Epistatic Networks Jointly Influence Phenotypes Related to Metabolic Disease and Gene Expression in Diversity Outbred Mice

Abstract

Genetic studies of multidimensional phenotypes can potentially link genetic variation, gene expression, and physiological data to create multi-scale models of complex traits. The challenge of reducing these data to specific hypotheses has become increasingly acute with the advent of genome-scale data resources. Multi-parent populations derived from model organisms provide a resource for developing methods to understand this complexity. In this study, we simultaneously modeled body composition, serum biomarkers, and liver transcript abundances from 474 Diversity Outbred mice. This population contained both sexes and two dietary cohorts. Transcript data were reduced to functional gene modules with weighted gene coexpression network analysis (WGCNA), which were used as summary phenotypes representing enriched biological processes. These module phenotypes were jointly analyzed with body composition and serum biomarkers in a combined analysis of pleiotropy and epistasis (CAPE), which inferred networks of epistatic interactions between quantitative trait loci that affect one or more traits. This network frequently mapped interactions between alleles of different ancestries, providing evidence of both genetic synergy and redundancy between haplotypes. Furthermore, a number of loci interacted with sex and diet to yield sex-specific genetic effects and alleles that potentially protect individuals from the effects of a high-fat diet. Although the epistatic interactions explained small amounts of trait variance, the combination of directional interactions, allelic specificity, and high genomic resolution provided context to generate hypotheses for the roles of specific genes in complex traits. Our approach moves beyond the cataloging of single loci to infer genetic networks that map genetic etiology by simultaneously modeling all phenotypes.

Keywords: MPP; epistasis; multiparental populations; outbred mouse population; pleiotropy; systems genetics.

Figure 1

Overview of study work flow. Boxes separate steps into four themes: mouse experimentation, processing of genotype and phenotype data, combined analysis of pleiotropy and epistasis (CAPE), and interpretation of network results.

Figure 2

Overview of methods used to filter transcripts with potential trans-eQTL and create coexpression modules.

Figure 3

Four types of network motifs. Each motif consists of two markers interacting to influence one phenotype. The markers can either have the same-signed (coherent) or opposite-signed (incoherent) main effects. Their interaction, which can be either enhancing (positive sign) or suppressing (negative sign), may affect additional phenotypes through other main effects.

Figure 4

Map of the positions of genes encoding transcripts (y-axis) and their associated eQTL (x-axis). The effect of each eQTL is conditioned on the nearest marker, which eliminates diagonal eQTL likely acting in cis. LOD scores range from 7.4 (P = 0.05) to 300, with darker dots represents larger LOD scores. A region on distal Chr 11 (arrow) indicates a potential eQTL hotspot, and may encode a gene that influences many transcripts.

Figure 5

Pearson correlation for all phenotype pairs in this study. Traits tend to be modestly correlated with each other. Physiological traits and expression traits are positively correlated within their groups, but negatively correlated between groups.

Figure 6

LOD scores for genome scans of all eight phenotypes. A single QTL, at distal Chr 1 for cholesterol, was the only locus at genome wide significance (P < 0.05; Arrow 1). Although no other loci were genome-wide significant, a potentially pleiotropic QTL on distal Chr 11 is suggestive for both fat mass and cholesterol (Arrow 2). Horizontal lines denote permutation-based thresholds of P < 0.05 (red, LOD 7.3), P < 0.01 (orange, LOD 6.9), and P < 0.63 (yellow, LOD 5.8).

Figure 7

Estimated allele effects of each strain haplotype on Chr 11 for five traits: log fat mass, cholesterol, leptin, triglycerides, and the redox expression module. The CAST haplotype on distal Chr 11 has pleiotropic effects on all traits (Arrow 1). The NZO and A/J haplotypes have individual effects on cholesterol (Arrow 2) and leptin (Arrow 3), respectively. All effects are relative to the B6 reference.

Figure 8

ETs of combined phentoypes determined by singular value decomposition. (A) Eight orthogonal ETs and their variance content. Proportion of the total variance captured by each ET (gray bars), and relative contributions of each trait to each ET (heatmap) are shown. The box highlights the three ETs selected for CAPE analysis. (B) LOD scores for genome scans of the first three ETs. One QTL on distal Chr 11 was suggestive (P < 0.2, arrow) and may reflect a pleiotropic locus influencing both fat mass and cholesterol. The red and black horizontal lines are at permutation-based thresholds of P < 0.05 (LOD 7.49) and P < 0.2 (LOD 6.54), respectively. (C) Individual haplotype effects for Chr 11 on the first three ETs. The box highlights the QTL location for ET2.

Figure 9

The pleiotropic QTL interaction network derived from CAPE. Main effects, colored by haplotype, appear in the concentric circles. Sex and diet main effects are shown in brown or blue to denote positive and negative effects, respectively. Arrows between chromosomal regions denote genetic interactions that indicate an enhancing effect (brown) or a suppressing effect (blue).

Figure 10

Variance explained by covariates, main effects, and interactions. Bars show the proportion of variance of each trait explained by the covariates, sex (light blue) and diet (dark blue), the main QTL effects (light green), and by the CAPE-derived genetic interactions (dark green). Numbers in the left margin report the number of significant main effects (# Main) and the number of significant interactions (# Int) influencing each trait.

Figure 11

Frequency of haplotype participation in genetic interactions. (A) The number of times haplotypes of each ancestry was the source or target of an interaction, sorted by total number of interactions. The final two columns indicate how many candidate markers were tested for pairwise interactions, and the total number of chromosomes containing the markers. Shading highlights higher counts. (B) A detailed count of the interactions by ancestry and covariate. Darker squares represent higher counts, and counts of 0 are represented by dashes for clarity.

Figure 12

Examples of QTL-sex and sex-diet interactions. (A) The CAST (CST) haplotype at a Chr 11 QTL had a negative effect on the metabolism module relative to all non-CAST haplotypes (—), and interactively enhanced the effect of the male sex. Thus, in males with the CAST haplotype, the metabolism module was lower than expected from the additive model. (B) The WSB (WS) haplotype at a Chr 17 QTL had a positive effect on cholesterol relative to all non-WSB alleles (—). Males also have higher cholesterol than females. The WSB allele suppressed this effect in males, however, and males with the WSB allele had lower cholesterol than expected from the additive model. (C) The HF diet had a negative effect on triglyceride levels relative to the chow diet (Ch), and males had higher triglycerides than females. However, males on the HF diet had higher triglyceride levels than expected from the additive model. Diet enhanced the positive effect of the male sex (M) which, in turn, overcame the negative marginal effect of diet. In (A) and (B) bars show mean phenotype values for animals partitioned by sex and genotype. In (C), bars show phenotype means for animals partitioned by sex and diet. Error bars denote SEs.

Figure 13

Counts of each different motif type in the QTL-QTL network for each phenotype. Darker shading indicates higher counts.

Figure 14

Phenotypic effects of enhancing-incoherent (left) and suppressing-coherent (right) network motifs. Main1 and Main2 denote the average deviation from population mean in normalized phenotype for animals carrying the alternate haplotype at the two QTL. Marker 1 and marker 2 are sorted such that marker 1 always has the lesser effect. Additive is the predicted additive effect determined by the sum of Main1 and Main2. Actual is the observed deviation from the population mean of animals carrying the alternate haplotype at both markers. Lines are drawn to connect dots from individual interactions. Blue and brown lines indicate motifs that bring phenotypes closer and further to the population mean than predicted by the additive model, respectively. Red lines indicate a subset of motifs that exhibit phenotypes more extreme than would be predicted by any additive model.

Figure 15

Gene prioritization for interacting QTL Chr9.2 and Chr2.4. (A) Both the A/J haplotype at Chr9.2 and the CAST haplotype at Chr2.4 have negative effects on the immune module. Together, they have an effect similar to that of the CAST haplotype at Chr 2.4. Error bars show SE. (B) Functional connections between Il1b and Casp4 from the IMP network. The two proteins are predicted to interact functionally with high confidence. (C) The transcripts of Casp4, in Chr9.2, and Il1b, in Chr2.4, are both correlated with the immune module. The transcripts are also correlated with each other.

Figure 16

Gene prioritization for interacting QTL Chr2.2 and Chr9.2. (A) The NOD haplotype at Chr2.4 and the A/J haplotype at Chr9.2 affect the immune module positively and negatively, respectively. Together, they have a negative effect similar to that of the A/J haplotype at Chr9.2. Error bars show SE. (B) Functional connections between Src and Casp4 from the IMP network. The two proteins are predicted to interact functionally by operating in related, but distinct pathways. (C) The transcripts of Src, in Chr 2.2, and Casp4, in Chr 9.2, are both correlated with the immune module. The transcripts are also correlated with each other.

Figure 17

Evidence supporting a role of the 129 haplotype of Sorbs1 increasing triglyceride levels through increased transcription. (A) eQTL mapping of the Sorbs1 transcript across Chr 19. The upper panel shows LOD scores for Sorbs1 transcript levels, with the position of the Sorbs1 gene marked with a vertical gray line. The lower panel shows haplotype effects for Sorbs1 transcript levels. (B) Transcript levels of Sorbs1 in male and female DO mice (a.u., arbitrary units). (C) Correlation between triglyceride levels and Sorbs1 expression ($r=1.7,$ $P<2\times {10}^{-16}$). Female and male mice are shown in blue and green, respectively.