Genomic signatures of local adaptation to the degree of environmental predictability in rotifers

Abstract

Environmental fluctuations are ubiquitous and thus essential for the study of adaptation. Despite this, genome evolution in response to environmental fluctuations -and more specifically to the degree of environmental predictability- is still unknown. Saline lakes in the Mediterranean region are remarkably diverse in their ecological conditions, which can lead to divergent local adaptation patterns in the inhabiting aquatic organisms. The facultatively sexual rotifer Brachionus plicatilis shows diverging local adaptation in its life-history traits in relation to estimated environmental predictability in its habitats. Here, we used an integrative approach -combining environmental, phenotypic and genomic data for the same populations- to understand the genomic basis of this diverging adaptation. Firstly, a novel draft genome for B. plicatilis was assembled. Then, genome-wide polymorphisms were studied using genotyping by sequencing on 270 clones from nine populations in eastern Spain. As a result, 4,543 high-quality SNPs were identified and genotyped. More than 90 SNPs were found to be putatively under selection with signatures of diversifying and balancing selection. Over 140 SNPs were correlated with environmental or phenotypic variables revealing signatures of local adaptation, including environmental predictability. Putative functions were associated to most of these SNPs, since they were located within annotated genes. Our results reveal associations between genomic variation and the degree of environmental predictability, providing genomic evidence of adaptation to local conditions in natural rotifer populations.

Figure 1

Principal component analysis based on 4,543 genome-wide SNPs for 30 clones (dots) from each of the nine Brachionus plicatilis populations. Ellipsoids are the 95% confidence interval for each population. Percentage of variance explained by each principal component is shown between parentheses in the axis label.

Figure 2

Relationship between F_ST and log10(q value) based on 4,543 genome-wide SNPs in nine rotifer field populations according to BayeScan. Adopting a p-value < 0.05 criterion, SNPs on the right side of the vertical line are putatively under selection.

Figure 3

Bayesian factors (BF) and mean rank for the correlation between SNPs (dots) and three environmental (upper row panels) and two phenotypic (lower row panels) variables. Results are based on twenty replicate runs of Bayenv. Vertical red line shows the mean rank threshold (mean rank > 0.99) to consider a SNP to be outlier (red dots).

Figure 4

Venn diagram showing the number of SNPs correlated with each variable according to Bayenv. The number of genes with at least a SNP in its coding regions is shown between parentheses. Aerial image of the pond from PNOA 2009 CC-BY 4.0 Instituto Geográfico Nacional - ign.es.

Figure 5

In the center, location of the nine lakes studied here. For each pond the water-surface area time series and its predictability (P) and hydroperiod values (H) are shown. Data obtained from Franch-Gras et al..