Yifei Zhang

This study investigates the activity-stability trade-off in PETase using simulations and experiments, revealing how reshaping loop dynamics can enhance both stability and activity.

The paper demonstrates a computational strategy to design new PET hydrolases by replicating functional motifs from a template enzyme using deep learning and molecular computations, resulting in enzymes with high activity and thermostability.

BBATProt predicts protein and peptide functions using explainable deep learning, outperforming existing models in hydrolytic catalysis, peptide activity, and post-translational modification site prediction.