Evolution of polygenic traits under global vs local adaptation

Abstract

Observations about the number, frequency, effect size, and genomic distribution of alleles associated with complex traits must be interpreted in light of evolutionary process. These characteristics, which constitute a trait's genetic architecture, can dramatically affect evolutionary outcomes in applications from agriculture to medicine, and can provide a window into how evolution works. Here, I review theoretical predictions about the evolution of genetic architecture under spatially homogeneous, global adaptation as compared with spatially heterogeneous, local adaptation. Due to the tension between divergent selection and migration, local adaptation can favor "concentrated" genetic architectures that are enriched for alleles of larger effect, clustered in a smaller number of genomic regions, relative to expectations under global adaptation. However, the evolution of such architectures may be limited by many factors, including the genotypic redundancy of the trait, mutation rate, and temporal variability of environment. I review the circumstances in which predictions differ for global vs local adaptation and discuss where progress can be made in testing hypotheses using data from natural populations and lab experiments. As the field of comparative population genomics expands in scope, differences in architecture among traits and species will provide insights into how evolution works, and such differences must be interpreted in light of which kind of selection has been operating.

Keywords: genetic architecture; genome scan; global adaptation; local adaptation; migration; recombination; selection.

Figure 1

Local adaptation can occur with very different underlying genetic architecture, depending on the balance between migration and selection, allele effect size, drift, mutation rate, and genotypic redundancy. Panel (A) shows a concentrated architecture, panel B shows a stable diffuse architecture, and panel C shows a transient architecture. Panels (D–F) show the mean phenotypic divergence (D) between two simulated populations experiencing stabilizing selection toward local optima of ±1 (such that optimal local adaptation occurs when D = 2); panels A–C show the contribution of each locus to phenotypic differentiation (d) for 160 equally spaced loci along a simulated chromosome with an even rate of recombination. Simulations differ according to the parameters shown below each scenario, where V_S is the width of the Gaussian fitness function for stabilizing selection (lower values result in stronger selection), the mutation rate (µ) is per locus, and σ² is the width of the Gaussian function for mutation effect sizes (see Appendix B for simulation details). The concentrated architecture in Panel A evolves mainly through competition among alleles with different linkage relationships. In panel B, migration is low and so there is little advantage for clustering of linked alleles and little architecture evolution. In panel C, individual alleles are often large enough to resist swamping (δ > 0) but the high redundancy and mutation rate result in a large number of alleles segregating at any given time, resulting in rapid turnover in the evolved architecture.

Figure 2

Comparison of the probability of a new mutation rising to fixation under global adaptation vs establishment under local adaptation (A) and the effect of linkage with local adaptation (B). Under global adaptation with spatial structure a decrease in fixation probability with decreasing migration occurs over approximately the same migration rates regardless of the strength of selection (s; A). By contrast, with local adaptation a reduction in establishment probability with increasing migration occurs over lower migration rates for more weakly selected mutations, but over higher migration rates for more strongly selected ones (A). Linkage to an existing locally adapted polymorphism dramatically increases the establishment probability of new mutations (B), but this is most pronounced within a narrow zone of migration rates, which shifts with the strength of selection on the new mutation (a). Panel A contrasts the global adaptation model of Whitlock (2003) with the two-population local adaptation approximation of Yeaman and Otto (2011; Equation 3), but splicing δ into 2 s N_e/N_tot (instead of Kimura’s equation) and assuming N_e = N_tot = 1000. Panel B shows the continent-island splicing approximation of Yeaman et al. (2016; Equation 7) with strength of selection of b = 0.1 on the established allele, strength of selection of a on the new mutation, and recombination rate r between loci.