Ding Luo

EzHit retrieves enzyme-reaction associations efficiently, outperforming baselines and enabling large-scale metagenomic biocatalyst discovery.

GraphKcat predicts enzyme kinetic parameters by integrating 3D binding conformations and multi-scale graph learning, achieving robust performance even under low sequence similarity conditions.

ApoDock improves molecular docking by combining machine learning-driven sidechain packing with traditional sampling to generate physically plausible protein-ligand poses.