def runSA(self, ifn, ofn, error_ofn, restart=True, startline=0):
import sys
sys.stderr = open('/dev/null', 'w') # silence the warnings
if restart is True:
err_ofs = open(error_ofn, 'w')
with open(ofn, 'w') as ofs:
with open(ifn, 'r') as ifs:
smis = [_.rstrip() for _ in ifs]
for smi in smis:
try:
m = Chem.MolFromSmiles(smi)
sa = sascorer.calculateScore(m)
ofs.write("%s\t%f\n" % (smi, sa))
except Exception as inst:
err_ofs.write("%s\t%s\n" % (smi, inst.args))
err_ofs.close()
else:
err_ofs = open(error_ofn, 'a')
with open(ofn, 'a') as ofs:
with open(ifn, 'r') as ifs:
smis = [_.rstrip() for _ in ifs]
for smi in smis[startline:]:
try:
m = Chem.MolFromSmiles(smi)
sa = sascorer.calculateScore(m)
ofs.write("%s\t%f\n" % (smi, sa))
except Exception as inst:
err_ofs.write("%s\t%s\n" % (smi, inst.args))
err_ofs.close()
def runSA(self, ifn, ofn, error_ofn, restart=True, startline=0):
import sys
sys.stderr = open('/dev/null', 'w') # silence the warnings
if restart is True:
err_ofs = open(error_ofn, 'w')
with open(ofn, 'w') as ofs:
with open(ifn, 'r') as ifs:
smis = [_.rstrip() for _ in ifs]
for smi in smis:
try:
m = Chem.MolFromSmiles(smi)
sa = sascorer.calculateScore(m)
ofs.write("%s\t%f\n" % (smi, sa))
except Exception as inst:
err_ofs.write("%s\t%s\n" % (smi, inst.args))
err_ofs.close()
else:
err_ofs = open(error_ofn, 'a')
with open(ofn, 'a') as ofs:
with open(ifn, 'r') as ifs:
smis = [_.rstrip() for _ in ifs]
for smi in smis[startline:]:
try:
m = Chem.MolFromSmiles(smi)
sa = sascorer.calculateScore(m)
ofs.write("%s\t%f\n" % (smi, sa))
except Exception as inst:
err_ofs.write("%s\t%s\n" % (smi, inst.args))
err_ofs.close()
def logP_score(s):
m = Chem.MolFromSmiles(s)
logp = Descriptors.MolLogP(m)
SA_score = -sascorer.calculateScore(m)
#cycle_list = nx.cycle_basis(nx.Graph(rdmolops.GetAdjacencyMatrix(m)))
cycle_list = m.GetRingInfo().AtomRings() #remove networkx dependence
#print cycle_list
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([ len(j) for j in cycle_list ])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
cycle_score = -cycle_length
#print cycle_score
#print SA_score
#print logp
SA_score_norm=(SA_score-SA_mean)/SA_std
logp_norm=(logp-logP_mean)/logP_std
cycle_score_norm=(cycle_score-cycle_mean)/cycle_std
score_one = SA_score_norm + logp_norm + cycle_score_norm
return score_one
def penalized_logp(s):
if s is None: return -100.0
mol = Chem.MolFromSmiles(s)
if mol is None: return -100.0
logP_mean = 2.4570953396190123
logP_std = 1.434324401111988
SA_mean = -3.0525811293166134
SA_std = 0.8335207024513095
cycle_mean = -0.0485696876403053
cycle_std = 0.2860212110245455
log_p = Descriptors.MolLogP(mol)
SA = -sascorer.calculateScore(mol)
# cycle score
cycle_list = nx.cycle_basis(nx.Graph(
Chem.rdmolops.GetAdjacencyMatrix(mol)))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
cycle_score = -cycle_length
normalized_log_p = (log_p - logP_mean) / logP_std
normalized_SA = (SA - SA_mean) / SA_std
normalized_cycle = (cycle_score - cycle_mean) / cycle_std
return normalized_log_p + normalized_SA + normalized_cycle
def gaussion_workers(chem_model, val):
while True:
simulation_time = time.time()
task = comm.recv(source=0, tag=MPI.ANY_TAG, status=status)
tag = status.Get_tag()
if tag == START:
state = task[0]
m = task[1]
all_posible = chem_kn_simulation(chem_model, state, val, m)
generate_smile = predict_smile(all_posible, val)
new_compound = make_input_smile(generate_smile)
score = []
kao = []
try:
m = Chem.MolFromSmiles(str(new_compound[0]))
except:
m = None
#if m!=None and len(task[i])<=81:
if m != None:
try:
logp = Descriptors.MolLogP(m)
except:
logp = -1000
SA_score = -sascorer.calculateScore(
MolFromSmiles(new_compound[0]))
cycle_list = nx.cycle_basis(
nx.Graph(
rdmolops.GetAdjacencyMatrix(
MolFromSmiles(new_compound[0]))))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
cycle_score = -cycle_length
#print cycle_score
#print SA_score
#print logp
SA_score_norm = (SA_score - SA_mean) / SA_std
logp_norm = (logp - logP_mean) / logP_std
cycle_score_norm = (cycle_score - cycle_mean) / cycle_std
score_one = SA_score_norm + logp_norm + cycle_score_norm
score.append(score_one)
else:
score.append(-1000)
score.append(new_compound[0])
score.append(rank)
comm.send(score, dest=0, tag=DONE)
simulation_fi_time = time.time() - simulation_time
print "simulation_fi_time:", simulation_fi_time
if tag == EXIT:
MPI.Abort(MPI.COMM_WORLD)
comm.send(None, dest=0, tag=EXIT)
def _reward(self):
molecule = Chem.MolFromSmiles(self._state)
if molecule is None:
return -self.loss_fn(self.target_sas)
sas = sascorer.calculateScore(molecule)
return -self.loss_fn(sas - self.target_sas) * (self.discount_factor**(
self.max_steps - self.num_steps_taken))
def check_node_type(new_compound):
node_index = []
valid_compound = []
all_smile = []
distance = []
score = []
for i in range(len(new_compound)):
ko = Chem.MolFromSmiles(new_compound[i])
if ko != None:
SA_score = -sascorer.calculateScore(MolFromSmiles(new_compound[i]))
cycle_list = nx.cycle_basis(
nx.Graph(
rdmolops.GetAdjacencyMatrix(MolFromSmiles(
new_compound[i]))))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
if cycle_length == 0:
m = rdock_score(new_compound[i])
if m < 10**10:
node_index.append(i)
valid_compound.append(new_compound[i])
score.append(m)
return node_index, score, valid_compound
def calc_sa_score_mol(mol, verbose=False):
if mol is None:
if verbose:
print("Error passing: %s" % smi)
return None
# Synthetic accessibility score
return sascorer.calculateScore(mol)
def calc_score(smiles):
if verify_sequence(smiles):
try:
molecule = MolFromSmiles(smiles)
if Descriptors.MolWt(molecule) > 500:
return -1e10
current_log_P_value = Descriptors.MolLogP(molecule)
current_SA_score = -sascorer.calculateScore(molecule)
cycle_list = nx.cycle_basis(
nx.Graph(rdmolops.GetAdjacencyMatrix(molecule)))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
current_cycle_score = -cycle_length
current_SA_score_normalized = (current_SA_score - SA_mean) / SA_std
current_log_P_value_normalized = (current_log_P_value -
logP_mean) / logP_std
current_cycle_score_normalized = (current_cycle_score -
cycle_mean) / cycle_std
score = (current_SA_score_normalized +
current_log_P_value_normalized +
current_cycle_score_normalized)
return score
except Exception:
return -1e10
else:
return -1e10
def compute_cost_logp(G, writefile="temp.txt"):
cost = 0.0
sas = ""
logP = ""
cycle_score = ""
#m1 = nx_to_mol(G)
if guess_correct_molecules_from_graph(G, writefile):
m1 = Chem.MolFromMol2File(writefile)
if m1 != None:
s = Chem.MolToSmiles(m1)
sas = -sascorer.calculateScore(m1)
logP = Descriptors.MolLogP(m1)
cycle_list = nx.cycle_basis(G)
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0.0
else:
cycle_length = cycle_length - 6.0
cycle_score = -cycle_length
cost = sas + logP + cycle_score
else:
print "Error: m1 is NONE"
cost = ""
else:
print "Error: gues correct molecule"
cost = ""
# we want to define this property value such that low vales are better
if cost != "":
cost = 10.00 - cost
return (sas, logP, cycle_score)
def calc_score(smiles):
if verify_sequence(smiles):
molecule = MolFromSmiles(smiles)
current_log_P_value = Descriptors.MolLogP(molecule)
current_SA_score = -sascorer.calculateScore(molecule)
cycle_list = nx.cycle_basis(
nx.Graph(rdmolops.GetAdjacencyMatrix(molecule)))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
current_cycle_score = -cycle_length
current_SA_score_normalized = (current_SA_score -
np.mean(SA_scores)) / np.std(SA_scores)
current_log_P_value_normalized = (
current_log_P_value - np.mean(logP_values)) / np.std(logP_values)
current_cycle_score_normalized = (
current_cycle_score - np.mean(cycle_scores)) / np.std(cycle_scores)
score = (current_SA_score_normalized + current_log_P_value_normalized +
current_cycle_score_normalized)
return score
else:
raise ValueError("Error in calc_score: smiles is invalid.")
def logP_score(m):
try:
logp = Descriptors.MolLogP(m)
except:
print(m, Chem.MolToSmiles(m))
sys.exit('failed to make a molecule')
SA_score = -sascorer.calculateScore(m)
#cycle_list = nx.cycle_basis(nx.Graph(rdmolops.GetAdjacencyMatrix(m)))
cycle_list = m.GetRingInfo().AtomRings() #remove networkx dependence
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
cycle_score = -cycle_length
#print cycle_score
#print SA_score
#print logp
SA_score_norm = (SA_score - SA_mean) / SA_std
logp_norm = (logp - logP_mean) / logP_std
cycle_score_norm = (cycle_score - cycle_mean) / cycle_std
score_one = SA_score_norm + logp_norm + cycle_score_norm
global max_score
global count
count += 1
if score_one > max_score[0]:
max_score = [score_one, Chem.MolToSmiles(m)]
return score_one
def penalized_logp(molecule):
"""Calculates the penalized logP of a molecule.
Refactored from
https://github.com/wengong-jin/icml18-jtnn/blob/master/bo/run_bo.py
See Junction Tree Variational Autoencoder for Molecular Graph Generation
https://arxiv.org/pdf/1802.04364.pdf
Section 3.2
Penalized logP is defined as:
y(m) = logP(m) - SA(m) - cycle(m)
y(m) is the penalized logP,
logP(m) is the logP of a molecule,
SA(m) is the synthetic accessibility score,
cycle(m) is the largest ring size minus by six in the molecule.
Args:
molecule: Chem.Mol. A molecule.
Returns:
Float. The penalized logP value.
"""
log_p = Descriptors.MolLogP(molecule)
sas_score = sascorer.calculateScore(molecule)
largest_ring_size = get_largest_ring_size(molecule)
cycle_score = max(largest_ring_size - 6, 0)
return log_p - sas_score - cycle_score
def calc_score(mol):
logP_mean = 2.457 # np.mean(logP_values)
logP_std = 1.434 # np.std(logP_values)
SA_mean = -3.053 # np.mean(SA_scores)
SA_std = 0.834 # np.std(SA_scores)
cycle_mean = -0.048 # np.mean(cycle_scores)
cycle_std = 0.287 # np.std(cycle_scores)
molecule = mol
if Descriptors.MolWt(molecule) > 500:
return -1e10
current_log_P_value = Descriptors.MolLogP(molecule)
current_SA_score = -sascorer.calculateScore(molecule)
cycle_list = nx.cycle_basis(nx.Graph(
rdmolops.GetAdjacencyMatrix(molecule)))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
current_cycle_score = -cycle_length
current_SA_score_normalized = (current_SA_score - SA_mean) / SA_std
current_log_P_value_normalized = (current_log_P_value -
logP_mean) / logP_std
current_cycle_score_normalized = (current_cycle_score -
cycle_mean) / cycle_std
score = (current_SA_score_normalized + current_log_P_value_normalized +
current_cycle_score_normalized)
def SA_evaluate(self, valid_smiles):
SA_lst = []
for i in valid_smiles:
mol = Chem.MolFromSmiles(i)
SA_score = calculateScore(mol)
SA_lst.append(SA_score)
return SA_lst
def _rdkit_eval(entry: dict) -> dict:
"""Computes the chemical properties from RDKit,
adds them to the input dictionary"""
mol = Chem.MolFromSmiles(entry['smiles'])
entry['logP'] = Crippen.MolLogP(mol)
entry['QED'] = QED.qed(mol)
entry['SA_score'] = calculateScore(mol)
return entry
def test1(self):
testData = [x.strip().split('\t') for x in file('data/zim.100.txt').readlines()]
testData.pop(0)
for row in testData:
smi = row[0]
m = Chem.MolFromSmiles(smi)
tgt = float(row[2])
val = sascorer.calculateScore(m)
self.failUnlessAlmostEqual(tgt,val,3)
def get_sa(x):
try:
return sascorer.calculateScore(Chem.MolFromSmiles(x))
except:
return -1
def evaluate_individual(self, individual):
if individual is None:
return None
else:
mol_graph = MolFromSmiles(individual.to_aromatic_smiles())
score = sascorer.calculateScore(mol_graph)
return score, [score]
def add_synthetic_accessibility_score(self):
"""create a list holding the 'synthetic accessibility score'
reference: https://doi.org/10.1186/1758-2946-1-8
module code is in: https://github.com/rdkit/rdkit/tree/master/Contrib/SA_Score"""
sa_score = [sascorer.calculateScore(i) for i in list(self.df['mols'])]
self.df['sa_score'] = sa_score
print(
f'Synthetic accessibility score range: {min(sa_score)} - {max(sa_score)}'
)
def evaluate_individual(self, individual):
mol_graph = MolFromSmiles(individual.to_aromatic_smiles())
log_p = Descriptors.MolLogP(mol_graph)
sas_score = sascorer.calculateScore(mol_graph)
largest_ring_size = self.get_largest_ring_size(mol_graph)
cycle_score = max(largest_ring_size - 6, 0)
score = log_p - sas_score - cycle_score
return score, [score]
def test1(self):
with open('data/zim.100.txt') as f:
testData = [x.strip().split('\t') for x in f]
testData.pop(0)
for row in testData:
smi = row[0]
m = Chem.MolFromSmiles(smi)
tgt = float(row[2])
val = sascorer.calculateScore(m)
self.assertAlmostEqual(tgt, val, 3)
def calc_sa_score_smi(smi, verbose=False):
# Create RDKit mol object
mol = Chem.MolFromSmiles(smi)
if mol is None:
if verbose:
print("Error passing: %s" % smi)
return None
# Synthetic accessibility score
return sascorer.calculateScore(mol)
def test1(self):
with open('data/zim.100.txt') as f:
testData = [x.strip().split('\t') for x in f]
testData.pop(0)
for row in testData:
smi = row[0]
m = Chem.MolFromSmiles(smi)
tgt = float(row[2])
val = sascorer.calculateScore(m)
self.assertAlmostEqual(tgt,val,3)
def check_node_type(new_compound, SA_mean, SA_std, logP_mean, logP_std,
cycle_mean, cycle_std):
node_index = []
valid_compound = []
logp_value = []
all_smile = []
distance = []
#print "SA_mean:",SA_mean
#print "SA_std:",SA_std
#print "logP_mean:",logP_mean
#print "logP_std:",logP_std
#print "cycle_mean:",cycle_mean
#print "cycle_std:",cycle_std
activity = []
score = []
for i in range(len(new_compound)):
try:
m = Chem.MolFromSmiles(str(new_compound[i]))
except:
print(None)
if m != None and len(new_compound[i]) <= 81:
try:
logp = Descriptors.MolLogP(m)
except:
logp = -1000
node_index.append(i)
valid_compound.append(new_compound[i])
SA_score = -sascorer.calculateScore(MolFromSmiles(new_compound[i]))
cycle_list = nx.cycle_basis(
nx.Graph(
rdmolops.GetAdjacencyMatrix(MolFromSmiles(
new_compound[i]))))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
cycle_score = -cycle_length
#print cycle_score
#print SA_score
#print logp
SA_score_norm = (SA_score - SA_mean) / SA_std
logp_norm = (logp - logP_mean) / logP_std
cycle_score_norm = (cycle_score - cycle_mean) / cycle_std
score_one = SA_score_norm + logp_norm + cycle_score_norm
score.append(score_one)
all_smile.append(new_compound[i])
return node_index, score, valid_compound, all_smile
def filtered_sa(self, valid_smiles):
count = 0
for i in valid_smiles:
mol = Chem.MolFromSmiles(i)
SA_score = calculateScore(mol)
if SA_score > 5:
valid_smiles.remove(i)
count = count + 1
print("unavaliable_SA_mol:%i" % count)
return valid_smiles
def worker(syba_model, my_syba_model, scscore_model, smi):
try:
syba_score = syba_model.predict(smi)
except:
syba_score = 0
try:
my_syba_score = my_syba_model.predict(smi)
except:
my_syba_score = 0
sa_score = sa.calculateScore(Chem.MolFromSmiles(smi))
sc_score = scscore_model.get_score_from_smi(smi)[1]
return syba_score, my_syba_score, sa_score, sc_score
def test1(self):
testData = [
x.strip().split('\t')
for x in file('data/zim.100.txt').readlines()
]
testData.pop(0)
for row in testData:
smi = row[0]
m = Chem.MolFromSmiles(smi)
tgt = float(row[2])
val = sascorer.calculateScore(m)
self.failUnlessAlmostEqual(tgt, val, 3)
def simulation(chem_model, state, node):
#time.sleep(10)
val = [
'\n', '&', 'C', '(', ')', 'c', '1', '2', 'o', '=', 'O', 'N', '3', 'F',
'[C@@H]', 'n', '-', '#', 'S', 'Cl', '[O-]', '[C@H]', '[NH+]', '[C@]',
's', 'Br', '/', '[nH]', '[NH3+]', '4', '[NH2+]', '[C@@]', '[N+]',
'[nH+]', '\\', '[S@]', '5', '[N-]', '[n+]', '[S@@]', '[S-]', '6', '7',
'I', '[n-]', 'P', '[OH+]', '[NH-]', '[P@@H]', '[P@@]', '[PH2]', '[P@]',
'[P+]', '[S+]', '[o+]', '[CH2-]', '[CH-]', '[SH+]', '[O+]', '[s+]',
'[PH+]', '[PH]', '8', '[S@@+]'
]
all_posible = chem_kn_simulation(chem_model, state, val)
generate_smile = predict_smile(all_posible, val)
new_compound = make_input_smile(generate_smile)
#score=[]
kao = []
try:
m = Chem.MolFromSmiles(str(new_compound[0]))
#print (str(new_compound[0]))
except:
m = None
if m != None:
try:
logp = Descriptors.MolLogP(m)
except:
logp = -1000
SA_score = -sascorer.calculateScore(MolFromSmiles(new_compound[0]))
cycle_list = nx.cycle_basis(
nx.Graph(
rdmolops.GetAdjacencyMatrix(MolFromSmiles(new_compound[0]))))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([len(j) for j in cycle_list])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
cycle_score = -cycle_length
SA_score_norm = SA_score #(SA_score-SA_mean)/SA_std
logp_norm = logp #(logp-logP_mean)/logP_std
cycle_score_norm = cycle_score #(cycle_score-cycle_mean)/cycle_std
score_one = SA_score_norm + logp_norm + cycle_score_norm
#score.append(score_one)
score = score_one / (1 + abs(score_one))
else:
#score.append(-1000)
score = -1000 / (1 + 1000)
#score.append(new_compound[0])
#score.append(rank)
return score
def _penalized_logp_cyclebasis(mol: Mol, dataset: str):
log_p = Descriptors.MolLogP(mol)
sa_score = sascorer.calculateScore(mol)
cycle_list = nx.cycle_basis(nx.Graph(Chem.rdmolops.GetAdjacencyMatrix(mol)))
largest_ring_size = max([len(j) for j in cycle_list]) if cycle_list else 0
cycle_score = max(largest_ring_size - 6, 0)
log_p = (log_p - LOGP_MEAN) / LOGP_STD
sa_score = (sa_score - SASCORE_MEAN) / SASCORE_STD
cycle_score = (cycle_score - CYCLEBASIS_CYCLESCORE_MEAN) / CYCLEBASIS_CYCLESCORE_STD
return log_p - sa_score - cycle_score
def _penalized_logp_atomrings(mol: Mol, dataset: str):
log_p = Descriptors.MolLogP(mol)
sa_score = sascorer.calculateScore(mol)
cycle_list = mol.GetRingInfo().AtomRings()
largest_ring_size = max([len(j) for j in cycle_list]) if cycle_list else 0
cycle_score = max(largest_ring_size - 6, 0)
log_p = (log_p - LOGP_MEAN) / LOGP_STD
sa_score = (sa_score - SASCORE_MEAN) / SASCORE_STD
cycle_score = (cycle_score - ATOMRING_CYCLESCORE_MEAN) / ATOMRING_CYCLESCORE_STD
return log_p - sa_score - cycle_score
def runSA(ifn, ofn, error_ofn):
err_ofs = open(error_ofn, 'w')
with open(ofn, 'w') as ofs:
with open(ifn, 'r') as ifs:
lines = ifs.readlines()
for line in lines:
try:
smi = line.split()[0]
m = Chem.MolFromSmiles(smi)
sa = sascorer.calculateScore(m)
ofs.write("%s\t%f\n" % (line.rstrip(), sa))
except Exception as inst:
err_ofs.write("%s\t%s\n" % (smi, inst.args))
err_ofs.close()
def penalized_logp(molecule):
"""Calculates the penalized logP of a molecule.
Refactored from
https://github.com/wengong-jin/icml18-jtnn/blob/master/bo/run_bo.py
See Junction Tree Variational Autoencoder for Molecular Graph Generation
https://arxiv.org/pdf/1802.04364.pdf
Section 3.2
Penalized logP is defined as:
y(m) = logP(m) - SA(m) - cycle(m)
y(m) is the penalized logP,
logP(m) is the logP of a molecule,
SA(m) is the synthetic accessibility score,
cycle(m) is the largest ring size minus by six in the molecule.
Args:
molecule: Chem.Mol. A molecule.
Returns:
Float. The penalized logP value.
"""
log_p = Descriptors.MolLogP(molecule)
sas_score = sascorer.calculateScore(molecule)
largest_ring_size = get_largest_ring_size(molecule)
cycle_score = max(largest_ring_size - 6, 0)
return log_p - sas_score - cycle_score
## !!!!!!!!!!이거 써야하는지 check 필요!!!!!!!!##
# def num_long_cycles(mol):
# """Calculate the number of long cycles.
# Args:
# mol: Molecule. A molecule.
# Returns:
# negative cycle length.
# """
# cycle_list = nx.cycle_basis(nx.Graph(Chem.rdmolops.GetAdjacencyMatrix(mol)))
# if not cycle_list:
# cycle_length = 0
# else:
# cycle_length = max([len(j) for j in cycle_list])
# if cycle_length <= 6:
# cycle_length = 0
# else:
# cycle_length = cycle_length - 6
# return -cycle_length
#
#
# def penalized_logp(molecule):
# log_p = Descriptors.MolLogP(molecule)
# sas_score = SA_Score.sascorer.calculateScore(molecule)
# cycle_score = num_long_cycles(molecule)
# return log_p - sas_score + cycle_score
# pred, uncert = sgp.predict(X_train, 0 * X_train)
# error = np.sqrt(np.mean((pred - y_train)**2))
# trainll = np.mean(sps.norm.logpdf(pred - y_train, scale = np.sqrt(uncert)))
# print 'Train RMSE: ', error
# print 'Train ll: ', trainll
next_inputs = sgp.batched_greedy_ei(50, np.min(X_train, 0), np.max(X_train, 0))
valid_smiles_final = decode_from_latent_space(next_inputs, model)
save_object(valid_smiles_final, "%s/valid_smiles-seed-%d-iter-%d.dat" % (cmd_args.save_dir, args.seed, iteration))
new_features = next_inputs
scores = []
for i in range(len(valid_smiles_final)):
if valid_smiles_final[ i ] is not None:
current_log_P_value = Descriptors.MolLogP(MolFromSmiles(valid_smiles_final[ i ]))
current_SA_score = -sascorer.calculateScore(MolFromSmiles(valid_smiles_final[ i ]))
cycle_list = nx.cycle_basis(nx.Graph(rdmolops.GetAdjacencyMatrix(MolFromSmiles(valid_smiles_final[ i ]))))
if len(cycle_list) == 0:
cycle_length = 0
else:
cycle_length = max([ len(j) for j in cycle_list ])
if cycle_length <= 6:
cycle_length = 0
else:
cycle_length = cycle_length - 6
current_cycle_score = -cycle_length
current_SA_score_normalized = (current_SA_score - np.mean(SA_scores)) / np.std(SA_scores)
current_log_P_value_normalized = (current_log_P_value - np.mean(logP_values)) / np.std(logP_values)
current_cycle_score_normalized = (current_cycle_score - np.mean(cycle_scores)) / np.std(cycle_scores)