Bayesian Neural Networks for Selection of Drug Sensitive Genes

doi:10.1080/01621459.2017.1409122

CORC > 数学与系统科学研究院 > 中国科学院数学与系统科学研究院 > 系统科学研究所

	Bayesian Neural Networks for Selection of Drug Sensitive Genes
	Liang, Faming 1; Li, Qizhai2 ; Zhou, Lei 3
刊名	JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
	2018
卷号	113 期号:523 页码:955-972
关键词	Cancer cell line encyclopedia Nonlinear variable selection Omics data OpenMP Parallel Markov chain Monte Carlo
ISSN号	0162-1459
DOI	10.1080/01621459.2017.1409122
英文摘要	Recent advances in high-throughput biotechnologies have provided an unprecedented opportunity for biomarker discovery, which, from a statistical point of view, can be cast as a variable selection problem. This problem is challenging due to the high-dimensional and nonlinear nature of omics data and, in general, it suffers three difficulties: (i) an unknown functional form of the nonlinear system, (ii) variable selection consistency, and (iii) high-demanding computation. To circumvent the first difficulty, we employ a feed-forward neural network to approximate the unknown nonlinear function motivated by its universal approximation ability. To circumvent the second difficulty, we conduct structure selection for the neural network, which induces variable selection, by choosing appropriate prior distributions that lead to the consistency of variable selection. To circumvent the third difficulty, we implement the population stochastic approximation Monte Carlo algorithm, a parallel adaptive Markov Chain Monte Carlo algorithm, on the OpenMP platform that provides a linear speedup for the simulation with the number of cores of the computer. The numerical results indicate that the proposed method can work very well for identification of relevant variables for high-dimensional nonlinear systems. The proposed method is successfully applied to identification of the genes that are associated with anticancer drug sensitivities based on the data collected in the cancer cell line encyclopedia study. Supplementary materials for this article are available online.
资助项目	NSF[DMS-1612924] ; NSF[DMS/NIGMS R01-GM117597]
WOS研究方向	Mathematics
语种	英语
出版者	AMER STATISTICAL ASSOC
WOS记录号	WOS:000446710500001
内容类型	期刊论文
源URL	[http://ir.amss.ac.cn/handle/2S8OKBNM/31333]
专题	系统科学研究所
通讯作者	Liang, Faming
作者单位	1.Purdue Univ, Dept Stat, W Lafayette, IN 47906 USA 2.Chinese Acad Sci, Acad Math & Syst Sci, Beijing, Peoples R China 3.Univ Florida, Dept Mol Genet & Microbiol, Gainesville, FL USA
推荐引用方式 GB/T 7714	Liang, Faming,Li, Qizhai,Zhou, Lei. Bayesian Neural Networks for Selection of Drug Sensitive Genes[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION,2018,113(523):955-972.
APA	Liang, Faming,Li, Qizhai,&Zhou, Lei.(2018).Bayesian Neural Networks for Selection of Drug Sensitive Genes.JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION,113(523),955-972.
MLA	Liang, Faming,et al."Bayesian Neural Networks for Selection of Drug Sensitive Genes".JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION 113.523(2018):955-972.