test(以下为旧站栏目)

Machine Learning and Graph Mining for Biological Problems

Jinyan Li

2014-09-27

报告人简介: Jinyan Li is an Professor and core member at Advanced Analytics Institute and Centre for Health Technologies, Faculty of Engineering and IT, University of Technology, Sydney, Australia. His research is focused on fundamental data mining algorithms, machine learning, gene expression data analysis, structural bioinformatics, and information theory. He is known for the notion of emerging patterns in data mining, and is known for the "double water exclusion" hypothesis in bioinformatics. Jinyan obtained his Ph.D. from the University of Melbourne, Master degree in Engineering from Hebei University of Technology, and Bachelor degree in Science from National University of Defense Technology.
 讲座内容: I introduce two prediction problems in this talk. One is about conformational B-cell epitope prediction, the other is about protein binding hotspot prediction. For the first problem, I present a two-stage machine learning method which can achieve a much higher performance than the state-of-the-art methods for the detection of B-cell epitopes. For the second problem, I present a double water exclusion hypothesis to characterize protein binding hotspots. This hypothesis translates binding free energy problems into graph mining problems.