北京大学定量生物学中心/化学与分子工程学院/生命科学联合中心

学术报告 

题    目: Application of Deep Learning for Designing Small Molecules and Peptides

报告人:  Dong Xu, Curators’ Distinguished Professor

Department of Electrical Engineering and Computer Science,

Bond Life Sciences Center,

University of Missouri, Columbia

时    间: 7月14日（周五）10:00-11:00

地    点: 吕志和楼三层大厅

主持人: 唐淳 教授

摘 要:

The conventional developments of molecules and peptides are mainly driven by human intuition, labor, and manual decision. Due to the complexity of design and the magnitude of experimental and computational work, these conventional methods usually take long development cycles with tremendous costs and time. Deep learning has opened a new avenue to dramatically speed up the development of molecules and peptides. Deep learning can be used to accurately predict molecular properties. Meanwhile, deep reinforcement learning provides an effective search strategy for optimal properties. In our applications, we have developed a self-attention-based message-passing graph neural network to study the relationship between chemical properties and chemical structures in an interpretive manner. We further used an advanced deep Q-learning network with a fragment-based drug design to generate potential lead compounds targeting SARS-CoV-2 and employed structure-based optimization procedures to obtain a series of derivatives from a lead compound. We also applied protein structure prediction and Bayesian optimization for designing peptides for medicinal and agricultural purposes.

报告人简介：

Dong Xu is Curators’ Distinguished Professor in the Department of Electrical Engineering and Computer Science, with appointments in the Christopher S. Bond Life Sciences Center and the Informatics Institute at the University of Missouri-Columbia. He obtained his Ph.D. from the University of Illinois, Urbana-Champaign in 1995 and did two years of postdoctoral work at the US National Cancer Institute. He was a Staff Scientist at Oak Ridge National Laboratory until 2003 before joining the University of Missouri, where he served as Department Chair of Computer Science during 2007-2016 and Director of Information Technology Program during 2017-2020. Over the past 30+ years, he has conducted research in many areas of computational biology and bioinformatics, including single-cell data analysis, protein structure prediction and modeling, protein post-translational modifications, protein localization prediction, computational systems biology, biological information systems, and bioinformatics applications in human, microbes, and plants. His research since 2012 has focused on the interface between bioinformatics and deep learning. He has published more than 400 papers with more than 23,000 citations and an H-index of 80 according to Google Scholar. He was elected to the rank of American Association for the Advancement of Science (AAAS) Fellow in 2015 and American Institute for Medical and Biological Engineering (AIMBE) Fellow in 2020.