def test_preferred_binding(self):
s = Strand('TAGATCCAGTCCACATCGA')
e = strand_to_enzymes(s)
e0 = e[0]
assert (e0.binding_preference == 'C')
s = Strand('CGTCATCTACTGGTTAGC')
e = strand_to_enzymes(s)
e0 = e[0]
assert (e0.binding_preference == 'T')
def test_delete(self):
s = Strand('ACGT')
e = Enzyme([AminoAcid('delete')])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['CGT'])
def test_swi_swi(self):
"""
v
Secondary: ....
Primary: ACGT
^
Copy mode: False
cop
v
Secondary: ..C.
Primary: ACGT
^
Copy mode: True
swi
v
Secondary: TGCA
Primary: .C..
^
Copy mode: True
swi
v
Secondary: ..C.
Primary: ACGT
^
"""
s = Strand('ACGT')
e = Enzyme([AminoAcid('cop'), AminoAcid('swi'), AminoAcid('swi')])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['ACGT', 'C'])
def test_apply_enzyme_ACA(self):
s = Strand('ACA')
e = Enzyme([AminoAcid('delete'), AminoAcid('mvr'), AminoAcid('int')])
final_strands = apply_enzyme(s, e)
assert (isinstance(final_strands[0], Strand) == True)
assert (final_strands[0].strand == 'CAT')
def test_del_gap(self):
"""
delete
v
Secondary: ........CCCC.
Primary: ACGTGGGGGG.GG
^
"""
s = Strand('ACGTGGGGGGGGG')
e = Enzyme([
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('cop'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvl'),
AminoAcid('delete')
])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['ACGTGGGGGG', 'CCCC', 'GG'])
def test_inc_cop(self):
"""
v
Secondary: ....
Primary: ACGT
^
Copy mode: False
cop
v
Secondary: T...
Primary: ACGT
^
Copy mode: True
inc
v
Secondary: TG...
Primary: ACCGT
^
Copy mode: True
['ACCGT', 'GT']
"""
s = Strand('ACGT')
e = Enzyme([AminoAcid('cop'), AminoAcid('inc')])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['ACCGT', 'GT'])
def test_cop_mvl(self):
"""
v
Secondary: ....
Primary: ACGT
^
Copy mode: False
mvr
v
Secondary: ....
Primary: ACGT
^
Copy mode: False
cop
v
Secondary: ...A
Primary: ACGT
^
Copy mode: True
mvl
v
Secondary: ..CA
Primary: ACGT
^
Copy mode: True
['AC', 'ACGT']
"""
s = Strand('ACGT')
e = Enzyme([AminoAcid('mvr'), AminoAcid('cop'), AminoAcid('mvl')])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['AC', 'ACGT'])
def test_punctuation(self):
s = Strand('CGGATACTAAACCGA')
e = strand_to_enzymes(s)
e_known = [Enzyme([AminoAcid('cop'), AminoAcid('ina'), AminoAcid('rpy'), AminoAcid('off')]),
Enzyme([AminoAcid('cut'), AminoAcid('cop')])]
self.assert_enzymes_eq(e, e_known)
def test_mvl_complement_none(self):
s = Strand('TCCGCAATTT')
e = strand_to_enzymes(s)[0]
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['GC', 'TCCGCAATTT'])
def test_strand_to_enzymes(self):
s = Strand('TAGATCCAGTCCACATCGA')
e = strand_to_enzymes(s)
e_known = [Enzyme([AminoAcid('rpy'), AminoAcid('ina'), AminoAcid('rpu'), AminoAcid('mvr'),
AminoAcid('int'), AminoAcid('mvl'), AminoAcid('cut'), AminoAcid('swi'),
AminoAcid('cop')])]
self.assert_enzymes_eq(e, e_known)
def test_apply_longer_enzyme(self):
s = Strand('CAAAGAGAATCCTCTTTGAT')
e = Enzyme([AminoAcid('rpy'), AminoAcid('cop'), AminoAcid('rpu')])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['CAAAGAGAATCCTCTTTGAT', 'CAAAGAGGA'])
def test_ing_cop(self):
"""
v
Secondary: ....
Primary: ACGT
^
Copy mode: False
cop
v
Secondary: T...
Primary: ACGT
^
Copy mode: True
off
v
Secondary: T...
Primary: ACGT
^
Copy mode: False
mvr
v
Secondary: T...
Primary: ACGT
^
Copy mode: False
mvr
v
Secondary: T...
Primary: ACGT
^
Copy mode: False
cop
v
Secondary: T.C.
Primary: ACGT
^
Copy mode: True
ing
v
Secondary: T.CC.
Primary: ACGGT
^
Copy mode: True
['ACGGT', 'CC', 'T']
"""
s = Strand('ACGT')
e = Enzyme([
AminoAcid('cop'),
AminoAcid('off'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('cop'),
AminoAcid('ing')
])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['ACGGT', 'CC', 'T'])
def test_delete_outofbounds(self):
s = Strand('ACGT')
e = Enzyme([
AminoAcid('mvr'),
AminoAcid('delete'),
AminoAcid('delete'),
AminoAcid('delete'),
AminoAcid('inc')
])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['A'])
def test_swi_none(self):
"""
v
Secondary: ....
Primary: ACGT
^
"""
s = Strand('ACGT')
e = Enzyme([AminoAcid('swi')])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['ACGT'])
def apply_enzyme(strand, enzyme, verbose=False):
""" Apply specific enzymes on a strand """
sm = StrandManipulationBuffer(strand.strand)
# find an initial binding pair
while (sm.primary.bound != enzyme.binding_preference):
try:
sm.mvr()
except OutOfStrandException:
# either couldn't find a binding partner or empty strand
# in both cases, just return the original strand
return [strand]
# log initial state, if desired
if verbose:
print sm
# apply the amino acid operations in order, unless we hit the end of a strand
for amino_acid in enzyme.amino_acids:
try:
# call operator
sm(amino_acid.op)
if verbose:
print amino_acid.op
print sm
except OutOfStrandException:
break
# collect all of the strands
strands = []
sm.primary_strands.append(sm.primary.dump())
sm.secondary_strands.append(sm.secondary.dump())
for strand in sm.primary_strands:
for sub_strand in strand.split(
PLACEHOLDER
): # in some cases there might be gaps, so split by the null placeholder
strands.append(sub_strand)
# the upper strands need to be reversed
for strand in sm.secondary_strands:
for sub_strand in strand.split(PLACEHOLDER):
strands.append(sub_strand[::-1])
# remove any empty strands/strings
strands = filter(lambda s: len(s), strands)
return [Strand(s) for s in strands]
def test_cut(self):
"""
v
Secondary: ....
Primary: ACGT
^
Copy mode: False
cut
v
Secondary: .
Primary: A
^
Copy mode: False
['A', 'CGT']
"""
s = Strand('ACGT')
e = Enzyme([AminoAcid('cut')])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['A', 'CGT'])
def test_book_example(self):
s = Strand('TAGATCCAGTCCATCGA')
e = Enzyme([
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid('mvr'),
AminoAcid(
'mvr'
), # some extra movements to lineup with the known example
AminoAcid('rpu'),
AminoAcid('inc'),
AminoAcid('cop'),
AminoAcid('mvr'),
AminoAcid('mvl'),
AminoAcid('swi'),
AminoAcid('lpu'),
AminoAcid('int')
])
final_strands = apply_enzyme(s, e)
strand_strs = sorted([strand.strand for strand in final_strands])
assert (strand_strs == ['ATG', 'TAGATCCAGTCCACATCGA'])
def test_null(self):
s = Strand('AAAAA')
e = strand_to_enzymes(s)
e_known = []
self.assert_enzymes_eq(e, e_known)
#!/usr/bin/env python
from typogenetics.strand import Strand
from typogenetics.ribosomes import strand_to_enzymes
from typogenetics.manipulation import apply_enzyme
if __name__ == '__main__':
# example strand
strand = Strand('TAGATCCAGTCCACTCGA')
# apply the ribosomes (which can produce more than one enzyme)
enzymes = strand_to_enzymes(strand)
# here, we'll apply all the enzymes to the original strand
daughter_strands = []
for enzyme in enzymes:
print "Next enzyme:"
print enzyme
print
print "Operations:"
print
daughter_strands.extend(apply_enzyme(strand, enzyme, verbose=True))
print
print "----------"
print "Resulting strands"
print "----------"
print[strand.strand for strand in set(daughter_strands)]
def test_non_base_input(self):
with assert_raises_regexp(InvalidStrand, 'Strand contains an invalid base unit'):
Strand('bat')
def test_str_input(self):
s = Strand('CATG')
assert s.strand == 'CATG'
def test_non_str_input(self):
with assert_raises_regexp(InvalidStrand, 'Wrong type, must be a str'):
Strand(4)
def test_lowercase(self):
s = Strand('attag')
assert s.strand == 'ATTAG'
def test_empty_strand(self):
s = Strand('')
e = Enzyme([AminoAcid('delete')])
final_strands = apply_enzyme(s, e)
assert (final_strands[0] == s)
def test_apply_empty_enzyme(self):
s = Strand('ACGT')
e = Enzyme([])
final_strands = apply_enzyme(s, e)
assert (final_strands[0].strand == 'ACGT')
def test_no_binding(self):
s = Strand('GGG')
e = strand_to_enzymes(s)[0]
final_strands = apply_enzyme(s, e)
assert (final_strands[0] == s)
