Pathway analysis can increase power to detect associations with a gene or a pathway by combining several signals at the single nucleotide polymorphism (SNP)-level into a single test. In this work, we propose to extend two well-known self-contained methods, the Fisher’s method (FM) and the Adaptive Rank Truncated Product (ARTP) method to the analysis of gene-environment (GxE) interaction at the gene and pathway-level. It has been previously suggested that the permutation procedures that are usually used to derive the significance of these tests are not appropriate for the analysis of GxE interaction and should be replaced by a bootstrap approach. We analyse and compare the performance of the extension of FM and ARTP using the permutation and the parametric bootstrap procedure in simulation studies. We illustrate its application by analysing the interaction between night work and circadian gene polymorphisms in the risk of breast cancer in a case-control study. The ARTP method, adapted for both gene- and pathway-environment interactions, gives promising results and has been wrapped to the R package PIGE available on the CRAN.
|Number of pages||28|
|Journal||Journal de la Société Française de Statistique|
|Publication status||Published - 13 Sep 2018|
- Gene-environment interactions
- Generalized Linear Models
- Pathway analysis
- Resampling methods