Genomic population structure and local adaptation of the wild strawberry Fragaria nilgerrensis

Abstract

The crop wild relative, Fragaria nilgerrensis, is adapted to a variety of diverse habitats across its native range in China. Thus, discoveries made in this species could serve useful to guide the development of new superior strawberry cultivars that are resilient to new or variable environments. However, the genetic diversity and genetic architecture of traits in this species underlying important adaptive traits remain poorly understood. Here, we used whole-genome resequencing data from 193 F. nilgerrensis individuals spanning the distribution range in China to investigate the genetic diversity, population structure and the genomic basis of local adaptation. We identified four genetic groups, with the western group located in Hengduan Mountains exhibited the highest genetic diversity. Redundancy analysis suggests that both environment and geographic variables shaped a significant proportion of genomic variation. Our analyses revealed that the environmental difference explains more of the observed genetic variation than geographic distance. This suggests that adaptation to distinct habitats, unique combination of abiotic factors, likely drove genetic differentiation. Lastly, by implementing selective sweeps scans and genome-environment association analysis throughout the genome, we identified the genetic variation associated with local adaptation and investigated the functions of putative candidate genes in F. nilgerrensis.

Figure 1

a Population structure of F. nilgerrensis identified with STRUCTURE based on genome-wide SNPs. K = 2 shows the highest ∆K, and K = 4 represents the fine-scale structure within F. nilgerrensis. b PCA for all populations based on the same SNP data set as STRUCTURE. (c) Neighbor-joining phylogenetic tree of all samples.

Figure 2

Historical changes in effective population size of the four F. nilgerrensis groups. a Inferred using MSMC based on sets of four haplotypes, with solid lines representing medians and shading representing ± standard deviation calculated across pairs of haplotypes. The dark gray bar indicates the period of the LGM. b Inferred using SMC++ based on individuals in each group

Figure 3

IBD, IBE, and RDA. a Genetic pairwise differentiation plotted against geographic distances. b Environmental distances between populations. c RDA testing the effect of geographic and environmental variables on the degree of genetic differentiation. The first two canonical axes (RDA1 and RDA2) are shown.

Figure 4

Manhattan plots for the results of GEA. a Empirical Bayesian P-value (eBPmc) for an association with the first environment principal component (top panel) and the second environment principal component (bottom panel). The dotted black line establishes the eBPmc significance threshold at 3. b SNP loadings on the first RDA axis (top panel) and the second RDA axis (bottom panel) accounting for spatial structure among populations. The black dots represent SNPs with significant associations along the RDA axes (at least three standard deviations away from the mean squared loadings). We only show the first two RDA axes here.