Strong population genetic structuring in an annual fish, Nothobranchius furzeri, suggests multiple savannah refugia in southern Mozambique

Background: Intraspecific genetic variation of African fauna has been significantly affected by pronounced climatic fluctuations in Plio-Pleistocene, but, with the exception of large mammals, very limited empirical data on diversity of natural populations are available for savanna-dwelling animals. Nothobranchius furzeri is an annual fish from south-eastern Africa, inhabiting discrete temporary savannah pools outside main river alluvia. Their dispersal is limited and population processes affecting its genetic structure are likely a combination of those affecting terrestrial and aquatic taxa. N. furzeri is a model taxon in ageing research and several populations of known geographical origin are used in laboratory studies. Here, we analysed the genetic structure, diversity, historical demography and temporal patterns of divergence in natural populations of N. furzeri across its entire distribution range. Results: Genetic structure and historical demography of N. furzeri were analysed using a combination of mitochondrial (partial cytochrome b sequences, 687 bp) and nuclear (13 microsatellites) markers in 693 fish from 36 populations. Genetic markers consistently demonstrated strong population structuring and suggested two main genetic groups associated with river basins. The split was dated to the Pliocene (>2 Mya). The northern group inhabits savannah pools across the basin of the intermittent river Chefu in south-western Mozambique and eastern Zimbabwe. The southern group (from southernmost Mozambique) is subdivided, with the River Limpopo forming a barrier (maximum divergence time 1 Mya). A strong habitat fragmentation (isolated temporary pools) is reflected in significant genetic structuring even between adjacent pools, with a major influence of genetic drift and significant isolation-by-distance. Analysis of historical demography revealed that the expansion of both groups is ongoing, supported by frequent founder effects in marginal parts of the range and evidence of secondary contact between Chefu and Limpopo populations. Conclusions: We demonstrated: (1) ancient (pre-Pleistocene) divergence between the two main N. furzeri lineages, their recent secondary contact and lack of reproductive isolation; (2) important genetic structuring attributed to the fragmented nature of their environment and isolation-by-distance, suggesting that dispersal is limited, occurs over short distances and is not directly associated with river routes; (3) an apparent role of the River Limpopo as a barrier to dispersal and gene flow.