Allele-specific expression reveals interactions between genetic variation and environment

Abstract

Identifying interactions between genetics and the environment (GxE) remains challenging. We have developed EAGLE, a hierarchical Bayesian model for identifying GxE interactions based on associations between environmental variables and allele-specific expression. Combining whole-blood RNA-seq with extensive environmental annotations collected from 922 human individuals, we identified 35 GxE interactions, compared with only four using standard GxE interaction testing. EAGLE provides new opportunities for researchers to identify GxE interactions using functional genomic data.

Figure 1

EAGLE associates allelic specific expression (ASE) with environmental covariates to detect GxE interactions. (a) Allelic imbalance can be driven by allele specific binding of an environmentally responsive transcription factor. (b) Relative to interaction QTL testing, using ASE increases power in the DGN cohort across 30 environmental variables. Interaction testing was performed on SNP within 200kb of each gene, followed by Bonferroni correction. EAGLE provides an internally controlled test and integrates across the cis-regulatory landscape of a gene.

Figure 2

EAGLE detects GxE interactions missed by standard interaction QTL testing. (a) Blood pressure medication modulates regulation of NPRL3, involved in fluid homeostasis. (b) Smoking interacts with regulation of IL10RA. (c–e) Using standard interaction QTL testing as a second phase within EAGLE hits, we detect rs685419 as a promising candidate variant for smoking’s association with IL10RA, lying 4Mb from the TSS in a conserved region corresponding to an enhancer in CD14+ primary cells.

Figure 3

EAGLE detects allele-specific effects of environments measured by “proxy” genes and of direct perturbations. (a) EAGLE recapitulates GxE interactions discovered using immune stimulation of monocytes in vitro. We used genes differentially expressed under immune stimulation in vitro as proxies for the environment (stimulus). The genes detected by EAGLE as being modulated by these environmental proxies replicate in the in vitro data: i.e. they have detectable response QTLs. Network depicts all EAGLE predictions for each stimulus, with replicating interactions highlighted in yellow; each edge is annotated with the tested proxy gene for reference. (b) EAGLE detects allele-specific responses to treatment of rat livers with various toxicants. The strongest association for agonists of the PPARα transcription factor is a known target, Acot1. While total Acot1 expression is up-regulated, we find that rats with the alternative C allele at exonic SNP Chr6:108042464 show no response. (c) Genes associated with PPARα by EAGLE show enrichment of relevant TF binding motifs within 5kb of the TSS.