Overview
Dr. Lei Xie is a professor at the intersection of Artificial Intelligence, Machine Learning, Systems Pharmacology, Computational Biology, Biophysics, and Chemoinformatics. His research focuses on developing next-generation computational methods to accelerate drug discovery, improve therapeutic design, and advance personalized medicine. By integrating mechanistic modeling, AI algorithms, multi-omics and real-world data, and systems-level thinking, his lab push beyond the “one-drug, one-target” paradigm to address unmet medical needs.
Dr. Xie’s team develops innovative frameworks to tackle challenges in reliable and generalizable AI for biomedicine, enabling predictive models to perform accurately and confidently on unseen chemical, biological, and clinical scenarios. These approaches guide risk-aware decisions, streamline early-stage drug discovery, and support patient-specific therapeutic strategies.
In addition to his research, Dr. Xie is committed to training the next generation of interdisciplinary scientists, fostering a collaborative environment where students and postdocs gain expertise at the interface of AI, biology, chemistry, and medicine. His work has been widely recognized for its impact on AI-driven drug discovery and systems pharmacology, and he actively collaborates across academia, industry, and clinical research.
Selected Publications
Wu Y, Bourne PE, Xie L (2025) AI-powered programmable virtual humans toward human physiologically-based drug discovery. Drug Discovery Today, 30(11):104497
Oliveros G, Wallace CH, Chaudry O, Liu Q, Qiu Y, Xie L, Rockwell P, Figueiredo-Pereira ME, Serrano PA. (2023). Repurposing ibudilast to mitigate Alzheimer’s disease by targeting inflammation. Brain. 146(3):898-911
Wu Y, Xie L, Liu Y, Xie L (2023) Hierarchical multi-omics data integration and modeling predict cell-specific chemical proteomics and drug responses. Cell Report Methods. 3(4):100452.
He D, Liu Q, Wu Y, Xie L (2022) A Context-aware deconfounding autoencoder for robust prediction of personalized clinical drug responses from cell line compound screening. Nature Machine Intelligence. 4(10):879-892.
Pham TH, Qiu Y, Xie L, Zhang P (2021) A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing. Nature Machine Intelligence. 3:247-257.
