
|
51
|
-
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
|
|
52
|
-
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
53
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
54
|
-
)
|
|
55
|
-
)
|
|
56
|
-
if base != cds[codon + 1]:
|
|
57
|
-
seq = cds[codon] + Seq(base) + cds[codon + 2]
|
|
58
|
-
if protein[index] != seq.translate():
|
|
59
|
-
variants.append(
|
|
60
|
-
(
|
|
61
|
-
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
|
|
62
|
-
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
63
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
64
|
-
)
|
|
65
|
-
)
|
|
66
|
-
else:
|
|
67
|
-
variants.append(
|
|
68
|
-
(
|
|
69
|
-
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
|
|
70
|
-
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
71
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
72
|
-
)
|
|
73
|
-
)
|
|
74
|
-
if base != cds[codon + 2]:
|
|
75
|
-
seq = cds[codon : codon + 2] + Seq(base)
|
|
76
|
-
if protein[index] != seq.translate():
|
|
77
|
-
variants.append(
|
|
78
|
-
(
|
|
79
|
-
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
|
|
80
|
-
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
81
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
82
|
-
)
|
|
83
|
-
)
|
|
84
|
-
else:
|
|
85
|
-
variants.append(
|
|
86
|
-
(
|
|
87
|
-
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
|
|
88
|
-
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
89
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
90
|
-
)
|
|
91
|
-
)
|
|
92
|
-
return variants
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
def utr5(gene: str) -> list:
|
|
96
|
-
variants = []
|
|
97
|
-
stream = Entrez.esearch(
|
|
98
|
-
db="nucleotide",
|
|
99
|
-
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
100
|
-
)
|
|
101
|
-
record = Entrez.read(stream)
|
|
102
|
-
stream = Entrez.efetch(
|
|
103
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
104
|
-
)
|
|
105
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
106
|
-
for feature in seqrecord.features:
|
|
107
|
-
if feature.type == "CDS":
|
|
108
|
-
utr5 = SimpleLocation(0, feature.location.start).extract(seqrecord).seq
|
|
109
|
-
for index in range(len(utr5)):
|
|
110
|
-
for base in unambiguous_dna_letters:
|
|
111
|
-
if base != utr5[index]:
|
|
112
|
-
variants.append(
|
|
113
|
-
(
|
|
114
|
-
f"{seqrecord.id}:c.{index - len(utr5)}{utr5[index]}>{base}",
|
|
115
|
-
"",
|
|
116
|
-
"",
|
|
117
|
-
)
|
|
118
|
-
)
|
|
119
|
-
return variants
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
def utr3(gene: str) -> list:
|
|
123
|
-
variants = []
|
|
124
|
-
stream = Entrez.esearch(
|
|
125
|
-
db="nucleotide",
|
|
126
|
-
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
127
|
-
)
|
|
128
|
-
record = Entrez.read(stream)
|
|
129
|
-
stream = Entrez.efetch(
|
|
130
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
131
|
-
)
|
|
132
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
133
|
-
for feature in seqrecord.features:
|
|
134
|
-
if feature.type == "CDS":
|
|
135
|
-
utr3 = (
|
|
136
|
-
SimpleLocation(feature.location.end, len(seqrecord))
|
|
137
|
-
.extract(seqrecord)
|
|
138
|
-
.seq
|
|
139
|
-
)
|
|
140
|
-
for index in range(len(utr3)):
|
|
141
|
-
for base in unambiguous_dna_letters:
|
|
142
|
-
if base != utr3[index]:
|
|
143
|
-
variants.append(
|
|
144
|
-
(
|
|
145
|
-
f"{seqrecord.id}:c.*{index + 1}{utr3[index]}>{base}",
|
|
146
|
-
"",
|
|
147
|
-
"",
|
|
148
|
-
)
|
|
149
|
-
)
|
|
150
|
-
return variants
|
|
151
|
-
|
|
152
|
-
|
|
153
|
-
def splicing(gene: str) -> list:
|
|
154
|
-
variants = []
|
|
155
|
-
exon = []
|
|
156
|
-
stream = Entrez.esearch(
|
|
157
|
-
db="nucleotide", term=f'{gene}[Gene Name] "mane select"[Keyword]'
|
|
158
|
-
)
|
|
159
|
-
record = Entrez.read(stream)
|
|
160
|
-
|
|
161
|
-
stream = Entrez.efetch(
|
|
162
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
163
|
-
)
|
|
164
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
165
|
-
splicing = []
|
|
166
|
-
variants = []
|
|
167
|
-
start = 0
|
|
168
|
-
end = 0
|
|
169
|
-
for feature in seqrecord.features:
|
|
170
|
-
if feature.type == "CDS":
|
|
171
|
-
start = feature.location.start
|
|
172
|
-
end = feature.location.end
|
|
173
|
-
for feature in seqrecord.features:
|
|
174
|
-
if feature.type == "exon":
|
|
175
|
-
if feature.location.start < start and feature.location.end < start:
|
|
176
|
-
splicing.extend(
|
|
177
|
-
(
|
|
178
|
-
feature.location.start - start - 1,
|
|
179
|
-
feature.location.end - start - 1,
|
|
180
|
-
)
|
|
181
|
-
)
|
|
182
|
-
elif feature.location.start < start and feature.location.end > start:
|
|
183
|
-
splicing.extend(
|
|
184
|
-
(feature.location.start - start - 1, feature.location.end - start)
|
|
185
|
-
)
|
|
186
|
-
else:
|
|
187
|
-
splicing.extend(
|
|
188
|
-
(feature.location.start - start, feature.location.end - start)
|
|
189
|
-
)
|
|
190
|
-
|
|
191
|
-
for coordinate in range(1, len(splicing) - 1, 2):
|
|
192
|
-
site = splicing[coordinate], splicing[coordinate] + 1
|
|
193
|
-
for base in unambiguous_dna_letters:
|
|
194
|
-
if base != "G":
|
|
195
|
-
variants.append((f"{seqrecord.id}:c.{site[0]}+1G>{base}"))
|
|
196
|
-
if base != "T":
|
|
197
|
-
variants.append((f"{seqrecord.id}:c.{site[0]}+2T>{base}"))
|
|
198
|
-
if base != "A":
|
|
199
|
-
variants.append((f"{seqrecord.id}:c.{site[1]}-2A>{base}"))
|
|
200
|
-
if base != "G":
|
|
201
|
-
variants.append((f"{seqrecord.id}:c.{site[1]}-1G>{base}"))
|
|
202
|
-
return variants
|
|
203
|
-
|
|
204
|
-
|
|
205
|
-
def aa_sub(gene: str) -> list:
|
|
206
|
-
variants = []
|
|
207
|
-
term = f'{gene}[Gene Name] AND "mane select"[keyword]'
|
|
208
|
-
stream = Entrez.esearch(db="protein", term=term)
|
|
209
|
-
record = Entrez.read(stream)
|
|
210
|
-
|
|
211
|
-
stream = Entrez.efetch(
|
|
212
|
-
db="protein", rettype="gp", retmode="text", id=record["IdList"]
|
|
213
|
-
)
|
|
214
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
215
|
-
for index, residue in enumerate(seqrecord.seq, 1):
|
|
216
|
-
for aa in protein_letters:
|
|
217
|
-
if aa != residue:
|
|
218
|
-
variants.append(
|
|
219
|
-
(
|
|
220
|
-
f"{seqrecord.id}:p.{residue}{index}{aa}",
|
|
221
|
-
f"{seqrecord.id}:p.{protein_letters_1to3[residue]}{index}{protein_letters_1to3[aa]}",
|
|
222
|
-
)
|
|
223
|
-
)
|
|
224
|
-
return variants
|
|
225
|
-
|
|
226
|
-
|
|
227
|
-
def missense(gene: str) -> list:
|
|
228
|
-
variants = []
|
|
229
|
-
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
230
|
-
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
231
|
-
record = Entrez.read(stream)
|
|
232
|
-
stream = Entrez.efetch(
|
|
233
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
234
|
-
)
|
|
235
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
236
|
-
for feature in seqrecord.features:
|
|
237
|
-
if feature.type == "CDS":
|
|
238
|
-
protein = "".join(feature.qualifiers.get("translation"))
|
|
239
|
-
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
240
|
-
cds = feature.location.extract(seqrecord).seq
|
|
241
|
-
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
242
|
-
for base in codons:
|
|
243
|
-
if base != cds[codon : codon + 3]:
|
|
244
|
-
seq = Seq(base)
|
|
245
|
-
if protein[index] != seq.translate():
|
|
246
|
-
if (
|
|
247
|
-
base[0] == cds[codon]
|
|
248
|
-
and base[1] == cds[codon + 1]
|
|
249
|
-
and base[2] != cds[codon + 2]
|
|
250
|
-
):
|
|
251
|
-
variants.append(
|
|
252
|
-
(
|
|
253
|
-
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
|
|
254
|
-
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
255
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
256
|
-
)
|
|
257
|
-
)
|
|
258
|
-
elif (
|
|
259
|
-
base[0] == cds[codon]
|
|
260
|
-
and base[1] != cds[codon + 1]
|
|
261
|
-
and base[2] == cds[codon + 2]
|
|
262
|
-
):
|
|
263
|
-
variants.append(
|
|
264
|
-
(
|
|
265
|
-
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
|
|
266
|
-
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
267
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
268
|
-
)
|
|
269
|
-
)
|
|
270
|
-
elif (
|
|
271
|
-
base[0] != cds[codon]
|
|
272
|
-
and base[1] == cds[codon + 1]
|
|
273
|
-
and base[2] == cds[codon + 2]
|
|
274
|
-
):
|
|
275
|
-
variants.append(
|
|
276
|
-
(
|
|
277
|
-
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
|
|
278
|
-
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
279
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
280
|
-
)
|
|
281
|
-
)
|
|
282
|
-
else:
|
|
283
|
-
variants.append(
|
|
284
|
-
(
|
|
285
|
-
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}>{base}",
|
|
286
|
-
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
287
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
288
|
-
)
|
|
289
|
-
)
|
|
290
|
-
else:
|
|
291
|
-
if (
|
|
292
|
-
base[0] == cds[codon]
|
|
293
|
-
and base[1] == cds[codon + 1]
|
|
294
|
-
and base[2] != cds[codon + 2]
|
|
295
|
-
):
|
|
296
|
-
variants.append(
|
|
297
|
-
(
|
|
298
|
-
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
|
|
299
|
-
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
300
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
301
|
-
)
|
|
302
|
-
)
|
|
303
|
-
elif (
|
|
304
|
-
base[0] == cds[codon]
|
|
305
|
-
and base[1] != cds[codon + 1]
|
|
306
|
-
and base[2] == cds[codon + 2]
|
|
307
|
-
):
|
|
308
|
-
variants.append(
|
|
309
|
-
(
|
|
310
|
-
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
|
|
311
|
-
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
312
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
313
|
-
)
|
|
314
|
-
)
|
|
315
|
-
elif (
|
|
316
|
-
base[0] != cds[codon]
|
|
317
|
-
and base[1] == cds[codon + 1]
|
|
318
|
-
and base[2] == cds[codon + 2]
|
|
319
|
-
):
|
|
320
|
-
variants.append(
|
|
321
|
-
(
|
|
322
|
-
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
|
|
323
|
-
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
324
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
325
|
-
)
|
|
326
|
-
)
|
|
327
|
-
else:
|
|
328
|
-
variants.append(
|
|
329
|
-
(
|
|
330
|
-
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}>{base}",
|
|
331
|
-
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
332
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
333
|
-
)
|
|
334
|
-
)
|
|
335
|
-
return variants
|
|
336
|
-
|
|
337
|
-
|
|
338
|
-
def inframe_del(gene: str) -> list:
|
|
339
|
-
variants = []
|
|
340
|
-
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
341
|
-
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
342
|
-
record = Entrez.read(stream)
|
|
343
|
-
stream = Entrez.efetch(
|
|
344
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
345
|
-
)
|
|
346
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
347
|
-
for feature in seqrecord.features:
|
|
348
|
-
if feature.type == "CDS":
|
|
349
|
-
protein = "".join(feature.qualifiers.get("translation"))
|
|
350
|
-
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
351
|
-
cds = feature.location.extract(seqrecord).seq
|
|
352
|
-
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
353
|
-
variants.append(
|
|
354
|
-
(
|
|
355
|
-
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}del",
|
|
356
|
-
f"{protein_id}:p.{protein[index]}{index + 1}del",
|
|
357
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}del",
|
|
358
|
-
)
|
|
359
|
-
)
|
|
360
|
-
return variants
|
|
361
|
-
|
|
362
|
-
|
|
363
|
-
def inframe_dup(gene: str) -> list:
|
|
364
|
-
variants = []
|
|
365
|
-
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
366
|
-
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
367
|
-
record = Entrez.read(stream)
|
|
368
|
-
stream = Entrez.efetch(
|
|
369
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
370
|
-
)
|
|
371
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
372
|
-
for feature in seqrecord.features:
|
|
373
|
-
if feature.type == "CDS":
|
|
374
|
-
protein = "".join(feature.qualifiers.get("translation"))
|
|
375
|
-
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
376
|
-
cds = feature.location.extract(seqrecord).seq
|
|
377
|
-
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
378
|
-
variants.append(
|
|
379
|
-
(
|
|
380
|
-
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}dup",
|
|
381
|
-
f"{protein_id}:p.{protein[index]}{index + 1}dup",
|
|
382
|
-
f"{protein_id}:p.{seq3(protein[index])}{index + 1}dup",
|
|
383
|
-
)
|
|
384
|
-
)
|
|
385
|
-
return variants
|
|
386
|
-
|
|
387
|
-
|
|
388
|
-
def frameshift_dup(gene: str) -> list:
|
|
389
|
-
variants = []
|
|
390
|
-
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
391
|
-
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
392
|
-
record = Entrez.read(stream)
|
|
393
|
-
stream = Entrez.efetch(
|
|
394
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
395
|
-
)
|
|
396
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
397
|
-
for feature in seqrecord.features:
|
|
398
|
-
if feature.type == "CDS":
|
|
399
|
-
cds = feature.location.extract(seqrecord).seq
|
|
400
|
-
for index, base in enumerate(cds, start=1):
|
|
401
|
-
variants.append((f"{seqrecord.id}:c.{str(index) + base}dup",))
|
|
402
|
-
return variants
|
|
403
|
-
|
|
404
|
-
|
|
405
|
-
def frameshift_del(gene: str) -> list:
|
|
406
|
-
variants = []
|
|
407
|
-
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
408
|
-
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
409
|
-
record = Entrez.read(stream)
|
|
410
|
-
stream = Entrez.efetch(
|
|
411
|
-
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
412
|
-
)
|
|
413
|
-
seqrecord = SeqIO.read(stream, "genbank")
|
|
414
|
-
for feature in seqrecord.features:
|
|
415
|
-
if feature.type == "CDS":
|
|
416
|
-
cds = feature.location.extract(seqrecord).seq
|
|
417
|
-
for index, base in enumerate(cds, start=1):
|
|
418
|
-
variants.append((f"{seqrecord.id}:c.{str(index) + base}del",))
|
|
419
|
-
return variants
|
|
420
|
-
|
|
421
13
|
|
|
422
14
|
__all__ = [
|
|
423
|
-
"frameshift_dup",
|
|
424
|
-
"frameshift_del",
|
|
425
15
|
"cds",
|
|
426
|
-
"inframe_dup",
|
|
427
|
-
"inframe_del",
|
|
428
|
-
"splicing",
|
|
429
16
|
"utr5",
|
|
430
17
|
"utr3",
|
|
18
|
+
"splicing",
|
|
19
|
+
"inframe_del",
|
|
20
|
+
"inframe_dup",
|
|
21
|
+
"frameshift_del",
|
|
22
|
+
"frameshift_dup",
|
|
431
23
|
"aa_sub",
|
|
432
24
|
"missense",
|
|
433
25
|
]
|
varsim/core.py
ADDED
|
@@ -0,0 +1,432 @@
|
|
|
1
|
+
import os
|
|
2
|
+
|
|
3
|
+
from Bio import Entrez, SeqIO
|
|
4
|
+
from Bio.Data.CodonTable import standard_dna_table
|
|
5
|
+
from Bio.Data.IUPACData import (
|
|
6
|
+
unambiguous_dna_letters,
|
|
7
|
+
protein_letters,
|
|
8
|
+
protein_letters_1to3,
|
|
9
|
+
protein_letters_3to1,
|
|
10
|
+
)
|
|
11
|
+
from Bio.Seq import Seq
|
|
12
|
+
from Bio.SeqFeature import SimpleLocation
|
|
13
|
+
from Bio.SeqUtils import seq3
|
|
14
|
+
|
|
15
|
+
__all__ = [
|
|
16
|
+
"frameshift_dup",
|
|
17
|
+
"frameshift_del",
|
|
18
|
+
"cds",
|
|
19
|
+
"inframe_dup",
|
|
20
|
+
"inframe_del",
|
|
21
|
+
"splicing",
|
|
22
|
+
"utr5",
|
|
23
|
+
"utr3",
|
|
24
|
+
"aa_sub",
|
|
25
|
+
"missense",
|
|
26
|
+
]
|
|
27
|
+
|
|
28
|
+
Entrez.email = os.environ["EMAIL"]
|
|
29
|
+
Entrez.api_key = os.environ["API_KEY"]
|
|
30
|
+
codons = standard_dna_table.forward_table.keys()
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
def cds(gene: str) -> list:
|
|
34
|
+
variants = []
|
|
35
|
+
stream = Entrez.esearch(
|
|
36
|
+
db="nucleotide",
|
|
37
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
38
|
+
)
|
|
39
|
+
record = Entrez.read(stream)
|
|
40
|
+
stream = Entrez.efetch(
|
|
41
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
42
|
+
)
|
|
43
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
44
|
+
for feature in seqrecord.features:
|
|
45
|
+
if feature.type == "CDS":
|
|
46
|
+
protein = "".join(feature.qualifiers.get("translation"))
|
|
47
|
+
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
48
|
+
cds = feature.extract(seqrecord).seq
|
|
49
|
+
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
50
|
+
for base in unambiguous_dna_letters:
|
|
51
|
+
if base != cds[codon]:
|
|
52
|
+
seq = Seq(base) + cds[codon + 1 : codon + 3]
|
|
53
|
+
if protein[index] != seq.translate():
|
|
54
|
+
variants.append(
|
|
55
|
+
(
|
|
56
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
|
|
57
|
+
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
58
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
59
|
+
)
|
|
60
|
+
)
|
|
61
|
+
else:
|
|
62
|
+
variants.append(
|
|
63
|
+
(
|
|
64
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
|
|
65
|
+
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
66
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
67
|
+
)
|
|
68
|
+
)
|
|
69
|
+
if base != cds[codon + 1]:
|
|
70
|
+
seq = cds[codon] + Seq(base) + cds[codon + 2]
|
|
71
|
+
if protein[index] != seq.translate():
|
|
72
|
+
variants.append(
|
|
73
|
+
(
|
|
74
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
|
|
75
|
+
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
76
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
77
|
+
)
|
|
78
|
+
)
|
|
79
|
+
else:
|
|
80
|
+
variants.append(
|
|
81
|
+
(
|
|
82
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
|
|
83
|
+
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
84
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
85
|
+
)
|
|
86
|
+
)
|
|
87
|
+
if base != cds[codon + 2]:
|
|
88
|
+
seq = cds[codon : codon + 2] + Seq(base)
|
|
89
|
+
if protein[index] != seq.translate():
|
|
90
|
+
variants.append(
|
|
91
|
+
(
|
|
92
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
|
|
93
|
+
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
94
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
95
|
+
)
|
|
96
|
+
)
|
|
97
|
+
else:
|
|
98
|
+
variants.append(
|
|
99
|
+
(
|
|
100
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
|
|
101
|
+
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
102
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
103
|
+
)
|
|
104
|
+
)
|
|
105
|
+
return variants
|
|
106
|
+
|
|
107
|
+
|
|
108
|
+
def utr5(gene: str) -> list:
|
|
109
|
+
variants = []
|
|
110
|
+
stream = Entrez.esearch(
|
|
111
|
+
db="nucleotide",
|
|
112
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
113
|
+
)
|
|
114
|
+
record = Entrez.read(stream)
|
|
115
|
+
stream = Entrez.efetch(
|
|
116
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
117
|
+
)
|
|
118
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
119
|
+
for feature in seqrecord.features:
|
|
120
|
+
if feature.type == "CDS":
|
|
121
|
+
utr5 = SimpleLocation(0, feature.location.start).extract(seqrecord).seq
|
|
122
|
+
for index in range(len(utr5)):
|
|
123
|
+
for base in unambiguous_dna_letters:
|
|
124
|
+
if base != utr5[index]:
|
|
125
|
+
variants.append(
|
|
126
|
+
(
|
|
127
|
+
f"{seqrecord.id}:c.{index - len(utr5)}{utr5[index]}>{base}",
|
|
128
|
+
"",
|
|
129
|
+
"",
|
|
130
|
+
)
|
|
131
|
+
)
|
|
132
|
+
return variants
|
|
133
|
+
|
|
134
|
+
|
|
135
|
+
def utr3(gene: str) -> list:
|
|
136
|
+
variants = []
|
|
137
|
+
stream = Entrez.esearch(
|
|
138
|
+
db="nucleotide",
|
|
139
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
140
|
+
)
|
|
141
|
+
record = Entrez.read(stream)
|
|
142
|
+
stream = Entrez.efetch(
|
|
143
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
144
|
+
)
|
|
145
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
146
|
+
for feature in seqrecord.features:
|
|
147
|
+
if feature.type == "CDS":
|
|
148
|
+
utr3 = (
|
|
149
|
+
SimpleLocation(feature.location.end, len(seqrecord))
|
|
150
|
+
.extract(seqrecord)
|
|
151
|
+
.seq
|
|
152
|
+
)
|
|
153
|
+
for index in range(len(utr3)):
|
|
154
|
+
for base in unambiguous_dna_letters:
|
|
155
|
+
if base != utr3[index]:
|
|
156
|
+
variants.append(
|
|
157
|
+
(
|
|
158
|
+
f"{seqrecord.id}:c.*{index + 1}{utr3[index]}>{base}",
|
|
159
|
+
"",
|
|
160
|
+
"",
|
|
161
|
+
)
|
|
162
|
+
)
|
|
163
|
+
return variants
|
|
164
|
+
|
|
165
|
+
|
|
166
|
+
def splicing(gene: str) -> list:
|
|
167
|
+
variants = []
|
|
168
|
+
exon = []
|
|
169
|
+
stream = Entrez.esearch(
|
|
170
|
+
db="nucleotide", term=f'{gene}[Gene Name] "mane select"[Keyword]'
|
|
171
|
+
)
|
|
172
|
+
record = Entrez.read(stream)
|
|
173
|
+
|
|
174
|
+
stream = Entrez.efetch(
|
|
175
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
176
|
+
)
|
|
177
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
178
|
+
splicing = []
|
|
179
|
+
variants = []
|
|
180
|
+
start = 0
|
|
181
|
+
end = 0
|
|
182
|
+
for feature in seqrecord.features:
|
|
183
|
+
if feature.type == "CDS":
|
|
184
|
+
start = feature.location.start
|
|
185
|
+
end = feature.location.end
|
|
186
|
+
for feature in seqrecord.features:
|
|
187
|
+
if feature.type == "exon":
|
|
188
|
+
if feature.location.start < start and feature.location.end < start:
|
|
189
|
+
splicing.extend(
|
|
190
|
+
(
|
|
191
|
+
feature.location.start - start - 1,
|
|
192
|
+
feature.location.end - start - 1,
|
|
193
|
+
)
|
|
194
|
+
)
|
|
195
|
+
elif feature.location.start < start and feature.location.end > start:
|
|
196
|
+
splicing.extend(
|
|
197
|
+
(feature.location.start - start - 1, feature.location.end - start)
|
|
198
|
+
)
|
|
199
|
+
else:
|
|
200
|
+
splicing.extend(
|
|
201
|
+
(feature.location.start - start, feature.location.end - start)
|
|
202
|
+
)
|
|
203
|
+
|
|
204
|
+
for coordinate in range(1, len(splicing) - 1, 2):
|
|
205
|
+
site = splicing[coordinate], splicing[coordinate] + 1
|
|
206
|
+
for base in unambiguous_dna_letters:
|
|
207
|
+
if base != "G":
|
|
208
|
+
variants.append((f"{seqrecord.id}:c.{site[0]}+1G>{base}"))
|
|
209
|
+
if base != "T":
|
|
210
|
+
variants.append((f"{seqrecord.id}:c.{site[0]}+2T>{base}"))
|
|
211
|
+
if base != "A":
|
|
212
|
+
variants.append((f"{seqrecord.id}:c.{site[1]}-2A>{base}"))
|
|
213
|
+
if base != "G":
|
|
214
|
+
variants.append((f"{seqrecord.id}:c.{site[1]}-1G>{base}"))
|
|
215
|
+
return variants
|
|
216
|
+
|
|
217
|
+
|
|
218
|
+
def aa_sub(gene: str) -> list:
|
|
219
|
+
variants = []
|
|
220
|
+
term = f'{gene}[Gene Name] AND "mane select"[keyword]'
|
|
221
|
+
stream = Entrez.esearch(db="protein", term=term)
|
|
222
|
+
record = Entrez.read(stream)
|
|
223
|
+
|
|
224
|
+
stream = Entrez.efetch(
|
|
225
|
+
db="protein", rettype="gp", retmode="text", id=record["IdList"]
|
|
226
|
+
)
|
|
227
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
228
|
+
for index, residue in enumerate(seqrecord.seq, 1):
|
|
229
|
+
for aa in protein_letters:
|
|
230
|
+
if aa != residue:
|
|
231
|
+
variants.append(
|
|
232
|
+
(
|
|
233
|
+
f"{seqrecord.id}:p.{residue}{index}{aa}",
|
|
234
|
+
f"{seqrecord.id}:p.{protein_letters_1to3[residue]}{index}{protein_letters_1to3[aa]}",
|
|
235
|
+
)
|
|
236
|
+
)
|
|
237
|
+
return variants
|
|
238
|
+
|
|
239
|
+
|
|
240
|
+
def missense(gene: str) -> list:
|
|
241
|
+
variants = []
|
|
242
|
+
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
243
|
+
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
244
|
+
record = Entrez.read(stream)
|
|
245
|
+
stream = Entrez.efetch(
|
|
246
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
247
|
+
)
|
|
248
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
249
|
+
for feature in seqrecord.features:
|
|
250
|
+
if feature.type == "CDS":
|
|
251
|
+
protein = "".join(feature.qualifiers.get("translation"))
|
|
252
|
+
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
253
|
+
cds = feature.location.extract(seqrecord).seq
|
|
254
|
+
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
255
|
+
for base in codons:
|
|
256
|
+
if base != cds[codon : codon + 3]:
|
|
257
|
+
seq = Seq(base)
|
|
258
|
+
if protein[index] != seq.translate():
|
|
259
|
+
if (
|
|
260
|
+
base[0] == cds[codon]
|
|
261
|
+
and base[1] == cds[codon + 1]
|
|
262
|
+
and base[2] != cds[codon + 2]
|
|
263
|
+
):
|
|
264
|
+
variants.append(
|
|
265
|
+
(
|
|
266
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
|
|
267
|
+
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
268
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
269
|
+
)
|
|
270
|
+
)
|
|
271
|
+
elif (
|
|
272
|
+
base[0] == cds[codon]
|
|
273
|
+
and base[1] != cds[codon + 1]
|
|
274
|
+
and base[2] == cds[codon + 2]
|
|
275
|
+
):
|
|
276
|
+
variants.append(
|
|
277
|
+
(
|
|
278
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
|
|
279
|
+
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
280
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
281
|
+
)
|
|
282
|
+
)
|
|
283
|
+
elif (
|
|
284
|
+
base[0] != cds[codon]
|
|
285
|
+
and base[1] == cds[codon + 1]
|
|
286
|
+
and base[2] == cds[codon + 2]
|
|
287
|
+
):
|
|
288
|
+
variants.append(
|
|
289
|
+
(
|
|
290
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
|
|
291
|
+
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
292
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
293
|
+
)
|
|
294
|
+
)
|
|
295
|
+
else:
|
|
296
|
+
variants.append(
|
|
297
|
+
(
|
|
298
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}>{base}",
|
|
299
|
+
f"{protein_id}:p.{protein[index]}{index + 1}{seq.translate()}",
|
|
300
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}{seq3(seq.translate())}",
|
|
301
|
+
)
|
|
302
|
+
)
|
|
303
|
+
else:
|
|
304
|
+
if (
|
|
305
|
+
base[0] == cds[codon]
|
|
306
|
+
and base[1] == cds[codon + 1]
|
|
307
|
+
and base[2] != cds[codon + 2]
|
|
308
|
+
):
|
|
309
|
+
variants.append(
|
|
310
|
+
(
|
|
311
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
|
|
312
|
+
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
313
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
314
|
+
)
|
|
315
|
+
)
|
|
316
|
+
elif (
|
|
317
|
+
base[0] == cds[codon]
|
|
318
|
+
and base[1] != cds[codon + 1]
|
|
319
|
+
and base[2] == cds[codon + 2]
|
|
320
|
+
):
|
|
321
|
+
variants.append(
|
|
322
|
+
(
|
|
323
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
|
|
324
|
+
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
325
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
326
|
+
)
|
|
327
|
+
)
|
|
328
|
+
elif (
|
|
329
|
+
base[0] != cds[codon]
|
|
330
|
+
and base[1] == cds[codon + 1]
|
|
331
|
+
and base[2] == cds[codon + 2]
|
|
332
|
+
):
|
|
333
|
+
variants.append(
|
|
334
|
+
(
|
|
335
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
|
|
336
|
+
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
337
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
338
|
+
)
|
|
339
|
+
)
|
|
340
|
+
else:
|
|
341
|
+
variants.append(
|
|
342
|
+
(
|
|
343
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}>{base}",
|
|
344
|
+
f"{protein_id}:p.{protein[index]}{index + 1}=",
|
|
345
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}=",
|
|
346
|
+
)
|
|
347
|
+
)
|
|
348
|
+
return variants
|
|
349
|
+
|
|
350
|
+
|
|
351
|
+
def inframe_del(gene: str) -> list:
|
|
352
|
+
variants = []
|
|
353
|
+
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
354
|
+
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
355
|
+
record = Entrez.read(stream)
|
|
356
|
+
stream = Entrez.efetch(
|
|
357
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
358
|
+
)
|
|
359
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
360
|
+
for feature in seqrecord.features:
|
|
361
|
+
if feature.type == "CDS":
|
|
362
|
+
protein = "".join(feature.qualifiers.get("translation"))
|
|
363
|
+
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
364
|
+
cds = feature.location.extract(seqrecord).seq
|
|
365
|
+
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
366
|
+
variants.append(
|
|
367
|
+
(
|
|
368
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}del",
|
|
369
|
+
f"{protein_id}:p.{protein[index]}{index + 1}del",
|
|
370
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}del",
|
|
371
|
+
)
|
|
372
|
+
)
|
|
373
|
+
return variants
|
|
374
|
+
|
|
375
|
+
|
|
376
|
+
def inframe_dup(gene: str) -> list:
|
|
377
|
+
variants = []
|
|
378
|
+
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
379
|
+
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
380
|
+
record = Entrez.read(stream)
|
|
381
|
+
stream = Entrez.efetch(
|
|
382
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
383
|
+
)
|
|
384
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
385
|
+
for feature in seqrecord.features:
|
|
386
|
+
if feature.type == "CDS":
|
|
387
|
+
protein = "".join(feature.qualifiers.get("translation"))
|
|
388
|
+
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
389
|
+
cds = feature.location.extract(seqrecord).seq
|
|
390
|
+
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
391
|
+
variants.append(
|
|
392
|
+
(
|
|
393
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}{cds[codon:codon + 3]}dup",
|
|
394
|
+
f"{protein_id}:p.{protein[index]}{index + 1}dup",
|
|
395
|
+
f"{protein_id}:p.{seq3(protein[index])}{index + 1}dup",
|
|
396
|
+
)
|
|
397
|
+
)
|
|
398
|
+
return variants
|
|
399
|
+
|
|
400
|
+
|
|
401
|
+
def frameshift_dup(gene: str) -> list:
|
|
402
|
+
variants = []
|
|
403
|
+
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
404
|
+
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
405
|
+
record = Entrez.read(stream)
|
|
406
|
+
stream = Entrez.efetch(
|
|
407
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
408
|
+
)
|
|
409
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
410
|
+
for feature in seqrecord.features:
|
|
411
|
+
if feature.type == "CDS":
|
|
412
|
+
cds = feature.location.extract(seqrecord).seq
|
|
413
|
+
for index, base in enumerate(cds, start=1):
|
|
414
|
+
variants.append((f"{seqrecord.id}:c.{str(index) + base}dup",))
|
|
415
|
+
return variants
|
|
416
|
+
|
|
417
|
+
|
|
418
|
+
def frameshift_del(gene: str) -> list:
|
|
419
|
+
variants = []
|
|
420
|
+
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
421
|
+
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
422
|
+
record = Entrez.read(stream)
|
|
423
|
+
stream = Entrez.efetch(
|
|
424
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
425
|
+
)
|
|
426
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
427
|
+
for feature in seqrecord.features:
|
|
428
|
+
if feature.type == "CDS":
|
|
429
|
+
cds = feature.location.extract(seqrecord).seq
|
|
430
|
+
for index, base in enumerate(cds, start=1):
|
|
431
|
+
variants.append((f"{seqrecord.id}:c.{str(index) + base}del",))
|
|
432
|
+
return variants
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
varsim/__init__.py,sha256=_Lb0mutPhj2XKnvssCgsxqGMk2LFmcJRmRA9EXS10ZU,368
|
|
2
|
+
varsim/core.py,sha256=ZIHKGBIp-8_seM6suoUCe2A8OgOL0gR8Oocu-IpCe_k,17712
|
|
3
|
+
varsim-1.0.7.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
|
|
4
|
+
varsim-1.0.7.dist-info/METADATA,sha256=-fHxAfvRqDftFLfz-oYZL9fTrxQtTh5Mpf3Jk61mVGw,2464
|
|
5
|
+
varsim-1.0.7.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
|
|
6
|
+
varsim-1.0.7.dist-info/top_level.txt,sha256=2fLprhnBvkF-7VEOzGcpKoodqW08HjyNbVzM6emJrTI,7
|
|
7
|
+
varsim-1.0.7.dist-info/RECORD,,
|
varsim-1.0.5.dist-info/RECORD
DELETED
|
@@ -1,6 +0,0 @@
|
|
|
1
|
-
varsim/__init__.py,sha256=r2jXdCqlbLaJsNGXum0B9hBoX0gpGMNQ_aIqt2GyXr8,17714
|
|
2
|
-
varsim-1.0.5.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
|
|
3
|
-
varsim-1.0.5.dist-info/METADATA,sha256=8Uo9_Gn2Pg3Mkct-ZC7oJ9la2ZfddqvduepCUwnorPA,2464
|
|
4
|
-
varsim-1.0.5.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
|
|
5
|
-
varsim-1.0.5.dist-info/top_level.txt,sha256=2fLprhnBvkF-7VEOzGcpKoodqW08HjyNbVzM6emJrTI,7
|
|
6
|
-
varsim-1.0.5.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|