-
Notifications
You must be signed in to change notification settings - Fork 1.7k
/
Restriction.py
2427 lines (1962 loc) · 81.3 KB
/
Restriction.py
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
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python
#
# Restriction Analysis Libraries.
# Copyright (C) 2004. Frederic Sohm.
#
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
#
""" Notes about the diverses class of the restriction enzyme implementation.
RestrictionType is the type of all restriction enzymes.
----------------------------------------------------------------------------
AbstractCut implements some methods that are common to all enzymes.
----------------------------------------------------------------------------
NoCut, OneCut,TwoCuts represent the number of double strand cuts
produced by the enzyme.
they correspond to the 4th field of the rebase
record emboss_e.NNN.
0->NoCut : the enzyme is not characterised.
2->OneCut : the enzyme produce one double strand cut.
4->TwoCuts : two double strand cuts.
----------------------------------------------------------------------------
Meth_Dep, Meth_Undep represent the methylation susceptibility to
the enzyme.
Not implemented yet.
----------------------------------------------------------------------------
Palindromic, if the site is palindromic or not.
NotPalindromic allow some optimisations of the code.
No need to check the reverse strand
with palindromic sites.
----------------------------------------------------------------------------
Unknown, Blunt, represent the overhang.
Ov5, Ov3 Unknown is here for symetry reasons and
correspond to enzymes that are not characterised
in rebase.
----------------------------------------------------------------------------
Defined, Ambiguous, represent the sequence of the overhang.
NotDefined
NotDefined is for enzymes not characterised in
rebase.
Defined correspond to enzymes that display a
constant overhang whatever the sequence.
ex : EcoRI. G^AATTC -> overhang :AATT
CTTAA^G
Ambiguous : the overhang varies with the
sequence restricted.
Typically enzymes which cut outside their
restriction site or (but not always)
inside an ambiguous site.
ex:
AcuI CTGAAG(22/20) -> overhang : NN
AasI GACNNN^NNNGTC -> overhang : NN
CTGN^NNNNNCAG
note : these 3 classes refers to the overhang not the site.
So the enzyme ApoI (RAATTY) is defined even if its restriction
site is ambiguous.
ApoI R^AATTY -> overhang : AATT -> Defined
YTTAA^R
Accordingly, blunt enzymes are always Defined even
when they cut outside their restriction site.
----------------------------------------------------------------------------
Not_available, as found in rebase file emboss_r.NNN files.
Commercially_available
allow the selection of the enzymes according to
their suppliers to reduce the quantity
of results.
Also will allow the implementation of buffer
compatibility tables. Not implemented yet.
the list of suppliers is extracted from
emboss_s.NNN
----------------------------------------------------------------------------
"""
import re
import itertools
from Bio.Seq import Seq, MutableSeq
from Bio.Alphabet import IUPAC
from Bio.Restriction.Restriction_Dictionary import rest_dict as enzymedict
from Bio.Restriction.Restriction_Dictionary import typedict
from Bio.Restriction.Restriction_Dictionary import suppliers as suppliers_dict
from Bio.Restriction.RanaConfig import *
from Bio.Restriction.PrintFormat import PrintFormat
#Used to use Bio.Restriction.DNAUtils.check_bases (and expose it under this
#namespace), but have deprecated that module.
def _check_bases(seq_string):
"""Check characters in a string (PRIVATE).
Remove digits and white space present in string. Allows any valid ambiguous
IUPAC DNA single letters codes (ABCDGHKMNRSTVWY, lower case are converted).
Other characters (e.g. symbols) trigger a TypeError.
Returns the string WITH A LEADING SPACE (!). This is for backwards
compatibility, and may in part be explained by the fact that
Bio.Restriction doesn't use zero based counting.
"""
#Remove white space and make upper case:
seq_string = "".join(seq_string.split()).upper()
#Remove digits
for c in "0123456789" : seq_string = seq_string.replace(c,"")
#Check only allowed IUPAC letters
if not set(seq_string).issubset(set("ABCDGHKMNRSTVWY")) :
raise TypeError("Invalid character found in %s" % repr(seq_string))
return " " + seq_string
matching = {'A' : 'ARWMHVDN', 'C' : 'CYSMHBVN', 'G' : 'GRSKBVDN',
'T' : 'TYWKHBDN', 'R' : 'ABDGHKMNSRWV', 'Y' : 'CBDHKMNSTWVY',
'W' : 'ABDHKMNRTWVY', 'S' : 'CBDGHKMNSRVY', 'M' : 'ACBDHMNSRWVY',
'K' : 'BDGHKNSRTWVY', 'H' : 'ACBDHKMNSRTWVY',
'B' : 'CBDGHKMNSRTWVY', 'V' : 'ACBDGHKMNSRWVY',
'D' : 'ABDGHKMNSRTWVY', 'N' : 'ACBDGHKMNSRTWVY'}
DNA = Seq
class FormattedSeq(object):
"""FormattedSeq(seq, [linear=True])-> new FormattedSeq.
Translate a Bio.Seq into a formatted sequence to be used with Restriction.
Roughly:
remove anything which is not IUPAC alphabet and then add a space
in front of the sequence to get a biological index instead of a
python index (i.e. index of the first base is 1 not 0).
Retains information about the shape of the molecule linear (default)
or circular. Restriction sites are search over the edges of circular
sequence."""
def __init__(self, seq, linear = True):
"""FormattedSeq(seq, [linear=True])-> new FormattedSeq.
seq is either a Bio.Seq, Bio.MutableSeq or a FormattedSeq.
if seq is a FormattedSeq, linear will have no effect on the
shape of the sequence."""
if isinstance(seq, Seq) or isinstance(seq, MutableSeq):
stringy = seq.tostring()
self.lower = stringy.islower()
#Note this adds a leading space to the sequence (!)
self.data = _check_bases(stringy)
self.linear = linear
self.klass = seq.__class__
self.alphabet = seq.alphabet
elif isinstance(seq, FormattedSeq):
self.lower = seq.lower
self.data = seq.data
self.linear = seq.linear
self.alphabet = seq.alphabet
self.klass = seq.klass
else:
raise TypeError('expected Seq or MutableSeq, got %s' % type(seq))
def __len__(self):
return len(self.data) - 1
def __repr__(self):
return 'FormattedSeq(%s, linear=%s)' %(repr(self[1:]), repr(self.linear))
def __eq__(self, other):
if isinstance(other, FormattedSeq):
if repr(self) == repr(other):
return True
else:
return False
return False
def circularise(self):
"""FS.circularise() -> circularise FS"""
self.linear = False
return
def linearise(self):
"""FS.linearise() -> linearise FS"""
self.linear = True
return
def to_linear(self):
"""FS.to_linear() -> new linear FS instance"""
new = self.__class__(self)
new.linear = True
return new
def to_circular(self):
"""FS.to_circular() -> new circular FS instance"""
new = self.__class__(self)
new.linear = False
return new
def is_linear(self):
"""FS.is_linear() -> bool.
True if the sequence will analysed as a linear sequence."""
return self.linear
def finditer(self, pattern, size):
"""FS.finditer(pattern, size) -> list.
return a list of pattern into the sequence.
the list is made of tuple (location, pattern.group).
the latter is used with non palindromic sites.
pattern is the regular expression pattern corresponding to the
enzyme restriction site.
size is the size of the restriction enzyme recognition-site size."""
if self.is_linear():
data = self.data
else:
data = self.data + self.data[1:size]
return [(i.start(), i.group) for i in re.finditer(pattern, data)]
def __getitem__(self, i):
if self.lower:
return self.klass((self.data[i]).lower(), self.alphabet)
return self.klass(self.data[i], self.alphabet)
class RestrictionType(type):
"""RestrictionType. Type from which derives all enzyme classes.
Implement the operator methods."""
def __init__(cls, name='', bases=(), dct={}):
"""RE(name, bases, dct) -> RestrictionType instance.
Not intended to be used in normal operation. The enzymes are
instantiated when importing the module.
see below."""
if "-" in name :
raise ValueError("Problem with hyphen in %s as enzyme name" \
% repr(name))
super(RestrictionType, cls).__init__(cls, name, bases, dct)
try :
cls.compsite = re.compile(cls.compsite)
except Exception, err :
raise ValueError("Problem with regular expression, re.compiled(%s)" \
% repr(cls.compsite))
def __add__(cls, other):
"""RE.__add__(other) -> RestrictionBatch().
if other is an enzyme returns a batch of the two enzymes.
if other is already a RestrictionBatch add enzyme to it."""
if isinstance(other, RestrictionType):
return RestrictionBatch([cls, other])
elif isinstance(other, RestrictionBatch):
return other.add_nocheck(cls)
else:
raise TypeError
def __div__(cls, other):
"""RE.__div__(other) -> list.
RE/other
returns RE.search(other)."""
return cls.search(other)
def __rdiv__(cls, other):
"""RE.__rdiv__(other) -> list.
other/RE
returns RE.search(other)."""
return cls.search(other)
def __truediv__(cls, other):
"""RE.__truediv__(other) -> list.
RE/other
returns RE.search(other)."""
return cls.search(other)
def __rtruediv__(cls, other):
"""RE.__rtruediv__(other) -> list.
other/RE
returns RE.search(other)."""
return cls.search(other)
def __floordiv__(cls, other):
"""RE.__floordiv__(other) -> list.
RE//other
returns RE.catalyse(other)."""
return cls.catalyse(other)
def __rfloordiv__(cls, other):
"""RE.__rfloordiv__(other) -> list.
other//RE
returns RE.catalyse(other)."""
return cls.catalyse(other)
def __str__(cls):
"""RE.__str__() -> str.
return the name of the enzyme."""
return cls.__name__
def __repr__(cls):
"""RE.__repr__() -> str.
used with eval or exec will instantiate the enzyme."""
return "%s" % cls.__name__
def __len__(cls):
"""RE.__len__() -> int.
length of the recognition site."""
return cls.size
def __hash__(cls):
#Python default is to use id(...)
#This is consistent with the __eq__ implementation
return id(cls)
def __eq__(cls, other):
"""RE == other -> bool
True if RE and other are the same enzyme.
Specifically this checks they are the same Python object.
"""
#assert (id(cls)==id(other)) == (other is cls) == (cls is other)
return id(cls)==id(other)
def __ne__(cls, other):
"""RE != other -> bool.
isoschizomer strict, same recognition site, same restriction -> False
all the other-> True
WARNING - This is not the inverse of the __eq__ method.
"""
if not isinstance(other, RestrictionType):
return True
elif cls.charac == other.charac:
return False
else:
return True
def __rshift__(cls, other):
"""RE >> other -> bool.
neoschizomer : same recognition site, different restriction. -> True
all the others : -> False"""
if not isinstance(other, RestrictionType):
return False
elif cls.site == other.site and cls.charac != other.charac:
return True
else:
return False
def __mod__(cls, other):
"""a % b -> bool.
Test compatibility of the overhang of a and b.
True if a and b have compatible overhang."""
if not isinstance(other, RestrictionType):
raise TypeError( \
'expected RestrictionType, got %s instead' % type(other))
return cls._mod1(other)
def __ge__(cls, other):
"""a >= b -> bool.
a is greater or equal than b if the a site is longer than b site.
if their site have the same length sort by alphabetical order of their
names."""
if not isinstance(other, RestrictionType):
raise NotImplementedError
if len(cls) > len(other):
return True
elif cls.size == len(other) and cls.__name__ >= other.__name__:
return True
else:
return False
def __gt__(cls, other):
"""a > b -> bool.
sorting order:
1. size of the recognition site.
2. if equal size, alphabetical order of the names."""
if not isinstance(other, RestrictionType):
raise NotImplementedError
if len(cls) > len(other):
return True
elif cls.size == len(other) and cls.__name__ > other.__name__:
return True
else:
return False
def __le__(cls, other):
"""a <= b -> bool.
sorting order:
1. size of the recognition site.
2. if equal size, alphabetical order of the names."""
if not isinstance(other, RestrictionType):
raise NotImplementedError
elif len(cls) < len(other):
return True
elif len(cls) == len(other) and cls.__name__ <= other.__name__:
return True
else:
return False
def __lt__(cls, other):
"""a < b -> bool.
sorting order:
1. size of the recognition site.
2. if equal size, alphabetical order of the names."""
if not isinstance(other, RestrictionType):
raise NotImplementedError
elif len(cls) < len(other):
return True
elif len(cls) == len(other) and cls.__name__ < other.__name__:
return True
else:
return False
class AbstractCut(RestrictionType):
"""Implement the methods that are common to all restriction enzymes.
All the methods are classmethod.
For internal use only. Not meant to be instantiate."""
def search(cls, dna, linear=True):
"""RE.search(dna, linear=True) -> list.
return a list of all the site of RE in dna. Compensate for circular
sequences and so on.
dna must be a Bio.Seq.Seq instance or a Bio.Seq.MutableSeq instance.
if linear is False, the restriction sites than span over the boundaries
will be included.
The positions are the first base of the 3' fragment,
i.e. the first base after the position the enzyme will cut. """
#
# Separating search from _search allow a (very limited) optimisation
# of the search when using a batch of restriction enzymes.
# in this case the DNA is tested once by the class which implements
# the batch instead of being tested by each enzyme single.
# see RestrictionBatch.search() for example.
#
if isinstance(dna, FormattedSeq):
cls.dna = dna
return cls._search()
else :
cls.dna = FormattedSeq(dna, linear)
return cls._search()
search = classmethod(search)
def all_suppliers(self):
"""RE.all_suppliers -> print all the suppliers of R"""
supply = [x[0] for x in suppliers_dict.itervalues()]
supply.sort()
print ",\n".join(supply)
return
all_suppliers = classmethod(all_suppliers)
def is_equischizomer(self, other):
"""RE.is_equischizomers(other) -> bool.
True if other is an isoschizomer of RE.
False else.
equischizomer <=> same site, same position of restriction."""
return not self != other
is_equischizomer = classmethod(is_equischizomer)
def is_neoschizomer(self, other):
"""RE.is_neoschizomers(other) -> bool.
True if other is an isoschizomer of RE.
False else.
neoschizomer <=> same site, different position of restriction."""
return self >> other
is_neoschizomer = classmethod(is_neoschizomer)
def is_isoschizomer(self, other):
"""RE.is_isoschizomers(other) -> bool.
True if other is an isoschizomer of RE.
False else.
isoschizomer <=> same site."""
return (not self != other) or self >> other
is_isoschizomer = classmethod(is_isoschizomer)
def equischizomers(self, batch=None):
"""RE.equischizomers([batch]) -> list.
return a tuple of all the isoschizomers of RE.
if batch is supplied it is used instead of the default AllEnzymes.
equischizomer <=> same site, same position of restriction."""
if not batch : batch = AllEnzymes
r = [x for x in batch if not self != x]
i = r.index(self)
del r[i]
r.sort()
return r
equischizomers = classmethod(equischizomers)
def neoschizomers(self, batch=None):
"""RE.neoschizomers([batch]) -> list.
return a tuple of all the neoschizomers of RE.
if batch is supplied it is used instead of the default AllEnzymes.
neoschizomer <=> same site, different position of restriction."""
if not batch : batch = AllEnzymes
r = [x for x in batch if self >> x]
r.sort()
return r
neoschizomers = classmethod(neoschizomers)
def isoschizomers(self, batch=None):
"""RE.isoschizomers([batch]) -> list.
return a tuple of all the equischizomers and neoschizomers of RE.
if batch is supplied it is used instead of the default AllEnzymes."""
if not batch : batch = AllEnzymes
r = [x for x in batch if (self >> x) or (not self != x)]
i = r.index(self)
del r[i]
r.sort()
return r
isoschizomers = classmethod(isoschizomers)
def frequency(self):
"""RE.frequency() -> int.
frequency of the site."""
return self.freq
frequency = classmethod(frequency)
class NoCut(AbstractCut):
"""Implement the methods specific to the enzymes that do not cut.
These enzymes are generally enzymes that have been only partially
characterised and the way they cut the DNA is unknow or enzymes for
which the pattern of cut is to complex to be recorded in Rebase
(ncuts values of 0 in emboss_e.###).
When using search() with these enzymes the values returned are at the start of
the restriction site.
Their catalyse() method returns a TypeError.
Unknown and NotDefined are also part of the base classes of these enzymes.
Internal use only. Not meant to be instantiated."""
def cut_once(self):
"""RE.cut_once() -> bool.
True if the enzyme cut the sequence one time on each strand."""
return False
cut_once = classmethod(cut_once)
def cut_twice(self):
"""RE.cut_twice() -> bool.
True if the enzyme cut the sequence twice on each strand."""
return False
cut_twice = classmethod(cut_twice)
def _modify(self, location):
"""RE._modify(location) -> int.
for internal use only.
location is an integer corresponding to the location of the match for
the enzyme pattern in the sequence.
_modify returns the real place where the enzyme will cut.
example:
EcoRI pattern : GAATTC
EcoRI will cut after the G.
so in the sequence:
______
GAATACACGGAATTCGA
|
10
dna.finditer(GAATTC, 6) will return 10 as G is the 10th base
EcoRI cut after the G so:
EcoRI._modify(10) -> 11.
if the enzyme cut twice _modify will returns two integer corresponding
to each cutting site.
"""
yield location
_modify = classmethod(_modify)
def _rev_modify(self, location):
"""RE._rev_modify(location) -> generator of int.
for internal use only.
as _modify for site situated on the antiparallel strand when the
enzyme is not palindromic
"""
yield location
_rev_modify = classmethod(_rev_modify)
def characteristic(self):
"""RE.characteristic() -> tuple.
the tuple contains the attributes:
fst5 -> first 5' cut ((current strand) or None
fst3 -> first 3' cut (complementary strand) or None
scd5 -> second 5' cut (current strand) or None
scd5 -> second 3' cut (complementary strand) or None
site -> recognition site."""
return None, None, None, None, self.site
characteristic = classmethod(characteristic)
class OneCut(AbstractCut):
"""Implement the methods specific to the enzymes that cut the DNA only once
Correspond to ncuts values of 2 in emboss_e.###
Internal use only. Not meant to be instantiated."""
def cut_once(self):
"""RE.cut_once() -> bool.
True if the enzyme cut the sequence one time on each strand."""
return True
cut_once = classmethod(cut_once)
def cut_twice(self):
"""RE.cut_twice() -> bool.
True if the enzyme cut the sequence twice on each strand."""
return False
cut_twice = classmethod(cut_twice)
def _modify(self, location):
"""RE._modify(location) -> int.
for internal use only.
location is an integer corresponding to the location of the match for
the enzyme pattern in the sequence.
_modify returns the real place where the enzyme will cut.
example:
EcoRI pattern : GAATTC
EcoRI will cut after the G.
so in the sequence:
______
GAATACACGGAATTCGA
|
10
dna.finditer(GAATTC, 6) will return 10 as G is the 10th base
EcoRI cut after the G so:
EcoRI._modify(10) -> 11.
if the enzyme cut twice _modify will returns two integer corresponding
to each cutting site.
"""
yield location + self.fst5
_modify = classmethod(_modify)
def _rev_modify(self, location):
"""RE._rev_modify(location) -> generator of int.
for internal use only.
as _modify for site situated on the antiparallel strand when the
enzyme is not palindromic
"""
yield location - self.fst3
_rev_modify = classmethod(_rev_modify)
def characteristic(self):
"""RE.characteristic() -> tuple.
the tuple contains the attributes:
fst5 -> first 5' cut ((current strand) or None
fst3 -> first 3' cut (complementary strand) or None
scd5 -> second 5' cut (current strand) or None
scd5 -> second 3' cut (complementary strand) or None
site -> recognition site."""
return self.fst5, self.fst3, None, None, self.site
characteristic = classmethod(characteristic)
class TwoCuts(AbstractCut):
"""Implement the methods specific to the enzymes that cut the DNA twice
Correspond to ncuts values of 4 in emboss_e.###
Internal use only. Not meant to be instantiated."""
def cut_once(self):
"""RE.cut_once() -> bool.
True if the enzyme cut the sequence one time on each strand."""
return False
cut_once = classmethod(cut_once)
def cut_twice(self):
"""RE.cut_twice() -> bool.
True if the enzyme cut the sequence twice on each strand."""
return True
cut_twice = classmethod(cut_twice)
def _modify(self, location):
"""RE._modify(location) -> int.
for internal use only.
location is an integer corresponding to the location of the match for
the enzyme pattern in the sequence.
_modify returns the real place where the enzyme will cut.
example:
EcoRI pattern : GAATTC
EcoRI will cut after the G.
so in the sequence:
______
GAATACACGGAATTCGA
|
10
dna.finditer(GAATTC, 6) will return 10 as G is the 10th base
EcoRI cut after the G so:
EcoRI._modify(10) -> 11.
if the enzyme cut twice _modify will returns two integer corresponding
to each cutting site.
"""
yield location + self.fst5
yield location + self.scd5
_modify = classmethod(_modify)
def _rev_modify(self, location):
"""RE._rev_modify(location) -> generator of int.
for internal use only.
as _modify for site situated on the antiparallel strand when the
enzyme is not palindromic
"""
yield location - self.fst3
yield location - self.scd3
_rev_modify = classmethod(_rev_modify)
def characteristic(self):
"""RE.characteristic() -> tuple.
the tuple contains the attributes:
fst5 -> first 5' cut ((current strand) or None
fst3 -> first 3' cut (complementary strand) or None
scd5 -> second 5' cut (current strand) or None
scd5 -> second 3' cut (complementary strand) or None
site -> recognition site."""
return self.fst5, self.fst3, self.scd5, self.scd3, self.site
characteristic = classmethod(characteristic)
class Meth_Dep(AbstractCut):
"""Implement the information about methylation.
Enzymes of this class possess a site which is methylable."""
def is_methylable(self):
"""RE.is_methylable() -> bool.
True if the recognition site is a methylable."""
return True
is_methylable = classmethod(is_methylable)
class Meth_Undep(AbstractCut):
"""Implement informations about methylation sensitibility.
Enzymes of this class are not sensible to methylation."""
def is_methylable(self):
"""RE.is_methylable() -> bool.
True if the recognition site is a methylable."""
return False
is_methylable = classmethod(is_methylable)
class Palindromic(AbstractCut):
"""Implement the methods specific to the enzymes which are palindromic
palindromic means : the recognition site and its reverse complement are
identical.
Remarks : an enzyme with a site CGNNCG is palindromic even if some
of the sites that it will recognise are not.
for example here : CGAACG
Internal use only. Not meant to be instantiated."""
def _search(self):
"""RE._search() -> list.
for internal use only.
implement the search method for palindromic and non palindromic enzyme.
"""
siteloc = self.dna.finditer(self.compsite,self.size)
self.results = [r for s,g in siteloc for r in self._modify(s)]
if self.results : self._drop()
return self.results
_search = classmethod(_search)
def is_palindromic(self):
"""RE.is_palindromic() -> bool.
True if the recognition site is a palindrom."""
return True
is_palindromic = classmethod(is_palindromic)
class NonPalindromic(AbstractCut):
"""Implement the methods specific to the enzymes which are not palindromic
palindromic means : the recognition site and its reverse complement are
identical.
Internal use only. Not meant to be instantiated."""
def _search(self):
"""RE._search() -> list.
for internal use only.
implement the search method for palindromic and non palindromic enzyme.
"""
iterator = self.dna.finditer(self.compsite, self.size)
self.results = []
modif = self._modify
revmodif = self._rev_modify
s = str(self)
self.on_minus = []
for start, group in iterator:
if group(s):
self.results += [r for r in modif(start)]
else:
self.on_minus += [r for r in revmodif(start)]
self.results += self.on_minus
if self.results:
self.results.sort()
self._drop()
return self.results
_search = classmethod(_search)
def is_palindromic(self):
"""RE.is_palindromic() -> bool.
True if the recognition site is a palindrom."""
return False
is_palindromic = classmethod(is_palindromic)
class Unknown(AbstractCut):
"""Implement the methods specific to the enzymes for which the overhang
is unknown.
These enzymes are also NotDefined and NoCut.
Internal use only. Not meant to be instantiated."""
def catalyse(self, dna, linear=True):
"""RE.catalyse(dna, linear=True) -> tuple of DNA.
RE.catalyze(dna, linear=True) -> tuple of DNA.
return a tuple of dna as will be produced by using RE to restrict the
dna.
dna must be a Bio.Seq.Seq instance or a Bio.Seq.MutableSeq instance.
if linear is False, the sequence is considered to be circular and the
output will be modified accordingly."""
raise NotImplementedError('%s restriction is unknown.' \
% self.__name__)
catalyze = catalyse = classmethod(catalyse)
def is_blunt(self):
"""RE.is_blunt() -> bool.
True if the enzyme produces blunt end.
see also:
RE.is_3overhang()
RE.is_5overhang()
RE.is_unknown()"""
return False
is_blunt = classmethod(is_blunt)
def is_5overhang(self):
"""RE.is_5overhang() -> bool.
True if the enzyme produces 5' overhang sticky end.
see also:
RE.is_3overhang()
RE.is_blunt()
RE.is_unknown()"""
return False
is_5overhang = classmethod(is_5overhang)
def is_3overhang(self):
"""RE.is_3overhang() -> bool.
True if the enzyme produces 3' overhang sticky end.
see also:
RE.is_5overhang()
RE.is_blunt()
RE.is_unknown()"""
return False
is_3overhang = classmethod(is_3overhang)
def overhang(self):
"""RE.overhang() -> str. type of overhang of the enzyme.,
can be "3' overhang", "5' overhang", "blunt", "unknown" """
return 'unknown'
overhang = classmethod(overhang)
def compatible_end(self):
"""RE.compatible_end() -> list.
list of all the enzymes that share compatible end with RE."""
return []
compatible_end = classmethod(compatible_end)
def _mod1(self, other):
"""RE._mod1(other) -> bool.
for internal use only
test for the compatibility of restriction ending of RE and other."""
return False
_mod1 = classmethod(_mod1)
class Blunt(AbstractCut):
"""Implement the methods specific to the enzymes for which the overhang
is blunt.
The enzyme cuts the + strand and the - strand of the DNA at the same
place.
Internal use only. Not meant to be instantiated."""
def catalyse(self, dna, linear=True):
"""RE.catalyse(dna, linear=True) -> tuple of DNA.
RE.catalyze(dna, linear=True) -> tuple of DNA.
return a tuple of dna as will be produced by using RE to restrict the
dna.
dna must be a Bio.Seq.Seq instance or a Bio.Seq.MutableSeq instance.
if linear is False, the sequence is considered to be circular and the
output will be modified accordingly."""
r = self.search(dna, linear)
d = self.dna
if not r : return d[1:],
fragments = []
length = len(r)-1
if d.is_linear():
#
# START of the sequence to FIRST site.
#
fragments.append(d[1:r[0]])
if length:
#
# if more than one site add them.
#
fragments += [d[r[x]:r[x+1]] for x in xrange(length)]
#
# LAST site to END of the sequence.
#
fragments.append(d[r[-1]:])
else:
#
# circular : bridge LAST site to FIRST site.