Genomic Analysis of European Drosophila melanogaster Populations Reveals Longitudinal Structure, Continent-Wide Selection, and Previously Unknown DNA Viruses

Abstract

Genetic variation is the fuel of evolution, with standing genetic variation especially important for short-term evolution and local adaptation. To date, studies of spatiotemporal patterns of genetic variation in natural populations have been challenging, as comprehensive sampling is logistically difficult, and sequencing of entire populations costly. Here, we address these issues using a collaborative approach, sequencing 48 pooled population samples from 32 locations, and perform the first continent-wide genomic analysis of genetic variation in European Drosophila melanogaster. Our analyses uncover longitudinal population structure, provide evidence for continent-wide selective sweeps, identify candidate genes for local climate adaptation, and document clines in chromosomal inversion and transposable element frequencies. We also characterize variation among populations in the composition of the fly microbiome, and identify five new DNA viruses in our samples.

Keywords: SNPs; adaptation, demography; clines; population genomics; selection; structural variants.

Fig. 1.

The geographic distribution of population samples. Locations of all samples in the 2014 DrosEU data set. The color of the circles indicates the sampling season for each location: ten of the 32 locations were sampled at least twice, once in summer and once in fall (see table 1 and supplementary table S1, Supplementary Material online). Note that some of the 12 Ukrainian locations overlap in the map.

Fig. 2.

Candidate signals of selective sweeps in European populations. The central panel shows the distribution of Tajima’s D in 50-kb sliding windows with 40-kb overlap, with red and green dashed lines indicating Tajima’s D = 0 and −1, respectively. The top panel shows a detail of a genomic region on chromosomal arm 2R in the vicinity of Cyp6g1 and Hen1 (highlighted in red), genes reportedly involved in pesticide resistance. This strong sweep signal is characterized by an excess of low-frequency SNP variants and overall negative Tajima’s D in all samples. Colored solid lines depict Tajima’s D for each sample (see supplementary fig. S2, Supplementary Material online, for color codes, Supplementary Material online); the black dashed line shows Tajima’s D averaged across all samples. The bottom panel shows a region on 3L previously identified as a potential target of selection, which shows a similar strong sweep signature. Notably, both regions show strongly reduced genetic variation (supplementary fig. S1, Supplementary Material online).

Fig. 3.

Genetic differentiation among European populations. (A) Average F_ST among populations at putatively neutral sites. The center plot shows the distribution of F_ST values for all 1,128 pairwise population comparisons, with the F_ST values for each comparison obtained from the mean across all 4,034 SNPs used in the analysis. Plots on the left and the right show population pairs in the lower (blue) and upper (red) 5% tails of the F_ST distribution. (B) PCA analysis of allele frequencies at the same SNPs reveals population substructuring in Europe. Hierarchical model fitting using the first four PCs showed that the populations fell into two clusters (indicated by red and blue), with cluster assignment of each population subsequently estimated by k-means clustering. (C) Admixture proportions for each population inferred by model-based clustering with ConStruct are highlighted as pie charts (left plot) or structure plots (center). The optimal number of three spatial layers (K) was inferred by cross-validation (right plot).

Fig. 4.

Manhattan plots of SNPs with q values <0.05 in BayeScEnv association tests with PC1 or PC2 of bioclimatic variables. Vertical lines denote the breakpoints of common inversions. The gene names highlight some candidate genes found in our study and which have previously been identified as varying clinally by Fabian et al. (2012) and Machado et al. (2016) along the North American east coast. Note that q values of 0 (which are infinite on a log-scale) are plotted at the top of each figure, above the gray dash-dotted horizontal lines in order to separate them from the other candidates with q values >0. These zero values are unlikely to be spurious as the densities of these infinite values tend to line up with peaks of log₁₀(q) below the dashed line, suggesting that they represent highly significant continuations of these peaks.

Fig. 5.

Mitochondrial haplotypes. (A) Network showing the relationship of five common mitochondrial haplotypes. (B) Estimated frequency of each mitochondrial haplotype in 48 European samples.

Fig. 6.

Geographic patterns of structural variants. The upper panel shows stacked bar plots with the relative abundances of transposable elements (TEs) in all 48 population samples. The proportion of each repeat class was estimated from sampled reads with dnaPipeTE (two samples per run, 0.1× coverage per sample). The lower panel shows stacked bar plots depicting absolute frequencies of six cosmopolitan inversions in all 48 population samples.

Fig. 7.

Microbiota associated with Drosophila. Relative abundance of Drosophila-associated microbes as assessed by MGRAST classified shotgun sequences. Microbes had to reach at least 3% relative abundance in one of the samples to be represented.