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.

报告内容简介：

Molecular dynamics (MD) simulation provides a powerful computational approach to studying proteins. However, current MD simulations cannot reach the time scales of most biological processes. The advent of deep learning made it possible to evaluate spatially short and long-range communications from MD trajectories to understand protein dynamics. For this purpose, we adapted a neural relational inference model using an encoder-decoder graph neural network architecture to infer latent interactions between residues. The model can predict free energy changes upon mutations more accurately than other methods. We applied our method to study protein allostery, a biological process facilitated by spatially long-range intra-protein communication, whereby ligand binding or amino acid mutation at a distant site affects the active site remotely. This model successfully learned the long-range interactions and pathways that mediate the allosteric communications between remote sites in the Pin1, SOD1, and MEK1 systems. Furthermore, it can discover allosteric patterns in early MD simulation trajectories before significant conformational changes.

主办单位：吉林大学计算机科学与技术学院

吉林大学软件学院

吉林大学计算机科学技术研究所

符号计算与知识工程教育部重点实验室

仿真技术教育部重点实验室

网络技术及应用软件教育部工程研究中心

吉林大学国家级计算机实验教学示范中心