Accelerated\nDiscovery of Carbamate Cbl‑b Inhibitors\nUsing Generative AI Models and Structure-Based Drug Design

Casitas\nB-lymphoma proto-oncogene-b (Cbl-b) is a RING\nfinger E3\nligase that has an important role in effector T cell function, acting\nas a negative regulator of T cell, natural killer (NK) cell, and B\ncell activation. A discovery effort toward Cbl-b inhibitors was pursued\nin which a generative AI design engine, REINVENT, was combined with\na medicinal chemistry structure-based design to discover novel inhibitors\nof Cbl-b. Key to the success of this effort was the evolution of the\n“Design” phase of the Design-Make-Test-Analyze cycle\nto involve iterative rounds of an in silico structure-based drug design,\nstrongly guided by physics-based affinity prediction and machine learning\nDMPK predictive models, prior to selection for synthesis. This led\nto the accelerated discovery of a potent series of carbamate Cbl-b\ninhibitors.