Feng Yin

DVE-stability predicts mutation-induced protein stability changes using a dual-view ensemble learning framework, achieving state-of-the-art performance on multiple benchmarks and showing strong generalization to rare beneficial mutations.

This study introduces SingleMod, a deep learning model for m6A modification mapping using single-molecule RNA sequencing, revealing m6A heterogeneity and species-specific distribution patterns.

This paper introduces PepGenWOA, a generative model for bioactive peptide design that outperforms existing methods and enables efficient virtual screening.