varsim 1.0.4__py3-none-any.whl → 1.0.5__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 +245 -82
- {varsim-1.0.4.dist-info → varsim-1.0.5.dist-info}/METADATA +1 -1
- varsim-1.0.5.dist-info/RECORD +6 -0
- varsim-1.0.4.dist-info/RECORD +0 -6
- {varsim-1.0.4.dist-info → varsim-1.0.5.dist-info}/WHEEL +0 -0
- {varsim-1.0.4.dist-info → varsim-1.0.5.dist-info}/licenses/LICENSE +0 -0
- {varsim-1.0.4.dist-info → varsim-1.0.5.dist-info}/top_level.txt +0 -0
varsim/__init__.py
CHANGED
|
@@ -2,7 +2,12 @@ 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
|
|
@@ -14,9 +19,14 @@ codons = standard_dna_table.forward_table.keys()
|
|
|
14
19
|
|
|
15
20
|
def cds(gene: str) -> list:
|
|
16
21
|
variants = []
|
|
17
|
-
stream = Entrez.esearch(
|
|
22
|
+
stream = Entrez.esearch(
|
|
23
|
+
db="nucleotide",
|
|
24
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
25
|
+
)
|
|
18
26
|
record = Entrez.read(stream)
|
|
19
|
-
stream = Entrez.efetch(
|
|
27
|
+
stream = Entrez.efetch(
|
|
28
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
29
|
+
)
|
|
20
30
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
21
31
|
for feature in seqrecord.features:
|
|
22
32
|
if feature.type == "CDS":
|
|
@@ -26,43 +36,72 @@ def cds(gene: str) -> list:
|
|
|
26
36
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
27
37
|
for base in unambiguous_dna_letters:
|
|
28
38
|
if base != cds[codon]:
|
|
29
|
-
seq = Seq(base) + cds[codon + 1: codon + 3]
|
|
39
|
+
seq = Seq(base) + cds[codon + 1 : codon + 3]
|
|
30
40
|
if protein[index] != seq.translate():
|
|
31
|
-
variants.append(
|
|
32
|
-
|
|
33
|
-
|
|
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
|
+
)
|
|
34
48
|
else:
|
|
35
|
-
variants.append(
|
|
36
|
-
|
|
37
|
-
|
|
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
|
+
)
|
|
38
56
|
if base != cds[codon + 1]:
|
|
39
57
|
seq = cds[codon] + Seq(base) + cds[codon + 2]
|
|
40
58
|
if protein[index] != seq.translate():
|
|
41
|
-
variants.append(
|
|
42
|
-
|
|
43
|
-
|
|
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
|
+
)
|
|
44
66
|
else:
|
|
45
|
-
variants.append(
|
|
46
|
-
|
|
47
|
-
|
|
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
|
+
)
|
|
48
74
|
if base != cds[codon + 2]:
|
|
49
|
-
seq = cds[codon: codon + 2] + Seq(base)
|
|
75
|
+
seq = cds[codon : codon + 2] + Seq(base)
|
|
50
76
|
if protein[index] != seq.translate():
|
|
51
|
-
variants.append(
|
|
52
|
-
|
|
53
|
-
|
|
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
|
+
)
|
|
54
84
|
else:
|
|
55
|
-
variants.append(
|
|
56
|
-
|
|
57
|
-
|
|
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
|
+
)
|
|
58
92
|
return variants
|
|
59
93
|
|
|
60
94
|
|
|
61
95
|
def utr5(gene: str) -> list:
|
|
62
96
|
variants = []
|
|
63
|
-
stream = Entrez.esearch(
|
|
97
|
+
stream = Entrez.esearch(
|
|
98
|
+
db="nucleotide",
|
|
99
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
100
|
+
)
|
|
64
101
|
record = Entrez.read(stream)
|
|
65
|
-
stream = Entrez.efetch(
|
|
102
|
+
stream = Entrez.efetch(
|
|
103
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
104
|
+
)
|
|
66
105
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
67
106
|
for feature in seqrecord.features:
|
|
68
107
|
if feature.type == "CDS":
|
|
@@ -70,33 +109,58 @@ def utr5(gene: str) -> list:
|
|
|
70
109
|
for index in range(len(utr5)):
|
|
71
110
|
for base in unambiguous_dna_letters:
|
|
72
111
|
if base != utr5[index]:
|
|
73
|
-
variants.append(
|
|
112
|
+
variants.append(
|
|
113
|
+
(
|
|
114
|
+
f"{seqrecord.id}:c.{index - len(utr5)}{utr5[index]}>{base}",
|
|
115
|
+
"",
|
|
116
|
+
"",
|
|
117
|
+
)
|
|
118
|
+
)
|
|
74
119
|
return variants
|
|
75
120
|
|
|
76
121
|
|
|
77
122
|
def utr3(gene: str) -> list:
|
|
78
123
|
variants = []
|
|
79
|
-
stream = Entrez.esearch(
|
|
124
|
+
stream = Entrez.esearch(
|
|
125
|
+
db="nucleotide",
|
|
126
|
+
term=f'{gene}[Gene Name] "mane select"[Keyword]',
|
|
127
|
+
)
|
|
80
128
|
record = Entrez.read(stream)
|
|
81
|
-
stream = Entrez.efetch(
|
|
129
|
+
stream = Entrez.efetch(
|
|
130
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
131
|
+
)
|
|
82
132
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
83
133
|
for feature in seqrecord.features:
|
|
84
134
|
if feature.type == "CDS":
|
|
85
|
-
utr3 = (
|
|
135
|
+
utr3 = (
|
|
136
|
+
SimpleLocation(feature.location.end, len(seqrecord))
|
|
137
|
+
.extract(seqrecord)
|
|
138
|
+
.seq
|
|
139
|
+
)
|
|
86
140
|
for index in range(len(utr3)):
|
|
87
141
|
for base in unambiguous_dna_letters:
|
|
88
142
|
if base != utr3[index]:
|
|
89
|
-
variants.append(
|
|
143
|
+
variants.append(
|
|
144
|
+
(
|
|
145
|
+
f"{seqrecord.id}:c.*{index + 1}{utr3[index]}>{base}",
|
|
146
|
+
"",
|
|
147
|
+
"",
|
|
148
|
+
)
|
|
149
|
+
)
|
|
90
150
|
return variants
|
|
91
151
|
|
|
92
152
|
|
|
93
153
|
def splicing(gene: str) -> list:
|
|
94
154
|
variants = []
|
|
95
155
|
exon = []
|
|
96
|
-
stream = Entrez.esearch(
|
|
156
|
+
stream = Entrez.esearch(
|
|
157
|
+
db="nucleotide", term=f'{gene}[Gene Name] "mane select"[Keyword]'
|
|
158
|
+
)
|
|
97
159
|
record = Entrez.read(stream)
|
|
98
160
|
|
|
99
|
-
stream = Entrez.efetch(
|
|
161
|
+
stream = Entrez.efetch(
|
|
162
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
163
|
+
)
|
|
100
164
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
101
165
|
splicing = []
|
|
102
166
|
variants = []
|
|
@@ -109,11 +173,20 @@ def splicing(gene: str) -> list:
|
|
|
109
173
|
for feature in seqrecord.features:
|
|
110
174
|
if feature.type == "exon":
|
|
111
175
|
if feature.location.start < start and feature.location.end < start:
|
|
112
|
-
splicing.extend(
|
|
176
|
+
splicing.extend(
|
|
177
|
+
(
|
|
178
|
+
feature.location.start - start - 1,
|
|
179
|
+
feature.location.end - start - 1,
|
|
180
|
+
)
|
|
181
|
+
)
|
|
113
182
|
elif feature.location.start < start and feature.location.end > start:
|
|
114
|
-
splicing.extend(
|
|
183
|
+
splicing.extend(
|
|
184
|
+
(feature.location.start - start - 1, feature.location.end - start)
|
|
185
|
+
)
|
|
115
186
|
else:
|
|
116
|
-
splicing.extend(
|
|
187
|
+
splicing.extend(
|
|
188
|
+
(feature.location.start - start, feature.location.end - start)
|
|
189
|
+
)
|
|
117
190
|
|
|
118
191
|
for coordinate in range(1, len(splicing) - 1, 2):
|
|
119
192
|
site = splicing[coordinate], splicing[coordinate] + 1
|
|
@@ -135,13 +208,19 @@ def aa_sub(gene: str) -> list:
|
|
|
135
208
|
stream = Entrez.esearch(db="protein", term=term)
|
|
136
209
|
record = Entrez.read(stream)
|
|
137
210
|
|
|
138
|
-
stream = Entrez.efetch(
|
|
211
|
+
stream = Entrez.efetch(
|
|
212
|
+
db="protein", rettype="gp", retmode="text", id=record["IdList"]
|
|
213
|
+
)
|
|
139
214
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
140
215
|
for index, residue in enumerate(seqrecord.seq, 1):
|
|
141
216
|
for aa in protein_letters:
|
|
142
217
|
if aa != residue:
|
|
143
|
-
variants.append(
|
|
144
|
-
|
|
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
|
+
)
|
|
145
224
|
return variants
|
|
146
225
|
|
|
147
226
|
|
|
@@ -150,7 +229,9 @@ def missense(gene: str) -> list:
|
|
|
150
229
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
151
230
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
152
231
|
record = Entrez.read(stream)
|
|
153
|
-
stream = Entrez.efetch(
|
|
232
|
+
stream = Entrez.efetch(
|
|
233
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
234
|
+
)
|
|
154
235
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
155
236
|
for feature in seqrecord.features:
|
|
156
237
|
if feature.type == "CDS":
|
|
@@ -159,42 +240,98 @@ def missense(gene: str) -> list:
|
|
|
159
240
|
cds = feature.location.extract(seqrecord).seq
|
|
160
241
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
161
242
|
for base in codons:
|
|
162
|
-
if base != cds[codon: codon + 3]:
|
|
243
|
+
if base != cds[codon : codon + 3]:
|
|
163
244
|
seq = Seq(base)
|
|
164
245
|
if protein[index] != seq.translate():
|
|
165
|
-
if (
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
variants.append(
|
|
171
|
-
|
|
172
|
-
|
|
173
|
-
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
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
|
+
)
|
|
177
282
|
else:
|
|
178
|
-
variants.append(
|
|
179
|
-
|
|
180
|
-
|
|
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
|
+
)
|
|
181
290
|
else:
|
|
182
|
-
if (
|
|
183
|
-
|
|
184
|
-
|
|
185
|
-
|
|
186
|
-
|
|
187
|
-
variants.append(
|
|
188
|
-
|
|
189
|
-
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
|
|
193
|
-
|
|
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
|
+
)
|
|
194
327
|
else:
|
|
195
|
-
variants.append(
|
|
196
|
-
|
|
197
|
-
|
|
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
|
+
)
|
|
198
335
|
return variants
|
|
199
336
|
|
|
200
337
|
|
|
@@ -203,7 +340,9 @@ def inframe_del(gene: str) -> list:
|
|
|
203
340
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
204
341
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
205
342
|
record = Entrez.read(stream)
|
|
206
|
-
stream = Entrez.efetch(
|
|
343
|
+
stream = Entrez.efetch(
|
|
344
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
345
|
+
)
|
|
207
346
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
208
347
|
for feature in seqrecord.features:
|
|
209
348
|
if feature.type == "CDS":
|
|
@@ -211,9 +350,13 @@ def inframe_del(gene: str) -> list:
|
|
|
211
350
|
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
212
351
|
cds = feature.location.extract(seqrecord).seq
|
|
213
352
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
214
|
-
variants.append(
|
|
215
|
-
|
|
216
|
-
|
|
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
|
+
)
|
|
217
360
|
return variants
|
|
218
361
|
|
|
219
362
|
|
|
@@ -222,7 +365,9 @@ def inframe_dup(gene: str) -> list:
|
|
|
222
365
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
223
366
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
224
367
|
record = Entrez.read(stream)
|
|
225
|
-
stream = Entrez.efetch(
|
|
368
|
+
stream = Entrez.efetch(
|
|
369
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
370
|
+
)
|
|
226
371
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
227
372
|
for feature in seqrecord.features:
|
|
228
373
|
if feature.type == "CDS":
|
|
@@ -230,9 +375,13 @@ def inframe_dup(gene: str) -> list:
|
|
|
230
375
|
protein_id = "".join(feature.qualifiers.get("protein_id"))
|
|
231
376
|
cds = feature.location.extract(seqrecord).seq
|
|
232
377
|
for index, codon in enumerate(range(0, len(cds) - 3, 3)):
|
|
233
|
-
variants.append(
|
|
234
|
-
|
|
235
|
-
|
|
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
|
+
)
|
|
236
385
|
return variants
|
|
237
386
|
|
|
238
387
|
|
|
@@ -241,7 +390,9 @@ def frameshift_dup(gene: str) -> list:
|
|
|
241
390
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
242
391
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
243
392
|
record = Entrez.read(stream)
|
|
244
|
-
stream = Entrez.efetch(
|
|
393
|
+
stream = Entrez.efetch(
|
|
394
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
395
|
+
)
|
|
245
396
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
246
397
|
for feature in seqrecord.features:
|
|
247
398
|
if feature.type == "CDS":
|
|
@@ -256,7 +407,9 @@ def frameshift_del(gene: str) -> list:
|
|
|
256
407
|
term = f'{gene}[Gene Name] "mane select"[keyword]'
|
|
257
408
|
stream = Entrez.esearch(db="nucleotide", term=term)
|
|
258
409
|
record = Entrez.read(stream)
|
|
259
|
-
stream = Entrez.efetch(
|
|
410
|
+
stream = Entrez.efetch(
|
|
411
|
+
db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
|
|
412
|
+
)
|
|
260
413
|
seqrecord = SeqIO.read(stream, "genbank")
|
|
261
414
|
for feature in seqrecord.features:
|
|
262
415
|
if feature.type == "CDS":
|
|
@@ -266,5 +419,15 @@ def frameshift_del(gene: str) -> list:
|
|
|
266
419
|
return variants
|
|
267
420
|
|
|
268
421
|
|
|
269
|
-
|
|
270
|
-
|
|
422
|
+
__all__ = [
|
|
423
|
+
"frameshift_dup",
|
|
424
|
+
"frameshift_del",
|
|
425
|
+
"cds",
|
|
426
|
+
"inframe_dup",
|
|
427
|
+
"inframe_del",
|
|
428
|
+
"splicing",
|
|
429
|
+
"utr5",
|
|
430
|
+
"utr3",
|
|
431
|
+
"aa_sub",
|
|
432
|
+
"missense",
|
|
433
|
+
]
|
|
@@ -0,0 +1,6 @@
|
|
|
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,,
|
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
|