<i>De novo</i> design of new chemical entities for SARS-CoV-2 using artificial intelligence

Background: The novel coronavirus SARS-CoV-2 has severely affected the health and economy of several countries. Multiple studies are in progress to design therapeutics against potential target proteins SARS-CoV-2, including 3CL protease, an essential protein for virus replication. Materials &amp; methods: In this study we employed deep neural network-based generative predictive models de novo small molecules capable inhibiting protease. model was optimized using transfer learning reinforcement focus around chemical space corresponding protease inhibitors. physicochemical property filters virtual screening score were used final screening. Conclusion: We have identified 33 compounds as ideal candidates further synthesis testing SARS-CoV-2.