qed_values = np.loadtxt('../solo_qed_features_and_targets/qed_values.txt')
qed_values_normalized = (np.array(qed_values) -
np.mean(qed_values)) / np.std(qed_values)
targets = qed_values_normalized
reg_scores = [] # collect scores for objective function
qed_scores = [] # collect scores for qed term in objective function
for i in range(len(valid_smiles_final)):
to_add = []
qed_store = []
if len(valid_smiles_final[i]) != 0:
for j in range(0, len(valid_smiles_final[i])):
current_qed_value = qed.default(
MolFromSmiles(valid_smiles_final[i][j]))
current_qed_value_normalized = (
current_qed_value -
np.mean(qed_values)) / np.std(qed_values)
score = current_qed_value_normalized
to_add.append(-score)
qed_store.append(current_qed_value)
reg_scores.append(to_add)
qed_scores.append(qed_store)
print(i)
print(valid_smiles_final)
print(reg_scores)
save_object(reg_scores,
"results_QED_solo/reg_scores{}.dat".format(iteration))
smiles[i] = smiles[i].strip()
# We load the auto-encoder
preproc = lasp.PreProcessing(dataset='drugs')
enc_dec = lasp.EncoderDecoder()
encoder, decoder = enc_dec.get_functions()
smiles_rdkit = []
for i in range(len(smiles)):
smiles_rdkit.append(MolToSmiles(MolFromSmiles(smiles[i])))
print(i)
qed_values = []
for i in range(len(smiles)):
qed_values.append(qed.default(MolFromSmiles(smiles_rdkit[i])))
print(i)
qed_values_normalized = (np.array(qed_values) -
np.mean(qed_values)) / np.std(qed_values)
smiles_one_hot_encoding = []
for i in range(len(smiles)):
smiles_one_hot_encoding.append(
preproc.smilelist_to_one_hot(smiles_rdkit[i]))
print(i)
latent_points = []
for i in range(len(smiles_one_hot_encoding)):
latent_points.append(encoder([smiles_one_hot_encoding[i]])[0][0])
print(i)