Genotype-environment interaction in transmission disequilibrium tests

Abstract

Transmission disequilibrium tests (TDTs) provide an approach to the detection of associations between alleles at marker loci and risk of complex disorders. The logistic regression approach to TDTs proposed by Sham and Curtis (1995) is generalized to provide separate tests of the main effects of marker loci on genetic risk and genotype-environment interaction (G x E) arising because multiple alleles differ in their sensitivity to specified environmental covariates. A modification of the same model may be used to detect the effects of genomic imprinting on the expression of susceptibility loci. In the presence of G x E, highly significant genetic effects may be present that will not produce marked twin or sibling resemblance and will not yield significant associations in conventional TDTs. However, simulation studies show how the logistic regression model can be used to detect the main effects of marker alleles and their interaction with covariates on continuous outcomes in offspring-parent trios, pairs of siblings and their parents, and monozygotic twin pairs and their parents. TDT tests with MZ with twin pairs permit the detection of alleles whose primary effects on the phenotype are mediated through the control of sensitivity to latent features of the within-family environment. It is shown that although the genotype-environment correlation caused by the environmental effects of parental alleles on offspring phenotypes can produce spurious marker-phenotype association in population studies, the outcome of TDTs is not biased thereby.