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 _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))
log_likelihoods = []
synthesis = []
sascores = []
ok_sascore = []
no_sascore = []
ok_ourscore = []
no_ourscore = []
with torch.no_grad():
for s in s_to_human_score.keys():
#for s in ['COc1ccc2cc1-c1c(O)cc(O)c3c(=O)cc(oc13)-c1ccc(O)c(c1)[C@H](C)c1c(O)cc3c(c1O)C(=O)C[C@@H]2O3']:
m = Chem.MolFromSmiles(s)
num_sc = CalcNumAtomStereoCenters(
m) - CalcNumUnspecifiedAtomStereoCenters(m)
synthesis.append(int(s_to_human_score[s]))
sascores.append(calculateScore(m))
if args.stereo:
isomers = list(EnumerateStereoisomers(m))
else:
isomers = [m]
likelihood = []
for s in isomers:
s = Chem.MolToSmiles(s, isomericSmiles=args.stereo)
s = s + 'Q'
x = torch.tensor([c_to_i[i]
for i in list(s)]).unsqueeze(0).to(device)
output = model(x)
likelihood.append(utils.output_to_likelihood(output, x))
a = max(likelihood)
from rdkit import Chem
from rdkit.Contrib.SA_Score.sascorer import calculateScore
with open('../id_smiles.txt') as f, open('data.txt', 'w') as w:
for l in f:
m_id, s1, s2 = l.split()
m1, m2 = Chem.MolFromSmiles(s1), Chem.MolFromSmiles(s2)
if m1 is None or m2 is None: continue
c1, c2 = calculateScore(m1), calculateScore(m2)
w.write(m_id + '\t' + str(c1) + '\t' + str(c2) + '\n')
smiles_f = open('./ZINC/smiles.txt')
smiles_list = smiles_f.readlines()
logPList = []
molWtList = []
TPSAList = []
QEDList = []
SASList = []
for smi in smiles_list:
smi = smi.strip()
m = Chem.MolFromSmiles(smi)
molWt = ExactMolWt(m)
logP = MolLogP(m)
TPSA = CalcTPSA(m)
_qed = qed(m)
sas = calculateScore(m)
logPList.append(logP)
molWtList.append(molWt)
TPSAList.append(TPSA)
QEDList.append(_qed)
SASList.append(sas)
logPList = np.asarray(logPList)
TPSAList = np.asarray(TPSAList)
QEDList = np.asarray(QEDList)
SASList = np.asarray(SASList)
np.save('./ZINC/logP.npy', logPList)
np.save('./ZINC/TPSA.npy', TPSAList)
np.save('./ZINC/QED.npy', QEDList)
