File size: 2,453 Bytes
b7e5b63 ea61d54 4466c5e 68a01ab 4466c5e b7e5b63 4466c5e b7e5b63 4466c5e 68a01ab 4466c5e 68a01ab 4466c5e | 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 | # Heuristic mutation search used by the Optimize page.
# Each round scores single-site mutants with predict_amp; accepts the best gain above threshold.
import random
from utils.predict import predict_amp
# Residue groups used to propose chemistry-aware substitutions.
HYDROPHOBIC = set("AILMFWVPG")
HYDROPHILIC = set("STNQYCH")
POSITIVE = set("KRH")
NEGATIVE = set("DE")
def mutate_residue(residue):
# Return a candidate replacement residue and rationale.
if residue in POSITIVE:
return residue, "Retained strong positive residue"
elif residue in NEGATIVE:
return random.choice(list(POSITIVE)), "Increased positive charge"
elif residue in HYDROPHILIC:
return random.choice(list(HYDROPHOBIC)), "Improved hydrophobicity balance"
elif residue in HYDROPHOBIC:
return random.choice(list(POSITIVE | HYDROPHILIC)), "Enhanced amphipathicity"
else:
return random.choice(list(HYDROPHOBIC)), "Adjusted physicochemical profile"
def optimize_sequence(seq, model, max_rounds=20, confidence_threshold=0.001):
# Iteratively improve AMP probability by accepting the best mutation per round.
current_seq = seq
label, conf = predict_amp(current_seq, model)
best_conf = conf
history = [(current_seq, conf, "-", "-", "-", "Original sequence")]
# Greedy loop: keep only the best confidence-improving mutation each round.
for _ in range(max_rounds):
best_mutation = None
best_mutation_conf = best_conf
for pos, old_res in enumerate(current_seq):
new_res, reason = mutate_residue(old_res)
if new_res == old_res:
continue
new_seq = current_seq[:pos] + new_res + current_seq[pos+1:]
_, new_conf = predict_amp(new_seq, model)
if new_conf > best_mutation_conf:
best_mutation_conf = new_conf
best_mutation = (new_seq, pos, old_res, new_res, reason)
if best_mutation and best_mutation_conf - best_conf >= confidence_threshold:
current_seq, pos, old_res, new_res, reason = best_mutation
best_conf = best_mutation_conf
change = f"Pos {pos+1}: {old_res} → {new_res}"
history.append((current_seq, best_conf, change, old_res, new_res, reason))
else:
# Stop when no mutation clears the minimum improvement threshold.
break
return current_seq, best_conf, history
|