Generative Active Learning for the Search of Small-molecule Protein Binders

arXiv:2405.01616v1 Announce Type: cross
Abstract: Despite substantial progress in machine learning for scientific discovery in recent years, truly de novo design of small molecules which exhibit a property of interest remains a significant challenge. We introduce LambdaZero, a generative active learning approach to search for synthesizable molecules. Powered by deep reinforcement learning, LambdaZero learns to search over the vast space of molecules to discover candidates with a desired property. We apply LambdaZero with molecular docking to design novel small molecules …

abstract active learning arxiv challenge cs.ai cs.lg design discovery generative machine machine learning molecules progress property protein q-bio.bm scientific scientific discovery search small type