Modeling dependent gene expression

Donatello Telesca, Peter Müller, Giovanni Parmigiani, Ralph S. Freedman

Research output: Contribution to journalArticle

Abstract

In this paper we propose a Bayesian approach for inference about dependence of high throughput gene expression. Our goals are to use prior knowledge about pathways to anchor inference about dependence among genes; to account for this dependence while making inferences about differences in mean expression across phenotypes; and to explore differences in the dependence itself across phenotypes. Useful features of the proposed approach are a model-based parsimonious representation of expression as an ordinal outcome, a novel and flexible representation of prior information on the nature of dependencies, and the use of a coherent probability model over both the structure and strength of the dependencies of interest. We valuate our approach through simulations and in the analysis of data on expression of genes in the Complement and Coagulation Cascade pathway in ovarian cancer.

Original languageEnglish (US)
Pages (from-to)542-560
Number of pages19
JournalAnnals of Applied Statistics
Volume6
Issue number2
DOIs
StatePublished - Jun 2012
Externally publishedYes

Fingerprint

Gene expression
Gene Expression
Genes
Dependent
Coagulation
Anchors
Modeling
Phenotype
Pathway
Throughput
Gene
Ovarian Cancer
Probability Model
Prior Information
Prior Knowledge
Bayesian Approach
High Throughput
Cascade
Complement
Model-based

Keywords

  • Conditional independence
  • Microarray data
  • Probability of expression
  • Probit models
  • Reciprocal graphs
  • Reversible jumps MCMC

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Modeling and Simulation
  • Statistics and Probability

Cite this

Telesca, D., Müller, P., Parmigiani, G., & Freedman, R. S. (2012). Modeling dependent gene expression. Annals of Applied Statistics, 6(2), 542-560. https://doi.org/10.1214/11-AOAS525

Modeling dependent gene expression. / Telesca, Donatello; Müller, Peter; Parmigiani, Giovanni; Freedman, Ralph S.

In: Annals of Applied Statistics, Vol. 6, No. 2, 06.2012, p. 542-560.

Research output: Contribution to journalArticle

Telesca, D, Müller, P, Parmigiani, G & Freedman, RS 2012, 'Modeling dependent gene expression', Annals of Applied Statistics, vol. 6, no. 2, pp. 542-560. https://doi.org/10.1214/11-AOAS525
Telesca D, Müller P, Parmigiani G, Freedman RS. Modeling dependent gene expression. Annals of Applied Statistics. 2012 Jun;6(2):542-560. https://doi.org/10.1214/11-AOAS525
Telesca, Donatello ; Müller, Peter ; Parmigiani, Giovanni ; Freedman, Ralph S. / Modeling dependent gene expression. In: Annals of Applied Statistics. 2012 ; Vol. 6, No. 2. pp. 542-560.
@article{e7637adda8714d43864594f1500e54f5,
title = "Modeling dependent gene expression",
abstract = "In this paper we propose a Bayesian approach for inference about dependence of high throughput gene expression. Our goals are to use prior knowledge about pathways to anchor inference about dependence among genes; to account for this dependence while making inferences about differences in mean expression across phenotypes; and to explore differences in the dependence itself across phenotypes. Useful features of the proposed approach are a model-based parsimonious representation of expression as an ordinal outcome, a novel and flexible representation of prior information on the nature of dependencies, and the use of a coherent probability model over both the structure and strength of the dependencies of interest. We valuate our approach through simulations and in the analysis of data on expression of genes in the Complement and Coagulation Cascade pathway in ovarian cancer.",
keywords = "Conditional independence, Microarray data, Probability of expression, Probit models, Reciprocal graphs, Reversible jumps MCMC",
author = "Donatello Telesca and Peter M{\"u}ller and Giovanni Parmigiani and Freedman, {Ralph S.}",
year = "2012",
month = "6",
doi = "10.1214/11-AOAS525",
language = "English (US)",
volume = "6",
pages = "542--560",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "2",

}

TY - JOUR

T1 - Modeling dependent gene expression

AU - Telesca, Donatello

AU - Müller, Peter

AU - Parmigiani, Giovanni

AU - Freedman, Ralph S.

PY - 2012/6

Y1 - 2012/6

N2 - In this paper we propose a Bayesian approach for inference about dependence of high throughput gene expression. Our goals are to use prior knowledge about pathways to anchor inference about dependence among genes; to account for this dependence while making inferences about differences in mean expression across phenotypes; and to explore differences in the dependence itself across phenotypes. Useful features of the proposed approach are a model-based parsimonious representation of expression as an ordinal outcome, a novel and flexible representation of prior information on the nature of dependencies, and the use of a coherent probability model over both the structure and strength of the dependencies of interest. We valuate our approach through simulations and in the analysis of data on expression of genes in the Complement and Coagulation Cascade pathway in ovarian cancer.

AB - In this paper we propose a Bayesian approach for inference about dependence of high throughput gene expression. Our goals are to use prior knowledge about pathways to anchor inference about dependence among genes; to account for this dependence while making inferences about differences in mean expression across phenotypes; and to explore differences in the dependence itself across phenotypes. Useful features of the proposed approach are a model-based parsimonious representation of expression as an ordinal outcome, a novel and flexible representation of prior information on the nature of dependencies, and the use of a coherent probability model over both the structure and strength of the dependencies of interest. We valuate our approach through simulations and in the analysis of data on expression of genes in the Complement and Coagulation Cascade pathway in ovarian cancer.

KW - Conditional independence

KW - Microarray data

KW - Probability of expression

KW - Probit models

KW - Reciprocal graphs

KW - Reversible jumps MCMC

UR - http://www.scopus.com/inward/record.url?scp=84866254664&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866254664&partnerID=8YFLogxK

U2 - 10.1214/11-AOAS525

DO - 10.1214/11-AOAS525

M3 - Article

C2 - 28473730

AN - SCOPUS:84866254664

VL - 6

SP - 542

EP - 560

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 2

ER -