Wenjun Xie

Wenjun Xie, Ph.D.

Assistant Professor

Department: Medicinal Chemistry
Business Phone: (352) 273-8846
Business Email: wenjunxie@ufl.edu

About Wenjun Xie

Wenjun Xie is an Assistant Professor in the Department of Medicinal Chemistry at the University of Florida. He earned his B.S. in Chemistry and Statistics and Ph.D. in Physical Chemistry from Peking University, followed by postdoctoral research at MIT and the University of Southern California. His research combines molecular simulation, artificial intelligence, and experimental methods to study enzyme catalysis, evolution, and design. His group has shown that generative AI models trained on natural enzyme sequences can accurately predict the impact of mutations on catalytic activity, enabling the rational improvement of enzymes shaped by billions of years of evolution. These findings led to the formulation of the concept of evolutionary catalysis—the idea that fundamental principles of catalytic efficiency are encoded in evolutionary sequence patterns and can be uncovered using generative AI.

Related Links:

Teaching Profile

Courses Taught
2024-2025
PHA6467C Drug Design II
2024
PHA6935 Selected Topics in Pharmacy
2024
PHA5439 Prin Med Chem-Pcol I
2024-2025
PHA6910 Supervised Research
2025
PHA4913 Undergraduate Research in Medicinal Chemistry

Research Profile

My lab integrates molecular simulation, AI, and experimental approaches to investigate enzyme catalysis, evolution, and design. We discovered that generative AI models trained on natural enzyme sequences can accurately predict the effects of mutations on catalytic activity (PNAS, 2022; JACS, 2025). This predictive power enables the rational enhancement of enzymes that have already undergone billions of years of evolution (PNAS, 2023). Based on these findings, we propose the concept of evolutionary catalysis—that the principles underlying catalytic efficiency are embedded in evolutionary sequence patterns and can be decoded using generative AI (Natl Sci Rev, 2023). Our research benefits from the collaborative synergy between computational scientists, life scientists, and engineers. Our lab focuses on three main areas: (1) evolutionary catalysis; (2) rational enzyme engineering; and (3) AI-driven drug discovery. For additional details, please visit our group’s website at https://evocatalysis.github.io.

Publications

Academic Articles
2025
Biochemical and Computational Characterization of Haloalkane Dehalogenase Variants Designed by Generative AI: Accelerating the SN2 Step
Journal of the American Chemical Society. 147(3):2747-2755 [DOI] 10.1021/jacs.4c15551.
2024
Exploring the Light-Emitting Agents in Renilla Luciferases by an Effective QM/MM Approach.
Journal of the American Chemical Society. 146(20):13875-13885 [DOI] 10.1021/jacs.4c00963. [PMID] 38718165.
2024
Molecular basis of Gabija anti-phage supramolecular assemblies.
Nature structural & molecular biology. 31(8):1243-1250 [DOI] 10.1038/s41594-024-01283-w. [PMID] 38627580.
2023
Enhancing luciferase activity and stability through generative modeling of natural enzyme sequences.
Proceedings of the National Academy of Sciences of the United States of America. 120(48) [DOI] 10.1073/pnas.2312848120. [PMID] 37983512.
2023
Harnessing generative AI to decode enzyme catalysis and evolution for enhanced engineering.
National science review. 10(12) [DOI] 10.1093/nsr/nwad331. [PMID] 38299119.
2022
Enhancing computational enzyme design by a maximum entropy strategy
Proceedings of the National Academy of Sciences. 119(7) [DOI] 10.1073/pnas.2122355119. [PMID] 35135886.
2022
Exploring the Role of Chemical Reactions in the Selectivity of Tyrosine Kinase Inhibitors
Journal of the American Chemical Society. 144(36):16638-16646 [DOI] 10.1021/jacs.2c07307. [PMID] 36044733.
2022
Natural Evolution Provides Strong Hints about Laboratory Evolution of Designer Enzymes
Proceedings of the National Academy of Sciences. 119(31) [DOI] 10.1073/pnas.2207904119. [PMID] 35901204.
2020
Characterizing chromatin folding coordinate and landscape with deep learning
PLOS Computational Biology. 16(9) [DOI] 10.1371/journal.pcbi.1008262. [PMID] 32986691.

Grants

Dec 2024 – Jun 2025
Designing Highly Efficient Enzymes with Physics-Based Features Powered by Generative AI and Molecular Simulations
Role: Principal Investigator
Funding: US DEPT OF DEFENSE ADV RES PROJ AGCY

Education

Postdoctoral Associate
2020-2023 · University of Southern California
Postdoctoral Associate
2017-2020 · Massachusetts Institute of Technology
Ph.D. in Physical Chemistry
2017 · Peking University
B.S. in Chemistry and Statistics
2012 · Peking University

Contact Details

Phones:
Business:
(352) 273-8846
Emails:
Business:
wenjunxie@ufl.edu
Addresses:
Business Mailing:
PO Box 100485
GAINESVILLE FL 32610
Business Street:
MSB P6-29
1345 Center Drive
GAINESVILLE FL 32610