A penalized robust method for identifying gene-environment interactions

Xingjie Shi, Jin Liu, Jian Huang, Yong Zhou, Yang Xie, Shuangge Ma

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

In high-throughput studies, an important objective is to identify gene-environment interactions associated with disease outcomes and phenotypes. Many commonly adopted methods assume specific parametric or semiparametric models, which may be subject to model misspecification. In addition, they usually use significance level as the criterion for selecting important interactions. In this study, we adopt the rank-based estimation, which is much less sensitive to model specification than some of the existing methods and includes several commonly encountered data and models as special cases. Penalization is adopted for the identification of gene-environment interactions. It achieves simultaneous estimation and identification and does not rely on significance level. For computation feasibility, a smoothed rank estimation is further proposed. Simulation shows that under certain scenarios, for example, with contaminated or heavy-tailed data, the proposed method can significantly outperform the existing alternatives with more accurate identification. We analyze a lung cancer prognosis study with gene expression measurements under the AFT (accelerated failure time) model. The proposed method identifies interactions different from those using the alternatives. Some of the identified genes have important implications.

Original languageEnglish (US)
Pages (from-to)220-230
Number of pages11
JournalGenetic Epidemiology
Volume38
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Gene-Environment Interaction
Lung Neoplasms
Phenotype
Gene Expression
Genes

Keywords

  • Gene-environment interaction
  • Marker identification
  • Penalization
  • Robust rank estimation

ASJC Scopus subject areas

  • Genetics(clinical)
  • Epidemiology

Cite this

A penalized robust method for identifying gene-environment interactions. / Shi, Xingjie; Liu, Jin; Huang, Jian; Zhou, Yong; Xie, Yang; Ma, Shuangge.

In: Genetic Epidemiology, Vol. 38, No. 3, 2014, p. 220-230.

Research output: Contribution to journalArticle

Shi, Xingjie ; Liu, Jin ; Huang, Jian ; Zhou, Yong ; Xie, Yang ; Ma, Shuangge. / A penalized robust method for identifying gene-environment interactions. In: Genetic Epidemiology. 2014 ; Vol. 38, No. 3. pp. 220-230.
@article{1be103e250a74227add1b485daf828a6,
title = "A penalized robust method for identifying gene-environment interactions",
abstract = "In high-throughput studies, an important objective is to identify gene-environment interactions associated with disease outcomes and phenotypes. Many commonly adopted methods assume specific parametric or semiparametric models, which may be subject to model misspecification. In addition, they usually use significance level as the criterion for selecting important interactions. In this study, we adopt the rank-based estimation, which is much less sensitive to model specification than some of the existing methods and includes several commonly encountered data and models as special cases. Penalization is adopted for the identification of gene-environment interactions. It achieves simultaneous estimation and identification and does not rely on significance level. For computation feasibility, a smoothed rank estimation is further proposed. Simulation shows that under certain scenarios, for example, with contaminated or heavy-tailed data, the proposed method can significantly outperform the existing alternatives with more accurate identification. We analyze a lung cancer prognosis study with gene expression measurements under the AFT (accelerated failure time) model. The proposed method identifies interactions different from those using the alternatives. Some of the identified genes have important implications.",
keywords = "Gene-environment interaction, Marker identification, Penalization, Robust rank estimation",
author = "Xingjie Shi and Jin Liu and Jian Huang and Yong Zhou and Yang Xie and Shuangge Ma",
year = "2014",
doi = "10.1002/gepi.21795",
language = "English (US)",
volume = "38",
pages = "220--230",
journal = "Genetic Epidemiology",
issn = "0741-0395",
publisher = "Wiley-Liss Inc.",
number = "3",

}

TY - JOUR

T1 - A penalized robust method for identifying gene-environment interactions

AU - Shi, Xingjie

AU - Liu, Jin

AU - Huang, Jian

AU - Zhou, Yong

AU - Xie, Yang

AU - Ma, Shuangge

PY - 2014

Y1 - 2014

N2 - In high-throughput studies, an important objective is to identify gene-environment interactions associated with disease outcomes and phenotypes. Many commonly adopted methods assume specific parametric or semiparametric models, which may be subject to model misspecification. In addition, they usually use significance level as the criterion for selecting important interactions. In this study, we adopt the rank-based estimation, which is much less sensitive to model specification than some of the existing methods and includes several commonly encountered data and models as special cases. Penalization is adopted for the identification of gene-environment interactions. It achieves simultaneous estimation and identification and does not rely on significance level. For computation feasibility, a smoothed rank estimation is further proposed. Simulation shows that under certain scenarios, for example, with contaminated or heavy-tailed data, the proposed method can significantly outperform the existing alternatives with more accurate identification. We analyze a lung cancer prognosis study with gene expression measurements under the AFT (accelerated failure time) model. The proposed method identifies interactions different from those using the alternatives. Some of the identified genes have important implications.

AB - In high-throughput studies, an important objective is to identify gene-environment interactions associated with disease outcomes and phenotypes. Many commonly adopted methods assume specific parametric or semiparametric models, which may be subject to model misspecification. In addition, they usually use significance level as the criterion for selecting important interactions. In this study, we adopt the rank-based estimation, which is much less sensitive to model specification than some of the existing methods and includes several commonly encountered data and models as special cases. Penalization is adopted for the identification of gene-environment interactions. It achieves simultaneous estimation and identification and does not rely on significance level. For computation feasibility, a smoothed rank estimation is further proposed. Simulation shows that under certain scenarios, for example, with contaminated or heavy-tailed data, the proposed method can significantly outperform the existing alternatives with more accurate identification. We analyze a lung cancer prognosis study with gene expression measurements under the AFT (accelerated failure time) model. The proposed method identifies interactions different from those using the alternatives. Some of the identified genes have important implications.

KW - Gene-environment interaction

KW - Marker identification

KW - Penalization

KW - Robust rank estimation

UR - http://www.scopus.com/inward/record.url?scp=84895920054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84895920054&partnerID=8YFLogxK

U2 - 10.1002/gepi.21795

DO - 10.1002/gepi.21795

M3 - Article

C2 - 24616063

AN - SCOPUS:84895920054

VL - 38

SP - 220

EP - 230

JO - Genetic Epidemiology

JF - Genetic Epidemiology

SN - 0741-0395

IS - 3

ER -