Jie Fu

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 paper introduces S3AI, an interpretable method for predicting antibody-antigen interactions by combining structural knowledge and chemical rules, outperforming existing models and identifying key CDR regions.

This paper proposes a risk-aware antibody design framework using protein language models and Bayesian optimization, showing improved efficiency and sequence quality over existing methods.

This paper develops an AI-based simulation method to predict future high-risk SARS-CoV-2 variants by simulating RBD mutations and screening potential variants efficiently.

GIMLET is a graph-text model that uses natural language instructions for zero-shot molecule property prediction, outperforming baselines and approaching supervised models.

This paper introduces EpiTrace, a method using scATAC data to estimate cell age and lineage by analyzing clock-like chromatin accessibility, revealing insights into development and aging.