def test_chembl(self):
"""
Problem with fixed-prop testing:
Almost all of the results (<10% for init_pool of 50) seem to be outside of the database,
and even less for smaller pool. Hence cannot get its score for testing;
setting them to zero leads to slow exploration.
"""
pool_all, dd = get_chembl_prop()
# loading with mol conversions takes 8 minutes
# pool_all = [Molecule(smiles, conv_enabled=True) for smiles in tqdm(pool_all[:10000])]
pool_all = [Molecule(smiles, conv_enabled=False) for smiles in pool_all]
start_pool = list(np.random.choice(pool_all, size=100, replace=False))
def print_props(pool):
props = [dd[mol.smiles] for mol in pool]
print("Props of pool", len(pool), np.min(props), np.mean(props), np.max(props))
print_props(pool_all)
print_props(start_pool)
func = lambda mol: dd[mol.smiles]
exp = RandomExplorer(lambda mol_list: func(mol_list[0]), initial_pool=start_pool)
print("Starting ChEMBL score 1 optimization")
t0 = time()
exp.run(30)
print("Completed ChEMBL score 1 optimization, time elapsed: %.3fs" % (time()-t0))
# print(exp.pool)
top = exp.get_best(1)[0]
print(top.get_synthesis_path())
print("Best achieved score: %.3f" % func(top))
props = [dd[mol.smiles] for mol in pool_all]
print("Best possible score: %.3f" % np.max(props))
def _test_len(self):
dummy_func = lambda mol: len(mol.smiles)
test_pool = ["CC", "O=C=O", "C#N", "CCN(CC)CC", "CC(=O)O", "C1CCCCC1", "c1ccccc1"]
test_pool = [Molecule(smiles) for smiles in test_pool]
exp = RandomExplorer(dummy_func, initial_pool=test_pool)
print("Starting len of SMILES optimization")
exp.run(2)
#check
print(exp.pool)
def _test_sas(self):
sas_func = lambda mol: calculateSAScore(Chem.MolFromSmiles(mol.smiles))
print(sas_func(Molecule("CC")))
test_pool = ["CC", "O=C=O", "C#N", "CCN(CC)CC", "CC(=O)O", "C1CCCCC1", "c1ccccc1"]
test_pool = [Molecule(smiles) for smiles in test_pool]
exp = RandomExplorer(sas_func, initial_pool=test_pool)
print("Starting SA score optimization")
t0 = time()
exp.run(10)
#check
print("Completed SA score optimization, time elapsed: %.3fs" % (time()-t0))
print(exp.pool)
top = exp.get_best(1)[0]
print(top.get_synthesis_path())
def explore_and_validate_synth(init_pool_size, seed, budget, objective,
dataset, max_pool_size, reporter):
"""
This experiment is equivalent to unlimited-evaluation optimization.
It compares optimal found vs optimal over pool, and checks if synthesizeability is improved.
"""
obj_func = get_objective_by_name(objective)
sampler = MolSampler(dataset, sampling_seed=seed)
pool = sampler(init_pool_size)
exp = RandomExplorer(obj_func,
initial_pool=pool,
max_pool_size=max_pool_size)
real_budget = budget - init_pool_size
props = [obj_func(mol) for mol in pool]
reporter.writeln(
f"Properties of pool: quantity {len(pool)}, min {np.min(props)}, avg {np.mean(props)}, max {np.max(props)}"
)
reporter.writeln(f"Starting {objective} optimization")
t0 = time.time()
top_value, top_point, history = exp.run(real_budget)
reporter.writeln("Finished run in {:.3f} minutes".format(
(time.time() - t0) / 60))
reporter.writeln(f"Is a valid molecule: {check_validity(top_point)}")
reporter.writeln(f"Resulting molecule: {top_point}")
reporter.writeln(f"Top score: {obj_func(top_point)}")
reporter.writeln(
f"Minimum synthesis score over the path: {compute_min_sa_score(top_point)}"
)
with open(SYN_PATH_FILE, 'wb') as f:
pkl.dump(top_point.get_synthesis_path(), f)
sorted_by_prop = sorted(pool, key=obj_func)[-5:]
for opt_mol in sorted_by_prop:
min_sa_score = compute_min_sa_score(opt_mol)
reporter.writeln(
f"Minimum synthesis score of optimal molecules: {min_sa_score}")
vals = history['objective_vals']
plt.title(f'Optimizing {objective} with random explorer')
plt.plot(range(len(vals)), vals)
plt.savefig(PLOT_FILE, format='eps', dpi=1000)
with open(OPT_VALS_FILE, 'w') as f:
f.write(' '.join([str(v) for v in vals]))
def _opt_method_optimise_initalise(self):
""" Important setup: creating the optimization object """
initial_pool = [mol_lst[0] for mol_lst in self.history.query_points]
logging.info(
f'Length of initial pool {len(initial_pool)}, should be equal to init_capital.'
)
if self.acq_opt_method == 'rand_explorer':
self.acq_optimizer = RandomExplorer(
initial_pool=initial_pool,
max_pool_size=self.options.max_pool_size)
else:
raise NotImplementedError(
"Acq opt method {} not implemented.".format(
self.acq_opt_method))