《科学大讲堂 第246期》王俊 教授：人工智能时代的抗病毒药物设计

以下内容根据公开信息整理，并经大模型处理生成，可能存在疏漏或误差，请以实际信息为准。

• 题目: 人工智能时代的抗病毒药物设计
• 主讲人：王俊 教授 @ 罗格斯大学
• 时间：2026年6月15日 16:00
• 地点：理学院一楼1142报告厅

主讲人简介

Dr. Jun Wang is a Professor of Medicinal Chemistry at the Ernest Mario School of Pharmacy, Rutgers University. His research focuses on the discovery and development of antiviral therapeutics, with particular emphasis on viral cysteine proteases, deubiquitinases, and other essential viral enzymes and proteins. His laboratory integrates structure-based drug design, covalent and noncovalent inhibitor discovery, biochemical and cellular assay development, antiviral validation, pharmacokinetic evaluation, and AI-enabled virtual screening to advance new antiviral drug candidates.

Dr. Wang’s group has made important contributions to the discovery of first-in-class inhibitors targeting coronavirus papain-like proteases, including SARS-CoV-2 PLpro, and has developed mechanistically validated antiviral series with defined target engagement, cellular activity, and in vivo efficacy. His broader research program also includes antiviral discovery against enteroviruses, coronaviruses, and other emerging or re-emerging viral pathogens.

In addition to experimental medicinal chemistry, Dr. Wang’s laboratory actively develops and applies computational and AI-assisted approaches for drug discovery, including ultralarge-scale virtual screening, active learning, molecular docking, protein–ligand modeling, and structure-guided lead optimization. These approaches are integrated with direct-to-biology synthesis and rigorous experimental validation to accelerate the identification of novel chemical matter.

Dr. Wang has received national and international recognition for his contributions to bioorganic and medicinal chemistry, including the 2026 Tetrahedron Young Investigator Award for Bioorganic and Medicinal Chemistry and the 2026 ACS Division of Medicinal Chemistry Robert M. Scarborough Award for Excellence in Medicinal Chemistry. His work aims to build broadly applicable antiviral discovery platforms that can respond rapidly to current and future viral threats.

讲座简介

Emerging and re-emerging viral infections continue to pose major threats to global health, yet the development of direct-acting antivirals remains slow, costly, and technically challenging. Artificial intelligence is beginning to reshape antiviral drug discovery by enabling rapid analysis of large chemical spaces, prioritization of novel chemical matter, and integration of structural, biochemical, cellular, and pharmacological data. In this presentation, I will discuss how AI-enabled approaches can be combined with medicinal chemistry, structure-based drug design, and rigorous experimental validation to accelerate the discovery of antiviral therapeutics.

Our laboratory focuses on viral cysteine proteases, deubiquitinases, and other essential viral targets, including coronavirus papain-like proteases and enterovirus proteins. We integrate ultralarge-scale virtual screening, active learning, molecular docking, protein–ligand modeling, and direct-to-biology synthesis with biochemical assays, cellular target engagement studies, antiviral assays, mechanism-of-action validation, and pharmacokinetic evaluation. This workflow allows rapid progression from computational hit identification to experimentally validated inhibitors with defined potency, selectivity, cellular activity, and translational potential.

I will highlight examples from our discovery of first-in-class inhibitors targeting SARS-CoV-2 papain-like protease and related antiviral programs. These studies illustrate both the opportunities and limitations of AI in drug discovery: AI can improve speed, scale, and prioritization, but high-impact antiviral discovery still depends on target biology, assay quality, medicinal chemistry judgment, and orthogonal validation. Together, these integrated platforms provide a practical framework for developing new antivirals and preparing for future viral outbreaks.

海报链接