Small and genetically highly structured populations in a long-legged bee, Rediviva longimanus, as inferred by pooled RAD-seq

Abstract

Adaptation to local host plants may impact a pollinator's population genetic structure by reducing gene flow and driving population genetic differentiation, representing an early stage of ecological speciation. South African Rediviva longimanus bees exhibit elongated forelegs, a bizarre adaptation for collecting oil from floral spurs of their Diascia hosts. Furthermore, R. longimanus foreleg length (FLL) differs significantly among populations, which has been hypothesised to result from selection imposed by inter-population variation in Diascia floral spur length. Here, we used a pooled restriction site-associated DNA sequencing (pooled RAD-seq) approach to investigate the population genetic structure of R. longimanus and to test if phenotypic differences in FLL translate into increased genetic differentiation (i) between R. longimanus populations and (ii) between phenotypes across populations. We also inferred the effects of demographic processes on population genetic structure and tested for genetic markers underpinning local adaptation. RESULTS: Populations showed marked genetic differentiation (average F_ST = 0.165), though differentiation was not statistically associated with differences between populations in FLL. All populations exhibited very low genetic diversity and were inferred to have gone through recent bottleneck events, suggesting extremely low effective population sizes. Genetic differentiation between samples pooled by leg length (short versus long) rather than by population of origin was even higher (F_ST = 0.260) than between populations, suggesting reduced interbreeding between long and short-legged individuals. Signatures of selection were detected in 1119 (3.8%) of a total of 29,721 SNP markers, CONCLUSIONS: Populations of R. longimanus appear to be small, bottlenecked and isolated. Though we could not detect the effect of local adaptation (FLL in response to floral spurs of host plants) on population genetic differentiation, short and long legged bees appeared to be partially differentiated, suggesting incipient ecological speciation. To test this hypothesis, greater resolution through the use of individual-based whole-genome analyses is now needed to quantify the degree of reproductive isolation between long and short legged bees between and even within populations.

Keywords: Ecological adaptation; Pollinators; Pool-Seq; Population genetic structure; Population genomics; Selection; South Africa.

Fig. 1

Sampling locations of R. longimanus populations in South Africa. Population labels with an asterisk correspond to the four population pools (AP, LC, LI, LF) used for population genetic analysis in this study. For the two leg pools, we included individuals from LC, LI and LF as well as from three other populations (LA, LB, LG) to obtain two pools comprising either individuals with the longest or the shortest foreleg length (FLL), irrespective of population of origin. Sample sizes and mean relative FLL are given in brackets

Fig. 2

Population genetic structure of Rediviva longimanus according to principal component analysis (PCA). (a) PCA, performed in PCADAPT, suggested that three principal components explained most of the population genetic structure and revealed a clear separation into four population clusters. (b) Analysing more than three components did not contribute to disentangle further population genetic structure and revealed additional variance within rather than between clusters

Fig. 3

Regression of genetic differentiation of Rediviva longimanus population pools upon (a) foreleg length (FLL) and (b) geographic distance (log₁₀). Although we failed to detect a significant pattern of isolation by adaptation (IBA) or isolation by distance (IBD) for the R. longimanus populations, there was a positive trend in both

Fig. 4

Overall we identified 1119 unique outlier RAD-tag loci. Shown is the overlap between (a) the different methods for the population pools and between (b) the population pools and leg pools datasets. Diagrams were created with http://bioinformatics.psb.ugent.be/webtools/Venn