Analysis of Multivariate Phenotypes by Canonical Correlation Biplot in Genetic Association Study

Abstract

In the genetic association study of complex diseases, we may obtain several continuous phenotypes which are correlated to each other. The purpose of the analysis is to identify the relationship between genetic polymorphism and multiple phenotypes. Performing univariate analysis separately for each phenotype is common, but it has limitations in detecting pleiotropic genes. Its performance tends to deteriorate in the multiple testing problems. In this study, we suggest to employ a canonical correlation biplot (CCB) and a semi-partial canonical correlation biplot (SPCCB) as the multivariate approaches. The CCB summarizes the correlation between linear composites for phenotypes and genotypes. Also, it produces three kinds of graphs which are able to catch the relationship between genotypes, between phenotypes and ultimately between genotypes and phenotypes at a glance. SPCCB is an extension of the CCB by permitting covariates. We show the results of these methods by applying them to a sample genetic data as an illustration.