On the Generation of Novel Ligands for SARS-CoV-2 Protease and ACE2 Receptor via Constrained Graph Variational Autoencoders

SARS-CoV-2 has no known vaccine nor any effective treatment that has been released for clinical trials yet. This has ultimately paved the way for novel drug discovery approaches since although there are multiple efforts focused on drug repurposing of clinically-approved drugs for SARS-CoV-2, it is also worth considering that these existing drugs can be surpassed in effectivity by novel ones. This research focuses on the generation of novel candidate inhibitors via constrained graph variational autoencoders and the calculation of their Tanimoto similarities against existing drugs---repurposing these existing drugs and considering the novel ligands as possible SARS-CoV-2 main protease inhibitors and ACE2 receptor blockers by docking them through PyRx and ranking these ligands. Additionally, this research has successfully generated three novel ligands for the SARS-CoV-2 main protease and four novel ligands for the ACE2 receptor.