def test_primers_collection_example():
def create_new_primer(existing_primers):
"""Create a new primer based on the primers created so far"""
problem = DnaOptimizationProblem(
sequence=random_dna_sequence(length=20),
constraints=[
AvoidHeterodimerization(existing_primers, tmax=3),
AvoidPattern("3x3mer"),
AvoidPattern("4xG"),
],
objectives=[EnforceGCContent(target=0.6)],
logger=None,
)
problem.resolve_constraints()
problem.optimize()
return problem.sequence
# MAIN LOOP, WHERE PRIMERS ARE CREATED ONE BY ONE
existing_primers = []
for i in range(10):
new_primer = create_new_primer(existing_primers)
existing_primers.append(new_primer)
print("PRIMERS GENERATED: \n\n%s\n" % "\n".join(existing_primers))
for sequence in existing_primers:
assert "GGGG" not in sequence
assert "CCCC" not in sequence
max_tm = max(
primer3.calcHeterodimer(seq1, seq2).tm
for seq1, seq2 in itertools.combinations(existing_primers, 2))
assert max_tm < 3
gc_contents = [gc_content(p) for p in existing_primers]
assert min(gc_contents) > 0.55
assert max(gc_contents) < 0.65
def evaluate(self, problem):
"""Return the sum of breaches extent for all windowed breaches."""
wstart, wend = self.location.start, self.location.end
sequence = self.location.extract_sequence(problem.sequence)
gc = gc_content(sequence, window_size=self.window)
breaches = (np.maximum(0, self.mini - gc) +
np.maximum(0, gc - self.maxi))
score = -breaches.sum()
breaches_starts = wstart + (breaches > 0).nonzero()[0]
if len(breaches_starts) == 0:
breaches_locations = []
elif len(breaches_starts) == 1:
if self.window is not None:
start = breaches_starts[0]
breaches_locations = [[start, start + self.window]]
else:
breaches_locations = [[wstart, wend]]
else:
segments = [(bs, bs + self.window) for bs in breaches_starts]
groups = group_nearby_segments(segments,
max_start_spread=max(
1, self.locations_span))
breaches_locations = [(group[0][0], group[-1][-1])
for group in groups]
if breaches_locations == []:
message = "Passed !"
else:
breaches_locations = [Location(*loc) for loc in breaches_locations]
message = ("Out of bound on segments " +
", ".join([str(l) for l in breaches_locations]))
return SpecEvaluation(self,
problem,
score,
locations=breaches_locations,
message=message)
def evaluate_end(self, sequence):
gc = gc_content(sequence)
return -(max(0, self.mini - gc) + max(0, gc - self.maxi))
objectives=[EnforceGCContent(target=0.6)],
logger=None,
)
problem.resolve_constraints()
problem.optimize()
return problem.sequence
# MAIN LOOP, WHERE PRIMERS ARE CREATED ONE BY ONE
existing_primers = []
for i in range(20):
new_primer = create_new_primer(existing_primers)
existing_primers.append(new_primer)
print("PRIMERS GENERATED: \n\n%s\n" % "\n".join(existing_primers))
# (OPTIONAL VERIFICATION OF THE COLLECTION)
import itertools
import primer3
from dnachisel.biotools import gc_content
max_tm = max(
primer3.calcHeterodimer(seq1, seq2).tm
for seq1, seq2 in itertools.combinations(existing_primers, 2))
print("Max Tm heterodimerization between any 2 primers: %.2f" % max_tm)
gc_contents = [gc_content(p) for p in existing_primers]
print("GC content range %.2f-%.2f" % (min(gc_contents), max(gc_contents)))