Send to

Choose Destination
Biometrics. 2019 Aug 19. doi: 10.1111/biom.13139. [Epub ahead of print]

Structured gene-environment interaction analysis.

Wu M1,2, Zhang Q3, Ma S2.

Author information

School of Statistics and Management, Shanghai University of Finance and Economics, Shanghai, China.
Department of Biostatistics, Yale University, New Haven, Connecticut.
School of Economics and Wang Yanan Institute for Studies in Economics, Xiamen University, Xiamen, China.


For the etiology, progression, and treatment of complex diseases, gene-environment (G-E) interactions have important implications beyond the main G and E effects. G-E interaction analysis can be more challenging with higher dimensionality and need for accommodating the "main effects, interactions" hierarchy. In recent literature, an array of novel methods, many of which are based on the penalization technique, have been developed. In most of these studies, however, the structures of G measurements, for example, the adjacency structure of single nucleotide polymorphisms (SNPs; attributable to their physical adjacency on the chromosomes) and the network structure of gene expressions (attributable to their coordinated biological functions and correlated measurements) have not been well accommodated. In this study, we develop structured G-E interaction analysis, where such structures are accommodated using penalization for both the main G effects and interactions. Penalization is also applied for regularized estimation and selection. The proposed structured interaction analysis can be effectively realized. It is shown to have consistency properties under high-dimensional settings. Simulations and analysis of GENEVA diabetes data with SNP measurements and TCGA melanoma data with gene expression measurements demonstrate its competitive practical performance.


gene-environment interaction; high-dimensional modeling; structured analysis

[Available on 2021-02-19]

Supplemental Content

Full text links

Icon for Wiley
Loading ...
Support Center