Liang Hong

Enzymatic reactions are more than just molecular transformations; a unified model now captures both molecular structure and catalytic function, bridging a critical domain gap.

Protein foundation models can be significantly improved for fitness prediction by integrating evolutionary and structural context, boosting performance by an average of 0.073 Spearman correlation.

SciReasoner achieves a remarkable 31% improvement in Cellular Component annotation for low-homology proteins, showcasing the power of structural reasoning in AI.