报告题目：基于深度学习模型的生物序列分析

          Biological Sequence Analyses Based on Deep Learning Methods

报告时间：2018年12月19日上午9：30

报告地点：太阳成集团tyc4633(中国)有限公司-百度百科A521

报 告 人：许东 美国密苏里大学 James C.Dowell教授

报告人简介：Dong Xu is Shumaker Endowed Professor in Department of Electrical Engineering and Computer Science, Director of Information Technology Program, with appointments in the Christopher S. Bond Life Sciences Center and the Informatics Institute at the University of Missouri-Columbia. He obtained his PhD 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. His research is in computational biology and bioinformatics, including machine-learning application in bioinformatics, protein structure prediction, post-translational modification prediction, high-throughput biological data analyses, in silico studies of plants, microbes and cancers, biological information systems, and mobile App development for healthcare. He has published more than 300 papers. He was elected to the rank of American Association for the Advancement of Science (AAAS) Fellow in 2015.

报告内容简介：We have applied deep learning in several analysis and prediction problems for biological sequences, including prediction of protein secondary and super-secondary structures, protein domain partition, protein localization prediction, protein post-translational modification site prediction, and genotype-phenotype relationship. These applications utilized a broad spectrum of deep learning methods, including Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent neural network (RNN), Generative Adversarial Network (GAN) and Capsule Network. Various network architectures are also explored, including residual network, inception network, dense network, etc. Some of these applications represent novel formulations of the problems, while others significantly improved the performance over the previous methods. These studies also addressed some important deep-learning issues, such as handling small data, using transfer learning to pretrain models, and making the models transparent and explainable.

主办单位：

太阳成集团tyc4633(中国)有限公司-百度百科

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