Bayesian mixture models for the incorporation of prior knowledge to inform genetic association studies

Brooke L. Fridley, Daniel Serie, Gregory Jenkins, Kristin White, William Bamlet, John D. Potter, Ellen L Goode

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

In the last decade, numerous genome-wide linkage and association studies of complex diseases have been completed. The critical question remains of how to best use this potentially valuable information to improve study design and statistical analysis in current and future genetic association studies. With genetic effect size for complex diseases being relatively small, the use of all available information is essential to untangle the genetic architecture of complex diseases. One promising approach to incorporating prior knowledge from linkage scans, or other information, is to up- or down-weight P-values resulting from genetic association study in either a frequentist or Bayesian manner. As an alternative to these methods, we propose a fully Bayesian mixture model to incorporate previous knowledge into on-going association analysis. In this approach, both the data and previous information collectively inform the association analysis, in contrast to modifying the association results (P-values) to conform to the prior knowledge. By using a Bayesian framework, one has flexibility in modeling, and is able to comprehensively assess the impact of model specification on posterior inferences. We illustrate the use of this method through a genome-wide linkage study of colorectal cancer, and a genome-wide association study of colorectal polyps.

Original languageEnglish (US)
Pages (from-to)418-426
Number of pages9
JournalGenetic Epidemiology
Volume34
Issue number5
DOIs
StatePublished - Jul 2010

Fingerprint

Genetic Association Studies
Genome-Wide Association Study
Weights and Measures
Polyps
Colorectal Neoplasms
Genome

Keywords

  • Bayesian
  • Genetic association
  • Linkage
  • Mixture model
  • Prior information

ASJC Scopus subject areas

  • Genetics(clinical)
  • Epidemiology

Cite this

Bayesian mixture models for the incorporation of prior knowledge to inform genetic association studies. / Fridley, Brooke L.; Serie, Daniel; Jenkins, Gregory; White, Kristin; Bamlet, William; Potter, John D.; Goode, Ellen L.

In: Genetic Epidemiology, Vol. 34, No. 5, 07.2010, p. 418-426.

Research output: Contribution to journalArticle

Fridley, Brooke L. ; Serie, Daniel ; Jenkins, Gregory ; White, Kristin ; Bamlet, William ; Potter, John D. ; Goode, Ellen L. / Bayesian mixture models for the incorporation of prior knowledge to inform genetic association studies. In: Genetic Epidemiology. 2010 ; Vol. 34, No. 5. pp. 418-426.
@article{a0649c20673e48e5a9ebcc4f138b1e6c,
title = "Bayesian mixture models for the incorporation of prior knowledge to inform genetic association studies",
abstract = "In the last decade, numerous genome-wide linkage and association studies of complex diseases have been completed. The critical question remains of how to best use this potentially valuable information to improve study design and statistical analysis in current and future genetic association studies. With genetic effect size for complex diseases being relatively small, the use of all available information is essential to untangle the genetic architecture of complex diseases. One promising approach to incorporating prior knowledge from linkage scans, or other information, is to up- or down-weight P-values resulting from genetic association study in either a frequentist or Bayesian manner. As an alternative to these methods, we propose a fully Bayesian mixture model to incorporate previous knowledge into on-going association analysis. In this approach, both the data and previous information collectively inform the association analysis, in contrast to modifying the association results (P-values) to conform to the prior knowledge. By using a Bayesian framework, one has flexibility in modeling, and is able to comprehensively assess the impact of model specification on posterior inferences. We illustrate the use of this method through a genome-wide linkage study of colorectal cancer, and a genome-wide association study of colorectal polyps.",
keywords = "Bayesian, Genetic association, Linkage, Mixture model, Prior information",
author = "Fridley, {Brooke L.} and Daniel Serie and Gregory Jenkins and Kristin White and William Bamlet and Potter, {John D.} and Goode, {Ellen L}",
year = "2010",
month = "7",
doi = "10.1002/gepi.20494",
language = "English (US)",
volume = "34",
pages = "418--426",
journal = "Genetic Epidemiology",
issn = "0741-0395",
publisher = "Wiley-Liss Inc.",
number = "5",

}

TY - JOUR

T1 - Bayesian mixture models for the incorporation of prior knowledge to inform genetic association studies

AU - Fridley, Brooke L.

AU - Serie, Daniel

AU - Jenkins, Gregory

AU - White, Kristin

AU - Bamlet, William

AU - Potter, John D.

AU - Goode, Ellen L

PY - 2010/7

Y1 - 2010/7

N2 - In the last decade, numerous genome-wide linkage and association studies of complex diseases have been completed. The critical question remains of how to best use this potentially valuable information to improve study design and statistical analysis in current and future genetic association studies. With genetic effect size for complex diseases being relatively small, the use of all available information is essential to untangle the genetic architecture of complex diseases. One promising approach to incorporating prior knowledge from linkage scans, or other information, is to up- or down-weight P-values resulting from genetic association study in either a frequentist or Bayesian manner. As an alternative to these methods, we propose a fully Bayesian mixture model to incorporate previous knowledge into on-going association analysis. In this approach, both the data and previous information collectively inform the association analysis, in contrast to modifying the association results (P-values) to conform to the prior knowledge. By using a Bayesian framework, one has flexibility in modeling, and is able to comprehensively assess the impact of model specification on posterior inferences. We illustrate the use of this method through a genome-wide linkage study of colorectal cancer, and a genome-wide association study of colorectal polyps.

AB - In the last decade, numerous genome-wide linkage and association studies of complex diseases have been completed. The critical question remains of how to best use this potentially valuable information to improve study design and statistical analysis in current and future genetic association studies. With genetic effect size for complex diseases being relatively small, the use of all available information is essential to untangle the genetic architecture of complex diseases. One promising approach to incorporating prior knowledge from linkage scans, or other information, is to up- or down-weight P-values resulting from genetic association study in either a frequentist or Bayesian manner. As an alternative to these methods, we propose a fully Bayesian mixture model to incorporate previous knowledge into on-going association analysis. In this approach, both the data and previous information collectively inform the association analysis, in contrast to modifying the association results (P-values) to conform to the prior knowledge. By using a Bayesian framework, one has flexibility in modeling, and is able to comprehensively assess the impact of model specification on posterior inferences. We illustrate the use of this method through a genome-wide linkage study of colorectal cancer, and a genome-wide association study of colorectal polyps.

KW - Bayesian

KW - Genetic association

KW - Linkage

KW - Mixture model

KW - Prior information

UR - http://www.scopus.com/inward/record.url?scp=77954179645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954179645&partnerID=8YFLogxK

U2 - 10.1002/gepi.20494

DO - 10.1002/gepi.20494

M3 - Article

C2 - 20583285

AN - SCOPUS:77954179645

VL - 34

SP - 418

EP - 426

JO - Genetic Epidemiology

JF - Genetic Epidemiology

SN - 0741-0395

IS - 5

ER -