Speaker：Institute for Interdisciplinary Information Sciences, Tsinghua University
Zeng Jianyang （Tenure-Track associate professor，PhD supervisor, “one thousand talents plan”, advisor of “Yao Qizhi”class）
Date：Oct 10, 14:00- 15:00
Venue： B121, Main Building
The emergence of large-scale genomic, chemical and pharmacological data provides new opportunities for drug discovery and repositioning. In this talk, I will present our recent progress on applying machine learning algorithms for drug-target interaction prediction and computational drug repositioning (i.e., finding the new uses of old drugs). First, we develop a new computational pipeline, called DTINet, to predict novel drug-target interactions (DTIs) from a constructed heterogeneous network, which integrates diverse drug-related information. Second, we propose DeepCPI, a new framework that combines feature embedding (a technique of representation learning) with deep learning for predicting compound-protein interactions at large scale. In addition to comprehensive computational tests on real biological data, we have experimentally validated a number of new interactions predicted by our methods for several important protein targets, including COX proteins, and the GPCR proteins GLP-1R and RXFP4. Both our computational and wet-lab experimental results suggest that our algorithms can offer a useful and powerful pipeline for drug development and drug repositioning at large scale.
Bio of Speaker:
Zeng Jianyang, Tenure-track Assistant Professor and Doctoral Tutor of Tsinghua University Cross Research Institute, was selected in the organization of the fifth group of "young people plan." He received bachelor's and master's degrees from Zhejiang University in 1999 and 2002 respectively. In 2011, he received his Ph.D. in computer science from Duke University in the United States. From 2011 to 2012, he was engaged in postdoctoral research at the Department of Computer Science at Duke University and Duke Medical College. In 2012 as an overseas talent he was introduced to Tsinghua University Interdisciplinary Information Research Institute. At present, his main research directions include computational biology, machine learning and large-scale data analysis. He has published more than 40 papers in international core journals and conferences, including Nature magazine, Nature magazine, Nature Communications, Cellular magazine, Cellular System, Cell Systems), Nucleic Acids Research, Bioinformatics, IEEE / ACM Transactions on Computational Biology and Bioinformatics, International Symposium on Computational Biology and Artificial Intelligence RECOMB, ISMB and AAAI. In the field of biology and artificial intelligence of the world-class conference ISMB, RECOMB, IJCAI, he served as a member of the Committee. For more information, please visit http://iiis.tsinghua.edu.cn/zengjy or http://iiis.tsinghua.edu.cn/~compbio.
School of Software