DeepMutSim 1.0.0__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.
deepmutsim/__init__.py
ADDED
|
@@ -0,0 +1,611 @@
|
|
|
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 unambiguous_dna_letters, protein_letters
|
|
6
|
+
from Bio.Seq import Seq
|
|
7
|
+
from Bio.SeqFeature import SimpleLocation
|
|
8
|
+
from Bio.SeqUtils import seq3, seq1
|
|
9
|
+
|
|
10
|
+
Entrez.email = os.environ["EMAIL"]
|
|
11
|
+
Entrez.api_key = os.environ["API_KEY"]
|
|
12
|
+
genetic_code = list(standard_dna_table.forward_table.keys())+standard_dna_table.stop_codons
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
def nm(gene: str) -> str:
|
|
16
|
+
stream = Entrez.esearch(
|
|
17
|
+
db="nucleotide",
|
|
18
|
+
term=f'{gene}[Gene Name] AND ("MANE Select"[Keyword] OR "MANE Plus Clinical"[keyword])',
|
|
19
|
+
)
|
|
20
|
+
record = Entrez.read(stream)
|
|
21
|
+
stream = Entrez.efetch(
|
|
22
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
23
|
+
)
|
|
24
|
+
seqrecord = SeqIO.read(stream, "genbank")
|
|
25
|
+
return seqrecord
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
def np(gene: str) -> str:
|
|
29
|
+
stream = Entrez.esearch(
|
|
30
|
+
db="protein",
|
|
31
|
+
term=f'{gene}[Gene Name] AND ("MANE Select"[Keyword] OR "MANE Plus Clinical"[keyword])',
|
|
32
|
+
)
|
|
33
|
+
record = Entrez.read(stream)
|
|
34
|
+
stream = Entrez.efetch(
|
|
35
|
+
db="protein", id=record["IdList"], rettype="fasta", retmode="text"
|
|
36
|
+
)
|
|
37
|
+
seqrecord = SeqIO.read(stream, "fasta")
|
|
38
|
+
return seqrecord
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
def nc(gene: str) -> str:
|
|
42
|
+
stream = Entrez.esearch(
|
|
43
|
+
db="nucleotide",
|
|
44
|
+
term=f'{gene}[Gene Name] AND "Primary Assembly"[Title] AND human[Organism]',
|
|
45
|
+
)
|
|
46
|
+
record = Entrez.read(stream)
|
|
47
|
+
stream = Entrez.efetch(
|
|
48
|
+
db="nucleotide", id=record["IdList"], rettype="acc", retmode="text"
|
|
49
|
+
)
|
|
50
|
+
acc = stream.read().strip()
|
|
51
|
+
return acc
|
|
52
|
+
|
|
53
|
+
|
|
54
|
+
def cds(gene: str) -> list:
|
|
55
|
+
variants = []
|
|
56
|
+
seqrecord = nm(gene)
|
|
57
|
+
protein_seqrecord = np(gene)
|
|
58
|
+
protein = str(protein_seqrecord.seq)
|
|
59
|
+
protein_id = protein_seqrecord.id
|
|
60
|
+
for feature in seqrecord.features:
|
|
61
|
+
if feature.type == "CDS":
|
|
62
|
+
cds = feature.extract(seqrecord).seq
|
|
63
|
+
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
64
|
+
for base in unambiguous_dna_letters:
|
|
65
|
+
if index == 0:
|
|
66
|
+
if base != "A":
|
|
67
|
+
variants.append(
|
|
68
|
+
(
|
|
69
|
+
f"{seqrecord.id}:c.1A>{base}",
|
|
70
|
+
f"{protein_id}:p.(M1?)",
|
|
71
|
+
f"{protein_id}:p.(Met1?)",
|
|
72
|
+
)
|
|
73
|
+
)
|
|
74
|
+
else:
|
|
75
|
+
if base != cds[codon]:
|
|
76
|
+
seq = Seq(base) + cds[codon + 1 : codon + 3]
|
|
77
|
+
if protein[index] != seq.translate():
|
|
78
|
+
variants.append(
|
|
79
|
+
(
|
|
80
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
|
|
81
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
82
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
83
|
+
)
|
|
84
|
+
)
|
|
85
|
+
else:
|
|
86
|
+
variants.append(
|
|
87
|
+
(
|
|
88
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
|
|
89
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
90
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
91
|
+
)
|
|
92
|
+
)
|
|
93
|
+
if index == 0:
|
|
94
|
+
if base != "T":
|
|
95
|
+
variants.append(
|
|
96
|
+
(
|
|
97
|
+
f"{seqrecord.id}:c.2T>{base}",
|
|
98
|
+
f"{protein_id}:p.(M1?)",
|
|
99
|
+
f"{protein_id}:p.(Met1?)",
|
|
100
|
+
)
|
|
101
|
+
)
|
|
102
|
+
else:
|
|
103
|
+
if base != cds[codon + 1]:
|
|
104
|
+
seq = cds[codon] + Seq(base) + cds[codon + 2]
|
|
105
|
+
if protein[index] != seq.translate():
|
|
106
|
+
variants.append(
|
|
107
|
+
(
|
|
108
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
|
|
109
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
110
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
111
|
+
)
|
|
112
|
+
)
|
|
113
|
+
else:
|
|
114
|
+
variants.append(
|
|
115
|
+
(
|
|
116
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
|
|
117
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
118
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
119
|
+
)
|
|
120
|
+
)
|
|
121
|
+
if index == 0:
|
|
122
|
+
if base != "G":
|
|
123
|
+
variants.append(
|
|
124
|
+
(
|
|
125
|
+
f"{seqrecord.id}:c.3G>{base}",
|
|
126
|
+
f"{protein_id}:p.(M1?)",
|
|
127
|
+
f"{protein_id}:p.(Met1?)",
|
|
128
|
+
)
|
|
129
|
+
)
|
|
130
|
+
else:
|
|
131
|
+
if base != cds[codon + 2]:
|
|
132
|
+
seq = cds[codon : codon + 2] + Seq(base)
|
|
133
|
+
if protein[index] != seq.translate():
|
|
134
|
+
variants.append(
|
|
135
|
+
(
|
|
136
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
|
|
137
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
138
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
139
|
+
)
|
|
140
|
+
)
|
|
141
|
+
else:
|
|
142
|
+
variants.append(
|
|
143
|
+
(
|
|
144
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
|
|
145
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
146
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
147
|
+
)
|
|
148
|
+
)
|
|
149
|
+
return variants
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
def utr5(gene: str) -> list:
|
|
153
|
+
variants = []
|
|
154
|
+
seqrecord = nm(gene)
|
|
155
|
+
for feature in seqrecord.features:
|
|
156
|
+
if feature.type == "CDS":
|
|
157
|
+
utr5 = SimpleLocation(0, feature.location.start).extract(seqrecord).seq
|
|
158
|
+
for index in range(len(utr5)):
|
|
159
|
+
for base in unambiguous_dna_letters:
|
|
160
|
+
if base != utr5[index]:
|
|
161
|
+
variants.append(
|
|
162
|
+
f"{seqrecord.id}:c.{index - len(utr5)}{utr5[index]}>{base}"
|
|
163
|
+
)
|
|
164
|
+
return variants
|
|
165
|
+
|
|
166
|
+
|
|
167
|
+
def utr3(gene: str) -> list:
|
|
168
|
+
variants = []
|
|
169
|
+
seqrecord = nm(gene)
|
|
170
|
+
for feature in seqrecord.features:
|
|
171
|
+
if feature.type == "CDS":
|
|
172
|
+
utr3 = (
|
|
173
|
+
SimpleLocation(feature.location.end, len(seqrecord))
|
|
174
|
+
.extract(seqrecord)
|
|
175
|
+
.seq
|
|
176
|
+
)
|
|
177
|
+
for index in range(len(utr3)):
|
|
178
|
+
for base in unambiguous_dna_letters:
|
|
179
|
+
if base != utr3[index]:
|
|
180
|
+
variants.append(f"{seqrecord.id}:c.*{index + 1}{utr3[index]}>{base}")
|
|
181
|
+
return variants
|
|
182
|
+
|
|
183
|
+
|
|
184
|
+
def splice_site(gene: str) -> list:
|
|
185
|
+
variants = []
|
|
186
|
+
seqrecord = nm(gene)
|
|
187
|
+
acc = nc(gene)
|
|
188
|
+
splicing = []
|
|
189
|
+
for feature in seqrecord.features:
|
|
190
|
+
if feature.type == "CDS":
|
|
191
|
+
start = feature.location.start
|
|
192
|
+
end = feature.location.end
|
|
193
|
+
for feature in seqrecord.features:
|
|
194
|
+
if feature.type == "exon":
|
|
195
|
+
if feature.location.end < start or feature.location.start > end:
|
|
196
|
+
continue
|
|
197
|
+
else:
|
|
198
|
+
splicing.extend(
|
|
199
|
+
(feature.location.start - start, feature.location.end - start)
|
|
200
|
+
)
|
|
201
|
+
|
|
202
|
+
for coordinate in range(1, len(splicing) - 1, 2):
|
|
203
|
+
site = splicing[coordinate], splicing[coordinate] + 1
|
|
204
|
+
for base in unambiguous_dna_letters:
|
|
205
|
+
if base != "G":
|
|
206
|
+
variants.append(f"{acc}({seqrecord.id}):c.{site[0]}+1G>{base}")
|
|
207
|
+
if base != "T":
|
|
208
|
+
variants.append(f"{acc}({seqrecord.id}):c.{site[0]}+2T>{base}")
|
|
209
|
+
if base != "A":
|
|
210
|
+
variants.append(f"{acc}({seqrecord.id}):c.{site[1]}-2A>{base}")
|
|
211
|
+
if base != "G":
|
|
212
|
+
variants.append(f"{acc}({seqrecord.id}):c.{site[1]}-1G>{base}")
|
|
213
|
+
return variants
|
|
214
|
+
|
|
215
|
+
|
|
216
|
+
def aa_sub(gene: str) -> list:
|
|
217
|
+
variants = []
|
|
218
|
+
seqrecord = np(gene)
|
|
219
|
+
for index, residue in enumerate(seqrecord.seq, 1):
|
|
220
|
+
for aa in protein_letters:
|
|
221
|
+
if aa != residue:
|
|
222
|
+
if index != 1:
|
|
223
|
+
variants.append(
|
|
224
|
+
(
|
|
225
|
+
f"{seqrecord.id}:p.({residue}{index}{aa})",
|
|
226
|
+
f"{seqrecord.id}:p.({seq3(residue)}{index}{seq3(aa)})",
|
|
227
|
+
)
|
|
228
|
+
)
|
|
229
|
+
else:
|
|
230
|
+
variants.append(
|
|
231
|
+
(
|
|
232
|
+
f"{seqrecord.id}:p.({residue}{index}?)",
|
|
233
|
+
f"{seqrecord.id}:p.({seq3(residue)}{index}?)",
|
|
234
|
+
)
|
|
235
|
+
)
|
|
236
|
+
return variants
|
|
237
|
+
|
|
238
|
+
|
|
239
|
+
def codon_sub(gene: str) -> list:
|
|
240
|
+
variants = []
|
|
241
|
+
seqrecord = nm(gene)
|
|
242
|
+
for feature in seqrecord.features:
|
|
243
|
+
if feature.type == "CDS":
|
|
244
|
+
cds = feature.location.extract(seqrecord).seq
|
|
245
|
+
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
246
|
+
for base in genetic_code:
|
|
247
|
+
if base != cds[codon : codon + 3]:
|
|
248
|
+
seq = Seq(base)
|
|
249
|
+
if all(
|
|
250
|
+
(
|
|
251
|
+
base[0] != cds[codon],
|
|
252
|
+
base[1] != cds[codon + 1],
|
|
253
|
+
base[2] != cds[codon + 2],
|
|
254
|
+
)
|
|
255
|
+
):
|
|
256
|
+
variants.append(
|
|
257
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}"
|
|
258
|
+
)
|
|
259
|
+
elif all(
|
|
260
|
+
(
|
|
261
|
+
base[0] == cds[codon],
|
|
262
|
+
base[1] != cds[codon + 1],
|
|
263
|
+
base[2] != cds[codon + 2],
|
|
264
|
+
)
|
|
265
|
+
):
|
|
266
|
+
variants.append(
|
|
267
|
+
f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}"
|
|
268
|
+
)
|
|
269
|
+
elif all(
|
|
270
|
+
(
|
|
271
|
+
base[0] != cds[codon],
|
|
272
|
+
base[1] == cds[codon + 1],
|
|
273
|
+
base[2] != cds[codon + 2],
|
|
274
|
+
)
|
|
275
|
+
):
|
|
276
|
+
variants.append(
|
|
277
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}"
|
|
278
|
+
)
|
|
279
|
+
elif all(
|
|
280
|
+
(
|
|
281
|
+
base[0] != cds[codon],
|
|
282
|
+
base[1] != cds[codon + 1],
|
|
283
|
+
base[2] == cds[codon + 2],
|
|
284
|
+
)
|
|
285
|
+
):
|
|
286
|
+
variants.append(
|
|
287
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}"
|
|
288
|
+
)
|
|
289
|
+
elif all(
|
|
290
|
+
(
|
|
291
|
+
base[0] == cds[codon],
|
|
292
|
+
base[1] == cds[codon + 1],
|
|
293
|
+
base[2] != cds[codon + 2],
|
|
294
|
+
)
|
|
295
|
+
):
|
|
296
|
+
variants.append(
|
|
297
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}"
|
|
298
|
+
)
|
|
299
|
+
elif all(
|
|
300
|
+
(
|
|
301
|
+
base[0] == cds[codon],
|
|
302
|
+
base[1] != cds[codon + 1],
|
|
303
|
+
base[2] == cds[codon + 2],
|
|
304
|
+
)
|
|
305
|
+
):
|
|
306
|
+
variants.append(
|
|
307
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}"
|
|
308
|
+
)
|
|
309
|
+
elif all(
|
|
310
|
+
(
|
|
311
|
+
base[0] != cds[codon],
|
|
312
|
+
base[1] == cds[codon + 1],
|
|
313
|
+
base[2] == cds[codon + 2],
|
|
314
|
+
)
|
|
315
|
+
):
|
|
316
|
+
variants.append(
|
|
317
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}"
|
|
318
|
+
)
|
|
319
|
+
return variants
|
|
320
|
+
|
|
321
|
+
|
|
322
|
+
def missense(gene: str) -> list:
|
|
323
|
+
variants = []
|
|
324
|
+
seqrecord = nm(gene)
|
|
325
|
+
protein_seqrecord = np(gene)
|
|
326
|
+
protein = str(protein_seqrecord.seq)
|
|
327
|
+
protein_id = protein_seqrecord.id
|
|
328
|
+
for feature in seqrecord.features:
|
|
329
|
+
if feature.type == "CDS":
|
|
330
|
+
cds = feature.location.extract(seqrecord).seq
|
|
331
|
+
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
332
|
+
for base in genetic_code:
|
|
333
|
+
if base != cds[codon : codon + 3]:
|
|
334
|
+
seq = Seq(base)
|
|
335
|
+
if index == 0:
|
|
336
|
+
if all(
|
|
337
|
+
(
|
|
338
|
+
base[0] != cds[codon],
|
|
339
|
+
base[1] != cds[codon + 1],
|
|
340
|
+
base[2] != cds[codon + 2],
|
|
341
|
+
)
|
|
342
|
+
):
|
|
343
|
+
variants.append(
|
|
344
|
+
(
|
|
345
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
|
|
346
|
+
f"{protein_id}:p.(M1?)",
|
|
347
|
+
f"{protein_id}:p.(Met1?)",
|
|
348
|
+
)
|
|
349
|
+
)
|
|
350
|
+
elif all(
|
|
351
|
+
(
|
|
352
|
+
base[0] == cds[codon],
|
|
353
|
+
base[1] != cds[codon + 1],
|
|
354
|
+
base[2] != cds[codon + 2],
|
|
355
|
+
)
|
|
356
|
+
):
|
|
357
|
+
variants.append(
|
|
358
|
+
(
|
|
359
|
+
f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}",
|
|
360
|
+
f"{protein_id}:p.(M1?)",
|
|
361
|
+
f"{protein_id}:p.(Met1?)",
|
|
362
|
+
)
|
|
363
|
+
)
|
|
364
|
+
elif all(
|
|
365
|
+
(
|
|
366
|
+
base[0] != cds[codon],
|
|
367
|
+
base[1] == cds[codon + 1],
|
|
368
|
+
base[2] != cds[codon + 2],
|
|
369
|
+
)
|
|
370
|
+
):
|
|
371
|
+
variants.append(
|
|
372
|
+
(
|
|
373
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
|
|
374
|
+
f"{protein_id}:p.(M1?)",
|
|
375
|
+
f"{protein_id}:p.(Met1?)",
|
|
376
|
+
)
|
|
377
|
+
)
|
|
378
|
+
elif all(
|
|
379
|
+
(
|
|
380
|
+
base[0] != cds[codon],
|
|
381
|
+
base[1] != cds[codon + 1],
|
|
382
|
+
base[2] == cds[codon + 2],
|
|
383
|
+
)
|
|
384
|
+
):
|
|
385
|
+
variants.append(
|
|
386
|
+
(
|
|
387
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}",
|
|
388
|
+
f"{protein_id}:p.(M1?)",
|
|
389
|
+
f"{protein_id}:p.(Met1?)",
|
|
390
|
+
)
|
|
391
|
+
)
|
|
392
|
+
elif all(
|
|
393
|
+
(
|
|
394
|
+
base[0] == cds[codon],
|
|
395
|
+
base[1] == cds[codon + 1],
|
|
396
|
+
base[2] != cds[codon + 2],
|
|
397
|
+
)
|
|
398
|
+
):
|
|
399
|
+
variants.append(
|
|
400
|
+
(
|
|
401
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
|
|
402
|
+
f"{protein_id}:p.(M1?)",
|
|
403
|
+
f"{protein_id}:p.(Met1?)",
|
|
404
|
+
)
|
|
405
|
+
)
|
|
406
|
+
elif all(
|
|
407
|
+
(
|
|
408
|
+
base[0] == cds[codon],
|
|
409
|
+
base[1] != cds[codon + 1],
|
|
410
|
+
base[2] == cds[codon + 2],
|
|
411
|
+
)
|
|
412
|
+
):
|
|
413
|
+
variants.append(
|
|
414
|
+
(
|
|
415
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
|
|
416
|
+
f"{protein_id}:p.(M1?)",
|
|
417
|
+
f"{protein_id}:p.(Met1?)",
|
|
418
|
+
)
|
|
419
|
+
)
|
|
420
|
+
elif all(
|
|
421
|
+
(
|
|
422
|
+
base[0] != cds[codon],
|
|
423
|
+
base[1] == cds[codon + 1],
|
|
424
|
+
base[2] == cds[codon + 2],
|
|
425
|
+
)
|
|
426
|
+
):
|
|
427
|
+
variants.append(
|
|
428
|
+
(
|
|
429
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
|
|
430
|
+
f"{protein_id}:p.(M1?)",
|
|
431
|
+
f"{protein_id}:p.(Met1?)",
|
|
432
|
+
)
|
|
433
|
+
)
|
|
434
|
+
else:
|
|
435
|
+
if all(
|
|
436
|
+
(
|
|
437
|
+
base[0] != cds[codon],
|
|
438
|
+
base[1] != cds[codon + 1],
|
|
439
|
+
base[2] != cds[codon + 2],
|
|
440
|
+
)
|
|
441
|
+
):
|
|
442
|
+
if protein[index] != seq.translate():
|
|
443
|
+
variants.append(
|
|
444
|
+
(
|
|
445
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
|
|
446
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
447
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
448
|
+
)
|
|
449
|
+
)
|
|
450
|
+
else:
|
|
451
|
+
variants.append(
|
|
452
|
+
(
|
|
453
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
|
|
454
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
455
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
456
|
+
)
|
|
457
|
+
)
|
|
458
|
+
elif all(
|
|
459
|
+
(
|
|
460
|
+
base[0] == cds[codon],
|
|
461
|
+
base[1] != cds[codon + 1],
|
|
462
|
+
base[2] != cds[codon + 2],
|
|
463
|
+
)
|
|
464
|
+
):
|
|
465
|
+
if protein[index] != seq.translate():
|
|
466
|
+
variants.append(
|
|
467
|
+
(
|
|
468
|
+
f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}",
|
|
469
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
470
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
471
|
+
)
|
|
472
|
+
)
|
|
473
|
+
else:
|
|
474
|
+
variants.append(
|
|
475
|
+
(
|
|
476
|
+
f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}",
|
|
477
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
478
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
479
|
+
)
|
|
480
|
+
)
|
|
481
|
+
elif all(
|
|
482
|
+
(
|
|
483
|
+
base[0] != cds[codon],
|
|
484
|
+
base[1] == cds[codon + 1],
|
|
485
|
+
base[2] != cds[codon + 2],
|
|
486
|
+
)
|
|
487
|
+
):
|
|
488
|
+
if protein[index] != seq.translate():
|
|
489
|
+
variants.append(
|
|
490
|
+
(
|
|
491
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
|
|
492
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
493
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
494
|
+
)
|
|
495
|
+
)
|
|
496
|
+
else:
|
|
497
|
+
variants.append(
|
|
498
|
+
(
|
|
499
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
|
|
500
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
501
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
502
|
+
)
|
|
503
|
+
)
|
|
504
|
+
elif all(
|
|
505
|
+
(
|
|
506
|
+
base[0] != cds[codon],
|
|
507
|
+
base[1] != cds[codon + 1],
|
|
508
|
+
base[2] == cds[codon + 2],
|
|
509
|
+
)
|
|
510
|
+
):
|
|
511
|
+
if protein[index] != seq.translate():
|
|
512
|
+
variants.append(
|
|
513
|
+
(
|
|
514
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}",
|
|
515
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
516
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
517
|
+
)
|
|
518
|
+
)
|
|
519
|
+
else:
|
|
520
|
+
variants.append(
|
|
521
|
+
(
|
|
522
|
+
f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}",
|
|
523
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
524
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
525
|
+
)
|
|
526
|
+
)
|
|
527
|
+
elif all(
|
|
528
|
+
(
|
|
529
|
+
base[0] == cds[codon],
|
|
530
|
+
base[1] == cds[codon + 1],
|
|
531
|
+
base[2] != cds[codon + 2],
|
|
532
|
+
)
|
|
533
|
+
):
|
|
534
|
+
if protein[index] != seq.translate():
|
|
535
|
+
variants.append(
|
|
536
|
+
(
|
|
537
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
|
|
538
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
539
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
540
|
+
)
|
|
541
|
+
)
|
|
542
|
+
else:
|
|
543
|
+
variants.append(
|
|
544
|
+
(
|
|
545
|
+
f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
|
|
546
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
547
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
548
|
+
)
|
|
549
|
+
)
|
|
550
|
+
elif all(
|
|
551
|
+
(
|
|
552
|
+
base[0] == cds[codon],
|
|
553
|
+
base[1] != cds[codon + 1],
|
|
554
|
+
base[2] == cds[codon + 2],
|
|
555
|
+
)
|
|
556
|
+
):
|
|
557
|
+
if protein[index] != seq.translate():
|
|
558
|
+
variants.append(
|
|
559
|
+
(
|
|
560
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
|
|
561
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
562
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
563
|
+
)
|
|
564
|
+
)
|
|
565
|
+
else:
|
|
566
|
+
variants.append(
|
|
567
|
+
(
|
|
568
|
+
f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
|
|
569
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
570
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
571
|
+
)
|
|
572
|
+
)
|
|
573
|
+
elif all(
|
|
574
|
+
(
|
|
575
|
+
base[0] != cds[codon],
|
|
576
|
+
base[1] == cds[codon + 1],
|
|
577
|
+
base[2] == cds[codon + 2],
|
|
578
|
+
)
|
|
579
|
+
):
|
|
580
|
+
if protein[index] != seq.translate():
|
|
581
|
+
variants.append(
|
|
582
|
+
(
|
|
583
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
|
|
584
|
+
f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
|
|
585
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
|
|
586
|
+
)
|
|
587
|
+
)
|
|
588
|
+
else:
|
|
589
|
+
variants.append(
|
|
590
|
+
(
|
|
591
|
+
f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
|
|
592
|
+
f"{protein_id}:p.({protein[index]}{index + 1}=)",
|
|
593
|
+
f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
|
|
594
|
+
)
|
|
595
|
+
)
|
|
596
|
+
return variants
|
|
597
|
+
|
|
598
|
+
|
|
599
|
+
if __name__ == "__main__":
|
|
600
|
+
import pprint
|
|
601
|
+
|
|
602
|
+
# pprint.pprint(cds("INS"))
|
|
603
|
+
# pprint.pprint(missense("INS"))
|
|
604
|
+
# pprint.pprint(aa_sub("INS"))
|
|
605
|
+
# pprint.pprint(utr5("INS"))
|
|
606
|
+
# pprint.pprint(utr3("INS"))
|
|
607
|
+
pprint.pprint(splice_site("INS"))
|
|
608
|
+
# pprint.pprint(codon_sub("INS"))
|
|
609
|
+
# pprint.pprint(nc("INS"))
|
|
610
|
+
# pprint.pprint(np("INS"))
|
|
611
|
+
# pprint.pprint(nm("INS"))
|
|
@@ -0,0 +1,79 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: DeepMutSim
|
|
3
|
+
Version: 1.0.0
|
|
4
|
+
Summary: Generates all possible SNVs for MANE transcripts using HGVS nomenclature.
|
|
5
|
+
Author-email: Liu Sun <sunliu@yxnu.edu.cn>, Jian Yang <yangjian@yxnu.edu.cn>
|
|
6
|
+
Project-URL: Homepage, https://github.com/liu-sun/DeepMutSim
|
|
7
|
+
Project-URL: Issues, https://github.com/liu-sun/DeepMutSim/issues
|
|
8
|
+
Classifier: Programming Language :: Python :: 3
|
|
9
|
+
Classifier: Operating System :: OS Independent
|
|
10
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
11
|
+
Requires-Python: >=3.8
|
|
12
|
+
Description-Content-Type: text/markdown
|
|
13
|
+
License-File: LICENSE
|
|
14
|
+
Requires-Dist: biopython
|
|
15
|
+
Dynamic: license-file
|
|
16
|
+
|
|
17
|
+
# DeepMutSim
|
|
18
|
+
|
|
19
|
+
DeepMutSim generates simulations for all possible single nucleotide variants (SNVs) for the Matched Annotation from NCBI and EMBL-EBI (MANE) transcript, along with the corresponding protein using HGVS notation.
|
|
20
|
+
|
|
21
|
+
**INSTALLATION**
|
|
22
|
+
|
|
23
|
+
```powershell
|
|
24
|
+
pip install deepmutsim
|
|
25
|
+
```
|
|
26
|
+
CONFIGURATION (Mandatory)
|
|
27
|
+
|
|
28
|
+
Before you can use DeepMutSim, you must set two environment variables to query the NCBI Entrez database.
|
|
29
|
+
|
|
30
|
+
EMAIL: (Required by NCBI) A valid email address so NCBI can contact you if there's an issue with your queries.
|
|
31
|
+
|
|
32
|
+
API_KEY: (Recommended) An NCBI API key, which allows for a much higher query rate. You can obtain one from your NCBI account settings.
|
|
33
|
+
|
|
34
|
+
Linux/macOS:
|
|
35
|
+
```Bash
|
|
36
|
+
|
|
37
|
+
export EMAIL="your.email@example.com"
|
|
38
|
+
export API_KEY="your_api_key_here"
|
|
39
|
+
```
|
|
40
|
+
Windows (PowerShell):
|
|
41
|
+
|
|
42
|
+
```powershell
|
|
43
|
+
set EMAIL="your.email@example.com"
|
|
44
|
+
set API_KEY="your_api_key_here"
|
|
45
|
+
```
|
|
46
|
+
USAGE
|
|
47
|
+
|
|
48
|
+
Variant Simulator
|
|
49
|
+
```Python
|
|
50
|
+
|
|
51
|
+
import deepmutsim
|
|
52
|
+
# Assumes EMAIL and API_KEY are set
|
|
53
|
+
deepmutsim.cds("INS")
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
```python
|
|
57
|
+
[('NM_000207.3:c.1A>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ... ('NM_000207.3:c.328A>T', 'NP_000198.1:p.(N110Y)', 'NP_000198.1:p.(Asn110Tyr)'), ('NM_000207.3:c.328A>C', 'NP_000198.1:p.(N110H)', 'NP_000198.1:p.(Asn110His)'), ('NM_000207.3:c.329A>T', 'NP_000198.1:p.(N110I)', 'NP_000198.1:p.(Asn110Ile)'), ('NM_000207.3:c.329A>C', 'NP_000198.1:p.(N110T)', 'NP_000198.1:p.(Asn110Thr)'), ('NM_000207.3:c.330C>T', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>A', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>G', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)')]
|
|
58
|
+
```
|
|
59
|
+
```Python
|
|
60
|
+
|
|
61
|
+
deepmutsim.utr5("INS")
|
|
62
|
+
```
|
|
63
|
+
```python
|
|
64
|
+
['NM_000207.3:c.-59A>G', 'NM_000207.3:c.-59A>T', 'NM_000207.3:c.-59A>C', 'NM_000207.3:c.-58G>A', 'NM_000207.3:c.-58G>T', ... 'NM_000207.3:c.-2C>A', 'NM_000207.3:c.-2C>T', 'NM_000207.3:c.-1C>G', 'NM_000207.3:c.-1C>A', 'NM_000207.3:c.-1C>T']
|
|
65
|
+
```
|
|
66
|
+
```Python
|
|
67
|
+
|
|
68
|
+
deepmutsim.utr3("INS")
|
|
69
|
+
```
|
|
70
|
+
```python
|
|
71
|
+
['NM_000207.3:c.*1A>G', 'NM_000207.3:c.*1A>T', 'NM_000207.3:c.*1A>C', 'NM_000207.3:c.*2C>G', 'NM_000207.3:c.*2C>A', ... 'NM_000207.3:c.*72G>T', 'NM_000207.3:c.*72G>C', 'NM_000207.3:c.*73C>G', 'NM_000207.3:c.*73C>A', 'NM_000207.3:c.*73C>T']
|
|
72
|
+
```
|
|
73
|
+
```Python
|
|
74
|
+
|
|
75
|
+
deepmutsim.splice_site("INS")
|
|
76
|
+
```
|
|
77
|
+
```python
|
|
78
|
+
['NC_000011.10(NM_000207.3):c.187+1G>A', 'NC_000011.10(NM_000207.3):c.187+1G>T', 'NC_000011.10(NM_000207.3):c.187+1G>C', 'NC_000011.10(NM_000207.3):c.187+2T>A', 'NC_000011.10(NM_000207.3):c.187+2T>G', 'NC_000011.10(NM_000207.3):c.187+2T>C', 'NC_000011.10(NM_000207.3):c.188-2A>G', 'NC_000011.10(NM_000207.3):c.188-2A>T', 'NC_000011.10(NM_000207.3):c.188-2A>C', 'NC_000011.10(NM_000207.3):c.188-1G>A', 'NC_000011.10(NM_000207.3):c.188-1G>T', 'NC_000011.10(NM_000207.3):c.188-1G>C']
|
|
79
|
+
```
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
deepmutsim/__init__.py,sha256=5f3I3b-CrAWStTWof2Wr7aUd_RGB3E-4CvR1b028dBo,26502
|
|
2
|
+
deepmutsim-1.0.0.dist-info/licenses/LICENSE,sha256=cN3m_KlKLkPVUK4ggZfeeUCKlRjI83V819nV8pKxKI8,1085
|
|
3
|
+
deepmutsim-1.0.0.dist-info/METADATA,sha256=8Vu4nATd0GcM35EetI1vBsn9JAtWER114gTk9WNlM-k,4042
|
|
4
|
+
deepmutsim-1.0.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
|
|
5
|
+
deepmutsim-1.0.0.dist-info/top_level.txt,sha256=kfXY9GGa6VLuKvthpkcxsCjBE8Kq1go-tTAOSgSoDl0,11
|
|
6
|
+
deepmutsim-1.0.0.dist-info/RECORD,,
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
MIT License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2025 Liu Sun
|
|
4
|
+
|
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
|
7
|
+
in the Software without restriction, including without limitation the rights
|
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
|
10
|
+
furnished to do so, subject to the following conditions:
|
|
11
|
+
|
|
12
|
+
The above copyright notice and this permission notice shall be included in all
|
|
13
|
+
copies or substantial portions of the Software.
|
|
14
|
+
|
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
21
|
+
SOFTWARE.
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
deepmutsim
|