Jiaqi Luo

EPERep enhances protein function annotation for remote homologs by using evolutionary input to improve prediction accuracy for underrepresented proteins.

This paper introduces DETANGO, a deep learning framework that disentangles mutation effects on protein stability and function, identifying stable-but-inactive variants and functionally critical residues.

This paper introduces MSRep, a deep learning framework that improves protein function annotation by addressing class imbalance through neural collapse-inspired representations, achieving better performance for both common and rare function classes.

PenLight improves protein annotation by integrating 3D structure and sequence data using graph neural networks and contrastive learning.