New COVID-19 protease inhibitors

designed by AI with recurrent neural networks, molecular docking, and QSAR

Information about generated molecule # 42255

O=C(N[C@H](C[S@](=O)c1cc(Cl)cc(Cl)c1)C(=O)N[C@H]1c2ccccc2C[C@H]1O)O[C@H]1C=CCOC1



Predicted properties

Property Value Comments
Docking score -8.2 VINA score, less is better
pIC50 (SARS, M) 5.51 bigger is better
pIC50 (HIV, M) 9.74 bigger is better
logS (M) -3.99 Solubility based on the Transformer Model, bigger is better.
Cycle >4 The cycle when the molecule was generate, the bigger cycle the more RNN is inventive.
Cardiotoxicity, hERG 0.0021 Probability of being hERG binder (0-1), less is better.
Mutagenicity, AMES 0.109 Probability of being mutagenic (0-1), less is better.
Caco-2 permeability -5.6257 log(sm/s)
HIA, intestinal absorbtion 100.0 %
LD50, oral (rats) 2.7 -log(M)
SARS-CoV inhibition 16.0 %
Molecular weight 539.44 g/mole
This molecule was not found in references databases.

Generator summary

Random prospective compound




Cc1cc(C(C)(C)C)c(SC2C(=O)CC(c3ccccc3)(C(C)C)OC2=O)cc1O

COVID-19 protease

The structure has been recently solved, PDB code 6lu7. 6ul7 structure
Developed in group of Cheminformatics in the Institute of Structural Biology at Helmholtz-Zentrum Muenchen, Tetko group
With support of BIGCHEM GmBH (bigchem.de) and RULIS Ltd. (rulis.ru).