Zhiwei Nie

scEvolver enables continual cell-type annotation across expanding single-cell atlases, revealing cellular state transitions in disease contexts.

BiHiTo introduces a tokenizer inspired by biomolecular hierarchies to improve structure reconstruction and dynamic conformation exploration, achieving better performance than existing methods.

ProAR generates molecular dynamics trajectories with reduced error and improved conformational accuracy compared to existing methods.

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 develops a deep-learning framework to predict real-world prevalent SARS-CoV-2 mutations using in silico virus evolution and protein language models, achieving accurate predictions of future dominant 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 introduces PepGenWOA, a generative model for bioactive peptide design that outperforms existing methods and enables efficient virtual screening.

E2VD predicts virus variation drivers using an evolution-driven framework, outperforming existing methods and identifying critical mutations for viral survival and risk.

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.