报告题目：Deep Learning for Protein Structure Prediction
报 告 人：Professor Yi Shang 
主 持 人：曹桂涛  副书记兼副院长
报告时间：2018年6月13日 周三 13:30-15:00
报告地点：中北校区数学馆西113报告厅

报告人简介：
Yi Shang is Professor, Associate Chair and Director of Graduate Studies, Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri. He received Ph.D. in Computer Science from University of Illinois at Urbana-Champaign in 1997, M.S. from the Institute of Computing Technology, Chinese Academy of Sciences, Beijing, in 1991, and B.S. from University of Science and Technology of China, Hefei, in 1988. He has published over 180 refereed papers in the areas of artificial intelligence, wireless sensor networks, mobile computing, and bioinformatics and has been granted 6 US patents. His research has been supported by NSF, NIH, Army, DARPA, Microsoft, and Raytheon.

报告摘要：
Protein structure prediction is one of biggest unsolved problems in science. Protein secondary structure, backbone torsion angle and other structure features can provide useful information for protein 3D structure prediction and protein functions. Deep learning offers a new opportunity to significantly improve prediction accuracy. In this talk, I will present several new deep neural networks developed in our lab, including deep inception-inside-inception (Deep3I) networks and deep neighbor residual (DeepNRN) networks for secondary structure prediction; deep residual inception networks (DeepRIN) for backbone torsion angle prediction; deep dense inception networks (DeepDIN) for beta turn prediction; and deep inception capsule networks (DeepICN) for gamma turn prediction.  The inputs to those deep neural networks are carefully designed to represent a rich set of information derived from individual amino acid, as well as the context of the protein sequence. Extensive experiments on multiple benchmark datasets show that the proposed methods outperformed the best existing methods and other deep neural networks significantly. These methods has been implemented in the MUFold software and freely available to the research community.