Detection of Viruses Via Statistical Gene Expression Analysis

被引：18

作者：

Chen, Minhua ^{[1
]}

Carlson, David ^{[1
]}

Zaas, Aimee ^{[2
]}

Woods, Christopher W. ^{[2
]}

Ginsburg, Geoffrey S. ^{[2
]}

Hero, Alfred, III ^{[3
]}

Lucas, Joseph ^{[2
]}

Carin, Lawrence ^{[1
]}

机构：

[1] Duke Univ, Dept Elect & Comp Engn, Durham, NC USA

[2] Duke Univ, Dept Med, Inst Genome Sci & Policy, Durham, NC USA

[3] Univ Michigan, Dept Elect & Comp Engn, Ann Arbor, MI 48109 USA

来源：

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING | 2011年 / 58卷 / 03期

关键词：

Bayesian Lasso; elastic net (ENet); grouping effect; multitask learning; variable selection; BAYESIAN-ANALYSIS; CLASSIFICATION; PREDICTION; REGRESSION; SELECTION;

D O I：

10.1109/TBME.2010.2059702

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

We develop a new Bayesian construction of the elastic net (ENet), with variational Bayesian analysis. This modeling framework is motivated by analysis of gene expression data for viruses, with a focus on H3N2 and H1N1 influenza, as well as Rhino virus and RSV (respiratory syncytial virus). Our objective is to understand the biological pathways responsible for the host response to such viruses, with the ultimate objective of developing a clinical test to distinguish subjects infected by such viruses from subjects with other symptom causes (e. g., bacteria). In addition to analyzing these new datasets, we provide a detailed analysis of the Bayesian ENet and compare it to related models.

引用

页码：468 / 479

页数：12

共 31 条

[1] BAYESIAN-ANALYSIS OF BINARY AND POLYCHOTOMOUS RESPONSE DATA [J].