New COVID-19 protease inhibitors

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

Information about generated molecule # 36747

Cc1cccc(-n2cnc(C[C@@H](O)C[C@@H](Cc3ccccc3)C(=O)N[C@H]3c4ccccc4C[C@H]3O)n2)c1



Predicted properties

Property Value Comments
Docking score -8.9 VINA score, less is better
pIC50 (SARS, M) 5.14 bigger is better
pIC50 (HIV, M) 9.81 bigger is better
logS (M) -4.14 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 0.0169 Probability of being hERG binder (0-1), less is better.
Mutagenicity, AMES 0.0771 Probability of being mutagenic (0-1), less is better.
Caco-2 permeability -5.8089 log(sm/s)
HIA, intestinal absorbtion 98.3 %
LD50, oral (rats) 2.5 -log(M)
SARS-CoV inhibition 8.3 %
Molecular weight 496.61 g/mole
This molecule was not found in references databases.

Generator summary

Random prospective compound




CC(C)c1cc(O)c(CO)cc1SC1C(=O)CC(CCc2ccc(O)cc2)(C(C)C)OC1=O

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).