1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
|
import string
from Bio import Alphabet
from Bio.Alphabet import IUPAC
from Bio.Data import IUPACData
unambiguous_dna_by_name = {}
unambiguous_dna_by_id = {}
unambiguous_rna_by_name = {}
unambiguous_rna_by_id = {}
generic_by_name = {}
generic_by_id = {}
# standard IUPAC unambiguous codons
standard_dna_table = None
standard_rna_table = None
# In the future, the back_table could return a statistically
# appropriate distribution of codons, so do not cache the results of
# back_table lookups!
class TranslationError(Exception):
pass
class CodonTable:
nucleotide_alphabet = Alphabet.generic_nucleotide
protein_alphabet = Alphabet.generic_protein
forward_table = {} # only includes codons which actually code
back_table = {} # for back translations
start_codons = []
stop_codons = []
# Not always called from derived classes!
def __init__(self, nucleotide_alphabet = nucleotide_alphabet,
protein_alphabet = protein_alphabet,
forward_table = forward_table, back_table = back_table,
start_codons = start_codons, stop_codons = stop_codons):
self.nucleotide_alphabet = nucleotide_alphabet
self.protein_alphabet = protein_alphabet
self.forward_table = forward_table
self.back_table = back_table
self.start_codons = start_codons
self.stop_codons = stop_codons
def make_back_table(table, default_stop_codon):
# ONLY RETURNS A SINGLE CODON
# Do the sort so changes in the hash implementation won't affect
# the result when one amino acid is coded by more than one codon.
back_table = {}
keys = table.keys() ; keys.sort()
for key in keys:
back_table[table[key]] = key
back_table[None] = default_stop_codon
return back_table
class NCBICodonTable(CodonTable):
nucleotide_alphabet = Alphabet.generic_nucleotide
protein_alphabet = IUPAC.protein
def __init__(self, id, names, table, start_codons, stop_codons):
self.id = id
self.names = names
self.forward_table = table
self.back_table = make_back_table(table, stop_codons[0])
self.start_codons = start_codons
self.stop_codons = stop_codons
class NCBICodonTableDNA(NCBICodonTable):
nucleotide_alphabet = IUPAC.unambiguous_dna
class NCBICodonTableRNA(NCBICodonTable):
nucleotide_alphabet = IUPAC.unambiguous_rna
def register_ncbi_table(name, alt_name, id,
table, start_codons, stop_codons):
names = string.split(name, "; ")
dna = NCBICodonTableDNA(id, names + [alt_name], table, start_codons,
stop_codons)
# replace all T's with U's for the RNA tables
rna_table = {}
generic_table = {}
for codon, val in table.items():
generic_table[codon] = val
codon = codon.replace("T", "U")
generic_table[codon] = val
rna_table[codon] = val
rna_start_codons = []
generic_start_codons = []
for codon in start_codons:
generic_start_codons.append(codon)
codon = codon.replace("T", "U")
generic_start_codons.append(codon)
rna_start_codons.append(codon)
rna_stop_codons = []
generic_stop_codons = []
for codon in stop_codons:
generic_stop_codons.append(codon)
codon = codon.replace("T", "U")
generic_stop_codons.append(codon)
rna_stop_codons.append(codon)
generic = NCBICodonTable(id, names + [alt_name], generic_table,
generic_start_codons, generic_stop_codons)
rna = NCBICodonTableRNA(id, names + [alt_name], rna_table,
rna_start_codons, rna_stop_codons)
if id == 1:
global standard_dna_table, standard_rna_table
standard_dna_table = dna
standard_rna_table = rna
unambiguous_dna_by_id[id] = dna
unambiguous_rna_by_id[id] = rna
generic_by_id[id] = generic
if alt_name is not None:
names.append(alt_name)
for name in names:
unambiguous_dna_by_name[name] = dna
unambiguous_rna_by_name[name] = rna
generic_by_name[name] = generic
### These tables created from the data file
### ftp://ncbi.nlm.nih.gov/entrez/misc/data/gc.prt
### using the following:
##import re
##for line in open("gc.prt").readlines():
## if line[:2] == " {":
## names = []
## id = None
## aa = None
## start = None
## bases = []
## elif line[:6] == " name":
## names.append(re.search('"([^"]*)"', line).group(1))
## elif line[:8] == " name":
## names.append(re.search('"(.*)$', line).group(1))
## elif line == ' Mitochondrial; Mycoplasma; Spiroplasma" ,\n':
## names[-1] = names[-1] + " Mitochondrial; Mycoplasma; Spiroplasma"
## elif line[:4] == " id":
## id = int(re.search('(\d+)', line).group(1))
## elif line[:10] == " ncbieaa ":
## aa = line[12:12+64]
## elif line[:10] == " sncbieaa":
## start = line[12:12+64]
## elif line[:9] == " -- Base":
## bases.append(line[12:12+64])
## elif line[:2] == " }":
## assert names != [] and id is not None and aa is not None
## assert start is not None and bases != []
## if len(names) == 1:
## names.append(None)
## print "register_ncbi_table(name = %s," % repr(names[0])
## print " alt_name = %s, id = %d", % \
## (repr(names[1]), id)
## print " table = {"
## s = " "
## for i in range(64):
## if aa[i] != "*":
## t = " '%s%s%s': '%s'," % (bases[0][i], bases[1][i],
## bases[2][i], aa[i])
## if len(s) + len(t) > 75:
## print s
## s = " " + t
## else:
## s = s + t
## print s, "},"
## s = " stop_codons = ["
## for i in range(64):
## if aa[i] == "*":
## t = " '%s%s%s'," % (bases[0][i], bases[1][i], bases[2][i])
## if len(s) + len(t) > 75:
## print s
## s = " " + t
## else:
## s = s + t
## print s, "],"
## s = " start_codons = ["
## for i in range(64):
## if start[i] == "M":
## t = " '%s%s%s'," % (bases[0][i], bases[1][i], bases[2][i])
## if len(s) + len(t) > 75:
## print s
## s = " " + t
## else:
## s = s + t
## print s, "]"
## print " )"
## elif line[:2] == "--" or line == "\n" or line == "}\n" or \
## line == 'Genetic-code-table ::= {\n':
## pass
## else:
## raise "Unparsed", repr(line)
register_ncbi_table(name = 'Standard',
alt_name = 'SGC0', id = 1,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGG': 'W', 'CTT': 'L', 'CTC': 'L',
'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P', 'CCA': 'P',
'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R', 'ATT': 'I',
'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T', 'ACC': 'T',
'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N', 'AAA': 'K',
'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V', 'GCT': 'A',
'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D', 'GAC': 'D',
'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G', 'GGA': 'G',
'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', 'TGA', ],
start_codons = [ 'TTG', 'CTG', 'ATG', ]
)
register_ncbi_table(name = 'Vertebrate Mitochondrial',
alt_name = 'SGC1', id = 2,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W', 'CTT': 'L',
'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'M', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'GTT': 'V',
'GTC': 'V', 'GTA': 'V', 'GTG': 'V', 'GCT': 'A', 'GCC': 'A',
'GCA': 'A', 'GCG': 'A', 'GAT': 'D', 'GAC': 'D', 'GAA': 'E',
'GAG': 'E', 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', 'AGA', 'AGG', ],
start_codons = [ 'ATT', 'ATC', 'ATA', 'ATG', 'GTG', ]
)
register_ncbi_table(name = 'Yeast Mitochondrial',
alt_name = 'SGC2', id = 3,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W', 'CTT': 'T',
'CTC': 'T', 'CTA': 'T', 'CTG': 'T', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'M', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R',
'AGG': 'R', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D',
'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G',
'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', ],
start_codons = [ 'ATG', ]
)
register_ncbi_table(name = 'Mold Mitochondrial; Protozoan Mitochondrial; Coelenterate Mitochondrial; Mycoplasma; Spiroplasma',
alt_name = 'SGC3', id = 4,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W', 'CTT': 'L',
'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R',
'AGG': 'R', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D',
'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G',
'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', ],
start_codons = [ 'TTA', 'TTG', 'CTG', 'ATT', 'ATC',
'ATA', 'ATG', 'GTG', ]
)
register_ncbi_table(name = 'Invertebrate Mitochondrial',
alt_name = 'SGC4', id = 5,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W', 'CTT': 'L',
'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'M', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'S',
'AGG': 'S', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D',
'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G',
'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', ],
start_codons = [ 'TTG', 'ATT', 'ATC', 'ATA', 'ATG',
'GTG', ]
)
register_ncbi_table(name = 'Ciliate Nuclear; Dasycladacean Nuclear; Hexamita Nuclear',
alt_name = 'SGC5', id = 6,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TAA': 'Q', 'TAG': 'Q', 'TGT': 'C', 'TGC': 'C', 'TGG': 'W',
'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P',
'CCC': 'P', 'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H',
'CAA': 'Q', 'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R',
'CGG': 'R', 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N',
'AAC': 'N', 'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S',
'AGA': 'R', 'AGG': 'R', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V',
'GTG': 'V', 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G',
'GGC': 'G', 'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TGA', ],
start_codons = [ 'ATG', ]
)
register_ncbi_table(name = 'Echinoderm Mitochondrial',
alt_name = 'SGC8', id = 9,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W', 'CTT': 'L',
'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'N', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'S',
'AGG': 'S', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D',
'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G',
'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', ],
start_codons = [ 'ATG', ]
)
register_ncbi_table(name = 'Euplotid Nuclear',
alt_name = 'SGC9', id = 10,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGA': 'C', 'TGG': 'W', 'CTT': 'L',
'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R',
'AGG': 'R', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D',
'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G',
'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', ],
start_codons = [ 'ATG', ]
)
register_ncbi_table(name = 'Bacterial',
alt_name = None, id = 11,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGG': 'W', 'CTT': 'L', 'CTC': 'L',
'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P', 'CCA': 'P',
'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R', 'ATT': 'I',
'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T', 'ACC': 'T',
'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N', 'AAA': 'K',
'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V', 'GCT': 'A',
'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D', 'GAC': 'D',
'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G', 'GGA': 'G',
'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', 'TGA', ],
start_codons = [ 'TTG', 'CTG', 'ATT', 'ATC', 'ATA',
'ATG', 'GTG', ]
)
register_ncbi_table(name = 'Alternative Yeast Nuclear',
alt_name = None, id = 12,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGG': 'W', 'CTT': 'L', 'CTC': 'L',
'CTA': 'L', 'CTG': 'S', 'CCT': 'P', 'CCC': 'P', 'CCA': 'P',
'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R', 'ATT': 'I',
'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T', 'ACC': 'T',
'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N', 'AAA': 'K',
'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V', 'GCT': 'A',
'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D', 'GAC': 'D',
'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G', 'GGA': 'G',
'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', 'TGA', ],
start_codons = [ 'CTG', 'ATG', ]
)
register_ncbi_table(name = 'Ascidian Mitochondrial',
alt_name = None, id = 13,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W', 'CTT': 'L',
'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'M', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'G',
'AGG': 'G', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D',
'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G',
'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TAG', ],
start_codons = [ 'ATG', ]
)
register_ncbi_table(name = 'Flatworm Mitochondrial',
alt_name = None, id = 14,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TAA': 'Y', 'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W',
'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P',
'CCC': 'P', 'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H',
'CAA': 'Q', 'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R',
'CGG': 'R', 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N',
'AAC': 'N', 'AAA': 'N', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S',
'AGA': 'S', 'AGG': 'S', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V',
'GTG': 'V', 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G',
'GGC': 'G', 'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAG', ],
start_codons = [ 'ATG', ]
)
register_ncbi_table(name = 'Blepharisma Macronuclear',
alt_name = None, id = 15,
table = {
'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L', 'TCT': 'S',
'TCC': 'S', 'TCA': 'S', 'TCG': 'S', 'TAT': 'Y', 'TAC': 'Y',
'TAG': 'Q', 'TGT': 'C', 'TGC': 'C', 'TGG': 'W', 'CTT': 'L',
'CTC': 'L', 'CTA': 'L', 'CTG': 'L', 'CCT': 'P', 'CCC': 'P',
'CCA': 'P', 'CCG': 'P', 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q',
'CAG': 'Q', 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M', 'ACT': 'T',
'ACC': 'T', 'ACA': 'T', 'ACG': 'T', 'AAT': 'N', 'AAC': 'N',
'AAA': 'K', 'AAG': 'K', 'AGT': 'S', 'AGC': 'S', 'AGA': 'R',
'AGG': 'R', 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A', 'GAT': 'D',
'GAC': 'D', 'GAA': 'E', 'GAG': 'E', 'GGT': 'G', 'GGC': 'G',
'GGA': 'G', 'GGG': 'G', },
stop_codons = [ 'TAA', 'TGA', ],
start_codons = [ 'ATG', ]
)
######### Deal with ambiguous forward translations
class AmbiguousCodonTable(CodonTable):
def __init__(self, codon_table,
ambiguous_nucleotide_alphabet,
ambiguous_nucleotide_values,
ambiguous_protein_alphabet,
ambiguous_protein_values):
CodonTable.__init__(self,
ambiguous_nucleotide_alphabet,
ambiguous_protein_alphabet,
AmbiguousForwardTable(codon_table.forward_table,
ambiguous_nucleotide_values,
ambiguous_protein_values),
codon_table.back_table,
# These two are WRONG! I need to get the
# list of ambiguous codons which code for
# the stop codons XXX
list_ambiguous_codons(codon_table.start_codons),
list_ambiguous_codons(codon_table.stop_codons)
)
self._codon_table = codon_table
# Be sneaky and forward attribute lookups to the original table.
# This lets us get the names, if the original table is an NCBI
# table.
def __getattr__(self, name):
return getattr(self._codon_table, name)
def list_possible_proteins(codon, forward_table, ambiguous_nucleotide_values):
c1, c2, c3 = codon
x1 = ambiguous_nucleotide_values[c1]
x2 = ambiguous_nucleotide_values[c2]
x3 = ambiguous_nucleotide_values[c3]
possible = {}
stops = []
for y1 in x1:
for y2 in x2:
for y3 in x3:
try:
possible[forward_table[y1+y2+y3]] = 1
except KeyError:
# If tripping over a stop codon
stops.append(y1+y2+y3)
if stops:
if possible.keys():
raise TranslationError, ("ambiguous codon codes for both proteins and stop codons", codon)
# This is a true stop codon - tell the caller about it
raise KeyError, codon
return possible.keys()
def list_ambiguous_codons(codons):
# XXX not implemented!
return codons
# Forward translation is "onto", that is, any given codon always maps
# to the same protein, or it doesn't map at all. Thus, I can build
# off of an existing table to produce the ambiguous mappings.
#
# This handles the general case. Perhaps it's overkill?
# >>> t = CodonTable.ambiguous_dna_by_id[1]
# >>> t.forward_table["AAT"]
# 'N'
# >>> t.forward_table["GAT"]
# 'D'
# >>> t.forward_table["RAT"]
# 'B'
# >>> t.forward_table["YTA"]
# 'L'
class AmbiguousForwardTable:
def __init__(self, forward_table, ambiguous_nucleotide, ambiguous_protein):
self.forward_table = forward_table
self.ambiguous_nucleotide = ambiguous_nucleotide
self.ambiguous_protein = ambiguous_protein
inverted = {}
for name, val in ambiguous_protein.items():
for c in val:
x = inverted.get(c, {})
x[name] = 1
inverted[c] = x
for name, val in inverted.items():
inverted[name] = val.keys()
self._inverted = inverted
self._cache = {}
def get(self, codon, failobj = None):
try:
return self.__getitem__(codon)
except KeyError:
return failobj
def __getitem__(self, codon):
try:
x = self._cache[codon]
except KeyError:
pass
else:
if x is TranslationError:
raise TranslationError, codon # no unique translation
if x is KeyError:
raise KeyError, codon # it's a stop codon
return x
try:
x = self.forward_table[codon]
self._cache[codon] = x
return x
except KeyError:
pass
# XXX Need to make part of this into a method which returns
# a list of all possible encodings for a codon!
try:
possible = list_possible_proteins(codon,
self.forward_table,
self.ambiguous_nucleotide)
except KeyError:
self._cache[codon] = KeyError
raise KeyError, codon # stop codon
except TranslationError:
self._cache[codon] = TranslationError
raise TranslationError, codon # does not code
assert len(possible) > 0, "unambiguous codons must code"
# Hah! Only one possible protein, so use it
if len(possible) == 1:
self._cache[codon] = possible[0]
return possible[0]
# See if there's an ambiguous protein encoding for the multiples.
# Find residues which exist in every coding set.
ambiguous_possible = {}
for amino in possible:
for term in self._inverted[amino]:
ambiguous_possible[term] = ambiguous_possible.get(term, 0) + 1
n = len(possible)
possible = []
for amino, val in ambiguous_possible.items():
if val == n:
possible.append(amino)
# No amino acid encoding for the results
if len(possible) == 0:
self._cache[codon] = TranslationError
raise TranslationError, codon # no valid translation
# All of these are valid, so choose one
# To be unique, sort by smallet ambiguity then alphabetically
# Can get this if "X" encodes for everything.
def _sort(x, y, table = self.ambiguous_protein):
a = cmp(len(table[x]), len(table[y]))
if a == 0:
return cmp(x, y)
return a
possible.sort(_sort)
x = possible[0]
self._cache[codon] = x
return x
ambiguous_dna_by_name = {}
for key, val in unambiguous_dna_by_name.items():
ambiguous_dna_by_name[key] = AmbiguousCodonTable(val,
IUPAC.ambiguous_dna,
IUPACData.ambiguous_dna_values,
IUPAC.extended_protein,
IUPACData.extended_protein_values)
ambiguous_dna_by_id = {}
for key, val in unambiguous_dna_by_id.items():
ambiguous_dna_by_id[key] = AmbiguousCodonTable(val,
IUPAC.ambiguous_dna,
IUPACData.ambiguous_dna_values,
IUPAC.extended_protein,
IUPACData.extended_protein_values)
ambiguous_rna_by_name = {}
for key, val in unambiguous_rna_by_name.items():
ambiguous_rna_by_name[key] = AmbiguousCodonTable(val,
IUPAC.ambiguous_rna,
IUPACData.ambiguous_rna_values,
IUPAC.extended_protein,
IUPACData.extended_protein_values)
ambiguous_rna_by_id = {}
for key, val in unambiguous_rna_by_id.items():
ambiguous_rna_by_id[key] = AmbiguousCodonTable(val,
IUPAC.ambiguous_rna,
IUPACData.ambiguous_rna_values,
IUPAC.extended_protein,
IUPACData.extended_protein_values)
del key, val
|
