Reinforcement Learning for Aligning Structure-Based Molecular Generation toward Make-on-Demand Chemical Spaces
Re reinforcement learning is applied to a pocket-conditioned generative molecular model, demonstrating that RL alignment can substantially improve the experimental accessibility of SBDD candidates without sacrificing structural or chemical quality.
Rebecca M. Neeser, M. Yiğit, Adrian W. Dobbelstein et al.
· Journal of Chemical Informat... · 0 citations