Discovery of novel spike/ACE2 inhibitory macrocycles using in silico reinforcement learning

Introduction: The COVID-19 pandemic has cast a heavy toll in human lives and global economics. is caused by the SARS-CoV-2 virus, which infects cells via its spike protein binding ACE2. Methods: To discover potential inhibitory peptidomimetic macrocycles for spike/ACE2 complex we deployed Artificial Intelligence guided virtual screening with three distinct strategies: 1) Allosteric inhibitors 2) Competitive ACE2 3) inhibitors. Screening was performed docking to relevant sites, clustering synthesizing cluster representatives. Synthesized molecules were screened inhibition using AlphaLISA RSV particles. Results: All strategies yielded peptides, but only competitive showed “hit” level activity. Discussion: These results suggest that direct of RBD domain most attractive strategy peptidomimetic, “head-to-tail” macrocycle drug development against ongoing pandemic.