A bayesian approach to genome/linguistic relationships in native South Americans

Abstract

The relationship between the evolution of genes and languages has been studied for over three decades. These studies rely on the assumption that languages, as many other cultural traits, evolve in a gene-like manner, accumulating heritable diversity through time and being subjected to evolutionary mechanisms of change. In the present work we used genetic data to evaluate South American linguistic classifications. We compared discordant models of language classifications to the current Native American genome-wide variation using realistic demographic models analyzed under an Approximate Bayesian Computation (ABC) framework. Data on 381 STRs spread along the autosomes were gathered from the literature for populations representing the five main South Amerindian linguistic groups: Andean, Arawakan, Chibchan-Paezan, Macro-Jê, and Tupí. The results indicated a higher posterior probability for the classification proposed by J.H. Greenberg in 1987, although L. Campbell's 1997 classification cannot be ruled out. Based on Greenberg's classification, it was possible to date the time of Tupí-Arawakan divergence (2.8 kya), and the time of emergence of the structure between present day major language groups in South America (3.1 kya).

Figure 1. Alternative demographic models tested against the genetic variation in 381 autosomal STRs.

Parameters are explained in Table 1. Current average deme size (N_P) and gene flow (m) between populations are not shown.

Figure 2. Prior (black), posterior (red) and retained (blue) simulations distributions of time (in generations) and size (2n) of parameters of the demographic model based on Greenberg's language classification.

Figure 3. Quantile distributions (x-axis) of the known parameter values as inferred from the posterior distributions for 1,000 pseudo-observed data sets generated under Greenberg's model.