varsim 1.0.4__py3-none-any.whl → 1.0.6__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 +246 -84
- {varsim-1.0.4.dist-info → varsim-1.0.6.dist-info}/METADATA +1 -1
- varsim-1.0.6.dist-info/RECORD +6 -0
- varsim-1.0.4.dist-info/RECORD +0 -6
- {varsim-1.0.4.dist-info → varsim-1.0.6.dist-info}/WHEEL +0 -0
- {varsim-1.0.4.dist-info → varsim-1.0.6.dist-info}/licenses/LICENSE +0 -0
- {varsim-1.0.4.dist-info → varsim-1.0.6.dist-info}/top_level.txt +0 -0
varsim/__init__.py
CHANGED
|
@@ -2,11 +2,29 @@ import os
|
|
|
2
2
|
|
|
3
3
|
from Bio import Entrez, SeqIO
|
|
4
4
|
from Bio.Data.CodonTable import standard_dna_table
|
|
5
|
-
from Bio.Data.IUPACData import (
|
|
5
|
+
from Bio.Data.IUPACData import (
|
|
6
|
+
unambiguous_dna_letters,
|
|
7
|
+
protein_letters,
|
|
8
|
+
protein_letters_1to3,
|
|
9
|
+
protein_letters_3to1,
|
|
10
|
+
)
|
|
6
11
|
from Bio.Seq import Seq
|
|
7
12
|
from Bio.SeqFeature import SimpleLocation
|
|
8
13
|
from Bio.SeqUtils import seq3
|
|
9
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
|
+
|
|
10
28
|
Entrez.email = os.environ["EMAIL"]
|
|
11
29
|
Entrez.api_key = os.environ["API_KEY"]
|
|
12
30
|
codons = standard_dna_table.forward_table.keys()
|
|
@@ -14,9 +32,14 @@ codons = standard_dna_table.forward_table.keys()
|
|
|
14
32
|
|
|
15
33
|
def cds(gene: str) -> list:
|
|
16
34
|
variants = []
|
|
17
|
-
stream = Entrez.esearch(
|
|
35
|
+
stream = Entrez.esearch(
|
|
36
|
+
db="nucleotide",
|
|
37
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
38
|
+
)
|
|
18
39
|
record = Entrez.read(stream)
|
|
19
|
-
stream = Entrez.efetch(
|
|
40
|
+
stream = Entrez.efetch(
|
|
41
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
42
|
+
)
|
|
20
43
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
21
44
|
for feature in seqrecord.features:
|
|
22
45
|
if feature.type == "CDS":
|
|
@@ -26,43 +49,72 @@ def cds(gene: str) -> list:
|
|
|
26
49
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
27
50
|
for base in unambiguous_dna_letters:
|
|
28
51
|
if base != cds[codon]:
|
|
29
|
-
seq = Seq(base) + cds[codon + 1: codon + 3]
|
|
52
|
+
seq = Seq(base) + cds[codon + 1 : codon + 3]
|
|
30
53
|
if protein[index] != seq.translate():
|
|
31
|
-
variants.append(
|
|
32
|
-
|
|
33
|
-
|
|
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
|
+
)
|
|
34
61
|
else:
|
|
35
|
-
variants.append(
|
|
36
|
-
|
|
37
|
-
|
|
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
|
+
)
|
|
38
69
|
if base != cds[codon + 1]:
|
|
39
70
|
seq = cds[codon] + Seq(base) + cds[codon + 2]
|
|
40
71
|
if protein[index] != seq.translate():
|
|
41
|
-
variants.append(
|
|
42
|
-
|
|
43
|
-
|
|
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
|
+
)
|
|
44
79
|
else:
|
|
45
|
-
variants.append(
|
|
46
|
-
|
|
47
|
-
|
|
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
|
+
)
|
|
48
87
|
if base != cds[codon + 2]:
|
|
49
|
-
seq = cds[codon: codon + 2] + Seq(base)
|
|
88
|
+
seq = cds[codon : codon + 2] + Seq(base)
|
|
50
89
|
if protein[index] != seq.translate():
|
|
51
|
-
variants.append(
|
|
52
|
-
|
|
53
|
-
|
|
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
|
+
)
|
|
54
97
|
else:
|
|
55
|
-
variants.append(
|
|
56
|
-
|
|
57
|
-
|
|
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
|
+
)
|
|
58
105
|
return variants
|
|
59
106
|
|
|
60
107
|
|
|
61
108
|
def utr5(gene: str) -> list:
|
|
62
109
|
variants = []
|
|
63
|
-
stream = Entrez.esearch(
|
|
110
|
+
stream = Entrez.esearch(
|
|
111
|
+
db="nucleotide",
|
|
112
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
113
|
+
)
|
|
64
114
|
record = Entrez.read(stream)
|
|
65
|
-
stream = Entrez.efetch(
|
|
115
|
+
stream = Entrez.efetch(
|
|
116
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
117
|
+
)
|
|
66
118
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
67
119
|
for feature in seqrecord.features:
|
|
68
120
|
if feature.type == "CDS":
|
|
@@ -70,33 +122,58 @@ def utr5(gene: str) -> list:
|
|
|
70
122
|
for index in range(len(utr5)):
|
|
71
123
|
for base in unambiguous_dna_letters:
|
|
72
124
|
if base != utr5[index]:
|
|
73
|
-
variants.append(
|
|
125
|
+
variants.append(
|
|
126
|
+
(
|
|
127
|
+
f"{seqrecord.id}:c.{index - len(utr5)}{utr5[index]}>{base}",
|
|
128
|
+
"",
|
|
129
|
+
"",
|
|
130
|
+
)
|
|
131
|
+
)
|
|
74
132
|
return variants
|
|
75
133
|
|
|
76
134
|
|
|
77
135
|
def utr3(gene: str) -> list:
|
|
78
136
|
variants = []
|
|
79
|
-
stream = Entrez.esearch(
|
|
137
|
+
stream = Entrez.esearch(
|
|
138
|
+
db="nucleotide",
|
|
139
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
140
|
+
)
|
|
80
141
|
record = Entrez.read(stream)
|
|
81
|
-
stream = Entrez.efetch(
|
|
142
|
+
stream = Entrez.efetch(
|
|
143
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
144
|
+
)
|
|
82
145
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
83
146
|
for feature in seqrecord.features:
|
|
84
147
|
if feature.type == "CDS":
|
|
85
|
-
utr3 = (
|
|
148
|
+
utr3 = (
|
|
149
|
+
SimpleLocation(feature.location.end, len(seqrecord))
|
|
150
|
+
.extract(seqrecord)
|
|
151
|
+
.seq
|
|
152
|
+
)
|
|
86
153
|
for index in range(len(utr3)):
|
|
87
154
|
for base in unambiguous_dna_letters:
|
|
88
155
|
if base != utr3[index]:
|
|
89
|
-
variants.append(
|
|
156
|
+
variants.append(
|
|
157
|
+
(
|
|
158
|
+
f"{seqrecord.id}:c.*{index + 1}{utr3[index]}>{base}",
|
|
159
|
+
"",
|
|
160
|
+
"",
|
|
161
|
+
)
|
|
162
|
+
)
|
|
90
163
|
return variants
|
|
91
164
|
|
|
92
165
|
|
|
93
166
|
def splicing(gene: str) -> list:
|
|
94
167
|
variants = []
|
|
95
168
|
exon = []
|
|
96
|
-
stream = Entrez.esearch(
|
|
169
|
+
stream = Entrez.esearch(
|
|
170
|
+
db="nucleotide", term=f'{gene}[Gene Name] "mane select"[Keyword]'
|
|
171
|
+
)
|
|
97
172
|
record = Entrez.read(stream)
|
|
98
173
|
|
|
99
|
-
stream = Entrez.efetch(
|
|
174
|
+
stream = Entrez.efetch(
|
|
175
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
176
|
+
)
|
|
100
177
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
101
178
|
splicing = []
|
|
102
179
|
variants = []
|
|
@@ -109,11 +186,20 @@ def splicing(gene: str) -> list:
|
|
|
109
186
|
for feature in seqrecord.features:
|
|
110
187
|
if feature.type == "exon":
|
|
111
188
|
if feature.location.start < start and feature.location.end < start:
|
|
112
|
-
splicing.extend(
|
|
189
|
+
splicing.extend(
|
|
190
|
+
(
|
|
191
|
+
feature.location.start - start - 1,
|
|
192
|
+
feature.location.end - start - 1,
|
|
193
|
+
)
|
|
194
|
+
)
|
|
113
195
|
elif feature.location.start < start and feature.location.end > start:
|
|
114
|
-
splicing.extend(
|
|
196
|
+
splicing.extend(
|
|
197
|
+
(feature.location.start - start - 1, feature.location.end - start)
|
|
198
|
+
)
|
|
115
199
|
else:
|
|
116
|
-
splicing.extend(
|
|
200
|
+
splicing.extend(
|
|
201
|
+
(feature.location.start - start, feature.location.end - start)
|
|
202
|
+
)
|
|
117
203
|
|
|
118
204
|
for coordinate in range(1, len(splicing) - 1, 2):
|
|
119
205
|
site = splicing[coordinate], splicing[coordinate] + 1
|
|
@@ -135,13 +221,19 @@ def aa_sub(gene: str) -> list:
|
|
|
135
221
|
stream = Entrez.esearch(db="protein", term=term)
|
|
136
222
|
record = Entrez.read(stream)
|
|
137
223
|
|
|
138
|
-
stream = Entrez.efetch(
|
|
224
|
+
stream = Entrez.efetch(
|
|
225
|
+
db="protein", rettype="gp", retmode="text", id=record["IdList"]
|
|
226
|
+
)
|
|
139
227
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
140
228
|
for index, residue in enumerate(seqrecord.seq, 1):
|
|
141
229
|
for aa in protein_letters:
|
|
142
230
|
if aa != residue:
|
|
143
|
-
variants.append(
|
|
144
|
-
|
|
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
|
+
)
|
|
145
237
|
return variants
|
|
146
238
|
|
|
147
239
|
|
|
@@ -150,7 +242,9 @@ def missense(gene: str) -> list:
|
|
|
150
242
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
151
243
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
152
244
|
record = Entrez.read(stream)
|
|
153
|
-
stream = Entrez.efetch(
|
|
245
|
+
stream = Entrez.efetch(
|
|
246
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
247
|
+
)
|
|
154
248
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
155
249
|
for feature in seqrecord.features:
|
|
156
250
|
if feature.type == "CDS":
|
|
@@ -159,42 +253,98 @@ def missense(gene: str) -> list:
|
|
|
159
253
|
cds = feature.location.extract(seqrecord).seq
|
|
160
254
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
161
255
|
for base in codons:
|
|
162
|
-
if base != cds[codon: codon + 3]:
|
|
256
|
+
if base != cds[codon : codon + 3]:
|
|
163
257
|
seq = Seq(base)
|
|
164
258
|
if protein[index] != seq.translate():
|
|
165
|
-
if (
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
variants.append(
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
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
|
+
)
|
|
177
295
|
else:
|
|
178
|
-
variants.append(
|
|
179
|
-
|
|
180
|
-
|
|
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
|
+
)
|
|
181
303
|
else:
|
|
182
|
-
if (
|
|
183
|
-
|
|
184
|
-
|
|
185
|
-
|
|
186
|
-
|
|
187
|
-
variants.append(
|
|
188
|
-
|
|
189
|
-
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
|
|
193
|
-
|
|
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
|
+
)
|
|
194
340
|
else:
|
|
195
|
-
variants.append(
|
|
196
|
-
|
|
197
|
-
|
|
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
|
+
)
|
|
198
348
|
return variants
|
|
199
349
|
|
|
200
350
|
|
|
@@ -203,7 +353,9 @@ def inframe_del(gene: str) -> list:
|
|
|
203
353
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
204
354
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
205
355
|
record = Entrez.read(stream)
|
|
206
|
-
stream = Entrez.efetch(
|
|
356
|
+
stream = Entrez.efetch(
|
|
357
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
358
|
+
)
|
|
207
359
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
208
360
|
for feature in seqrecord.features:
|
|
209
361
|
if feature.type == "CDS":
|
|
@@ -211,9 +363,13 @@ def inframe_del(gene: str) -> list:
|
|
|
211
363
|
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
212
364
|
cds = feature.location.extract(seqrecord).seq
|
|
213
365
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
214
|
-
variants.append(
|
|
215
|
-
|
|
216
|
-
|
|
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
|
+
)
|
|
217
373
|
return variants
|
|
218
374
|
|
|
219
375
|
|
|
@@ -222,7 +378,9 @@ def inframe_dup(gene: str) -> list:
|
|
|
222
378
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
223
379
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
224
380
|
record = Entrez.read(stream)
|
|
225
|
-
stream = Entrez.efetch(
|
|
381
|
+
stream = Entrez.efetch(
|
|
382
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
383
|
+
)
|
|
226
384
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
227
385
|
for feature in seqrecord.features:
|
|
228
386
|
if feature.type == "CDS":
|
|
@@ -230,9 +388,13 @@ def inframe_dup(gene: str) -> list:
|
|
|
230
388
|
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
231
389
|
cds = feature.location.extract(seqrecord).seq
|
|
232
390
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
233
|
-
variants.append(
|
|
234
|
-
|
|
235
|
-
|
|
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
|
+
)
|
|
236
398
|
return variants
|
|
237
399
|
|
|
238
400
|
|
|
@@ -241,7 +403,9 @@ def frameshift_dup(gene: str) -> list:
|
|
|
241
403
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
242
404
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
243
405
|
record = Entrez.read(stream)
|
|
244
|
-
stream = Entrez.efetch(
|
|
406
|
+
stream = Entrez.efetch(
|
|
407
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
408
|
+
)
|
|
245
409
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
246
410
|
for feature in seqrecord.features:
|
|
247
411
|
if feature.type == "CDS":
|
|
@@ -256,7 +420,9 @@ def frameshift_del(gene: str) -> list:
|
|
|
256
420
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
257
421
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
258
422
|
record = Entrez.read(stream)
|
|
259
|
-
stream = Entrez.efetch(
|
|
423
|
+
stream = Entrez.efetch(
|
|
424
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
425
|
+
)
|
|
260
426
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
261
427
|
for feature in seqrecord.features:
|
|
262
428
|
if feature.type == "CDS":
|
|
@@ -264,7 +430,3 @@ def frameshift_del(gene: str) -> list:
|
|
|
264
430
|
for index, base in enumerate(cds, start=1):
|
|
265
431
|
variants.append((f"{seqrecord.id}:c.{str(index) + base}del",))
|
|
266
432
|
return variants
|
|
267
|
-
|
|
268
|
-
|
|
269
|
-
if __name__ == "__main__":
|
|
270
|
-
print(frameshift_del("INS"))
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
varsim/__init__.py,sha256=ZIHKGBIp-8_seM6suoUCe2A8OgOL0gR8Oocu-IpCe_k,17712
|
|
2
|
+
varsim-1.0.6.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
|
|
3
|
+
varsim-1.0.6.dist-info/METADATA,sha256=p205IC4VbHE2OXj7KexqchrFKTp0Ema67c37s4O3rFs,2464
|
|
4
|
+
varsim-1.0.6.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
|
|
5
|
+
varsim-1.0.6.dist-info/top_level.txt,sha256=2fLprhnBvkF-7VEOzGcpKoodqW08HjyNbVzM6emJrTI,7
|
|
6
|
+
varsim-1.0.6.dist-info/RECORD,,
|
varsim-1.0.4.dist-info/RECORD
DELETED
|
@@ -1,6 +0,0 @@
|
|
|
1
|
-
varsim/__init__.py,sha256=pZL4Wz3LJBoYvBdbNXByTx6qtCSkHqzBbR2dBWl7E60,14702
|
|
2
|
-
varsim-1.0.4.dist-info/licenses/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
|
|
3
|
-
varsim-1.0.4.dist-info/METADATA,sha256=4W43kr56JnS5Jpw-U6E_wDEpepZYSYnojsdV_YgI-1M,2464
|
|
4
|
-
varsim-1.0.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
|
|
5
|
-
varsim-1.0.4.dist-info/top_level.txt,sha256=2fLprhnBvkF-7VEOzGcpKoodqW08HjyNbVzM6emJrTI,7
|
|
6
|
-
varsim-1.0.4.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|