Bo Huang

This paper introduces RCDO, a closed-loop reinforcement learning framework that accelerates compound optimization by integrating experimental feedback with generative models, achieving significant improvements in drug candidate properties.

This paper introduces a two-stage method to evaluate 3D molecule conformations generated by AI, achieving high speed and quantum mechanical accuracy.

This paper introduces ExptGMS, a method using experimental electron density data to improve virtual screening by enhancing active compound enrichment, achieving a 20% improvement and identifying new inhibitors.

The paper introduces a 3D molecule generative model using electron density data to create drug-like molecules that match target protein pockets and active compounds.