Reconstructing the demographic history of divergence between European river and brook lampreys using approximate Bayesian computations

Abstract

Inferring the history of isolation and gene flow during species divergence is a central question in evolutionary biology. The European river lamprey (Lampetra fluviatilis) and brook lamprey (L. planeri) show a low reproductive isolation but have highly distinct life histories, the former being parasitic-anadromous and the latter non-parasitic and freshwater resident. Here we used microsatellite data from six replicated population pairs to reconstruct their history of divergence using an approximate Bayesian computation framework combined with a random forest model. In most population pairs, scenarios of divergence with recent isolation were outcompeted by scenarios proposing ongoing gene flow, namely the Secondary Contact (SC) and Isolation with Migration (IM) models. The estimation of demographic parameters under the SC model indicated a time of secondary contact close to the time of speciation, explaining why SC and IM models could not be discriminated. In case of an ancient secondary contact, the historical signal of divergence is lost and neutral markers converge to the same equilibrium as under the less parameterized model allowing ongoing gene flow. Our results imply that models of secondary contacts should be systematically compared to models of divergence with gene flow; given the difficulty to discriminate among these models, we suggest that genome-wide data are needed to adequately reconstruct divergence history.

Keywords: Approximate Bayesian computation; Divergence history; Gene flow; Lampetra fluviatilis; Lampetra planeri; Random forest; Speciation.

Figure 1. Map of sampling sites across the channel area.

River names match those given in Table 2 and F_st values are given for each population pair.

Figure 2. Different scenario of divergence between L. planeri and L. fluviatilis.

Five models with different parameters are tested and compared. Two null models: stict Isolation (SI) and Panmixia (PAN). Three models of migration: isolation with constant migration (IM), ancient migration (AM) and secondary contact (SC). The following parameters are shared by all models: τ_div : number of generations since divergence time. θ_A, θ_Lf, θ_Lp: effective population size of the ancestral population, of L. fluviatilis and L. planeri respectively. τ_isol is the number of generations since the two ecotypes have stopped exchanging genes. τ_sc is the number of generations since the two ecotypes have entered into a secondary contact after a period of isolation. M₁₂ and M₂₁ represent the number of migrants expressed in 4.Nm units per generation with m the proportion of population made of migrants from the other populations.

Figure 3. Curves of out-of-bag errors rates and estimation of variable importance.

Data based on one random forest, each composed of 1,000 trees obtained from a trained set of 50,000 simulated predictor variables (summary statistics). The response variable is the demographic model. Example taken from the Aa river. Estimation for the remaining rivers yielded similar results and are presented in Table S2 and Fig. S1.