def cut(self, *enzymes):
"""Returns a list of linear Dseq fragments produced in the digestion.
If there are no cuts, an empty list is returned.
Parameters
----------
enzymes : enzyme object or iterable of such objects
A Bio.Restriction.XXX restriction objects or iterable.
Returns
-------
frags : list
list of Dseq objects formed by the digestion
Examples
--------
>>> from pydna.dseq import Dseq
>>> seq=Dseq("ggatccnnngaattc")
>>> seq
Dseq(-15)
ggatccnnngaattc
cctaggnnncttaag
>>> from Bio.Restriction import BamHI,EcoRI
>>> type(seq.cut(BamHI))
<class 'tuple'>
>>> for frag in seq.cut(BamHI): print(repr(frag))
Dseq(-5)
g
cctag
Dseq(-14)
gatccnnngaattc
gnnncttaag
>>> seq.cut(EcoRI, BamHI) == seq.cut(BamHI, EcoRI)
True
>>> a,b,c = seq.cut(EcoRI, BamHI)
>>> a+b+c
Dseq(-15)
ggatccnnngaattc
cctaggnnncttaag
>>>
"""
pad = "n" * 50
if self.linear:
dsseq = self.mung()
else:
dsseq = Dseq.from_string(self._data, linear=True, circular=False)
if len(enzymes) == 1 and hasattr(enzymes[0],
"intersection"): # RestrictionBatch
enzymecuts = []
for e in enzymes[0]:
# cuts = e.search(dsseq+dsseq[:e.size-1] if self.circular else dsseq)
cuts = e.search(
_Seq(pad + dsseq.watson + dsseq.watson[:e.size - 1] +
pad) if self.circular else dsseq)
enzymecuts.append((cuts, e))
enzymecuts.sort()
enzymes = [e for (c, e) in enzymecuts if c]
else:
enzymes = [
e for e in list(dict.fromkeys(_flatten(enzymes))) if e.search(
_Seq(pad + dsseq.watson + dsseq.watson[:e.size - 1] +
pad) if self.circular else dsseq)
] # flatten
if not enzymes:
return ()
if self.linear:
frags = [self]
else:
l = len(self)
for e in enzymes:
wpos = [
x - len(pad) - 1 for x in e.search(
_Seq(pad + self.watson + self.watson[:e.size - 1]) +
pad)
][::-1]
cpos = [
x - len(pad) - 1 for x in e.search(
_Seq(pad + self.crick + self.crick[:e.size - 1]) + pad)
][::-1]
for w, c in _itertools.product(wpos, cpos):
if w % len(self) == (self.length - c + e.ovhg) % len(self):
frags = [
Dseq(
self.watson[w % l:] + self.watson[:w % l],
self.crick[c % l:] + self.crick[:c % l],
ovhg=e.ovhg,
pos=w,
)
]
break
else:
continue
break
newfrags = []
for enz in enzymes:
for frag in frags:
ws = [x - 1 for x in enz.search(_Seq(frag.watson) + "N")]
cs = [x - 1 for x in enz.search(_Seq(frag.crick) + "N")]
sitepairs = [(sw, sc)
for sw, sc in _itertools.product(ws, cs[::-1])
if (sw + max(0, frag.ovhg) -
max(0, enz.ovhg) == len(frag.crick) - sc -
min(0, frag.ovhg) + min(0, enz.ovhg))]
sitepairs.append((self.length, 0))
w2, c1 = sitepairs[0]
newfrags.append(
Dseq(frag.watson[:w2],
frag.crick[c1:],
ovhg=frag.ovhg,
pos=frag.pos))
for (w1, c2), (w2, c1) in zip(sitepairs[:-1], sitepairs[1:]):
newfrags.append(
Dseq(
frag.watson[w1:w2],
frag.crick[c1:c2],
ovhg=enz.ovhg,
pos=frag.pos + w1 - max(0, enz.ovhg),
))
frags = newfrags
newfrags = []
return tuple(frags)
def pcr(*args, **kwargs):
"""pcr is a convenience function for the Anneal class to simplify its
usage, especially from the command line. If more than one or no PCR
product is formed, a ValueError is raised.
args is any iterable of Dseqrecords or an iterable of iterables of
Dseqrecords. args will be greedily flattened.
Parameters
----------
args : iterable containing sequence objects
Several arguments are also accepted.
limit : int = 13, optional
limit length of the annealing part of the primers.
Notes
-----
sequences in args could be of type:
* string
* Seq
* SeqRecord (or subclass)
* Dseqrecord (or sublcass)
The last sequence will be assumed to be the template while
all preceeding sequences will be assumed to be primers.
This is a powerful function, use with care!
Returns
-------
product : Amplicon
An :class:`pydna.amplicon.Amplicon` object representing the PCR
product. The direction of the PCR product will be the same as for
the template sequence.
Examples
--------
>>> from pydna.dseqrecord import Dseqrecord
>>> from pydna.readers import read
>>> from pydna.amplify import pcr
>>> from pydna.primer import Primer
>>> template = Dseqrecord("tacactcaccgtctatcattatctac\
tatcgactgtatcatctgatagcac")
>>> from Bio.SeqRecord import SeqRecord
>>> p1 = Primer("tacactcaccgtctatcattatc")
>>> p2 = Primer("cgactgtatcatctgatagcac").reverse_complement()
>>> pcr(p1, p2, template)
Amplicon(51)
>>> pcr([p1, p2], template)
Amplicon(51)
>>> pcr((p1,p2,), template)
Amplicon(51)
>>>
"""
output = _flatten(args) # flatten
new = []
for s in output:
if hasattr(s, "watson"):
s = _SeqRecord(_Seq(s.watson))
elif hasattr(s, "transcribe"):
s = _SeqRecord(s)
elif isinstance(s, str):
s = _SeqRecord(_Seq(s))
elif hasattr(s, "features"):
pass
else:
raise TypeError("arguments need to be a string, Bio.Seq, SeqRecord"
", Primer, Dseqrecord or Amplicon object")
new.append(s)
# A single Amplicon object
if len(new) == 1 and hasattr(new[0], "forward_primer"):
new = [new[0].forward_primer, new[0].reverse_primer, new[0]]
if not hasattr(new[-1].seq, "watson"):
new[-1] = _Dseqrecord(s)
anneal_primers = Anneal(new[:-1], new[-1], **kwargs)
if len(anneal_primers.products) == 1:
return anneal_primers.products[0]
elif len(anneal_primers.products) == 0:
raise ValueError("No PCR product! {}".format(anneal_primers.report()))
raise ValueError("PCR not specific! {}".format(anneal_primers.report()))
def number_of_cuts(self, *enzymes):
"""This method returns the number of cuts by digestion with the Restriction enzymes contained in
the iterable."""
return sum([
len(enzyme.search(self.seq)) for enzyme in _flatten(enzymes)
]) # flatten
