|主题：||Estimating Time-Varying Directed Gene Regulation Networks|
报告题目： Estimating Time-Varying Directed Gene Regulation Networks
报 告 人： 曹际国博士
报告时间 ：2018年7月9日上午 16:00-17:00
Theproblem of modeling the dynamical regulation process within a gene network hasbeen of great interest for a long time. We propose to model this dynamicalsystem with a large number of nonlinear ordinary differential equations (ODEs),in which the regulation function is estimated directly from data without anyparametric assumption. Most current research assumes the gene regulationnetwork is static, but in reality, the connection and regulation function ofthe network may change with time or environment. This change is reflected inour dynamical model by allowing the regulation function varying with the geneexpression and forcing this regulation function to be zero if no regulationhappens. We introduce a statistical method called functional SCAD to estimate atime-varying sparse and directed gene regulation network, and, simultaneously, to provide a smoothestimation of the regulation function and identify the interval in which noregulation effect exists. The finite sample performance of the proposed methodis investigated in a Monte Carlo simulation study. Our method is demonstratedby estimating a time-varying directed gene regulation network of 20 genesinvolved in muscle development during the embryonic stage of Drosophilamelanogaster.
Dr. JiguoCao is the Canada Research Chair in Data Science at the Department ofStatistics and Actuarial Science, Simon Fraser University (SFU). He is also theDirector of Pacific Blue Cross Health Informatics Laboratory and the AssociateFaculty Member at School of Computing Science, SFU. He is serving as theAssociate Editor of Biometrics, Canadian Journal Statistics, Journal ofAgricultural, Biological, and Environmental Statistics, and Statistics andProbability Letter. He obtained his PhD in statistics at McGill University in2006 and worked as postdoctoral associate in statistics genetics at YaleUniversity in 2006-2007 before joining SFU with a faculty member in 2007. Dr.Cao's research interests include functional data analysis and estimating differentialequation models.