Discovery of novel quinoline papain-like protease inhibitors for COVID-19 through topology constrained molecular generative model

Papain-like protease (PL^pro) plays a critical role in both viral polyprotein processing and host antiviral immune suppression in SARS-CoV-2 infection, which causes COVID-19. Although several drugs have been approved for COVID-19, such as Remdesivir, Nirmatrelvir, etc., none of the PL^pro inhibitors have been approved for the treatment of COVID-19. The advent of artificial intelligence-based drug design methods has significantly accelerated the process of drug discovery. In current study, by harnessing the power of a topology constrained molecular generative model, we discovered a novel series of PL^pro inhibitors with strong potency against prevalent SARS-CoV-2 variants. Following a structure based computational approach for optimization, our lead compound, GZNL-2002, achieved decent PL^pro inhibitory potency and favorable pharmacokinetic properties, which warrants further development as a potential candidate compound for COVID-19 disease.