Dental evolutionary rates and its implications for the Neanderthal-modern human divergence

Abstract

The origin of Neanderthal and modern human lineages is a matter of intense debate. DNA analyses have generally indicated that both lineages diverged during the middle period of the Middle Pleistocene, an inferred time that has strongly influenced interpretations of the hominin fossil record. This divergence time, however, is not compatible with the anatomical and genetic Neanderthal affinities observed in Middle Pleistocene hominins from Sima de los Huesos (Spain), which are dated to 430 thousand years (ka) ago. Drawing on quantitative analyses of dental evolutionary rates and Bayesian analyses of hominin phylogenetic relationships, I show that any divergence time between Neanderthals and modern humans younger than 800 ka ago would have entailed unexpectedly rapid dental evolution in early Neanderthals from Sima de los Huesos. These results support a pre-800 ka last common ancestor for Neanderthals and modern humans unless hitherto unexplained mechanisms sped up dental evolution in early Neanderthals.

Fig. 1. Phylogenetic scenarios and SH dental morphology.

(A) Hominin phylogeny used in the analysis of evolutionary rates (phylogeny-1). The SH branch is represented in teal, and the LCA branch in orange, which are the colors used to represent the evolutionary rates on these two branches in Figs. 4 and 5 and fig. S5. Gray lines represent the different divergence times that have been evaluated. (B) Transformation of the Neanderthal-Denisovan-SH lineage into the SH lineage. (C) Densitree showing a randomly selected sample of 100 phylogenies [of the total sample of 60,000 phylogenies generated by Dembo and colleagues’ Bayesian analysis of hominin phylogenetic relationships (20)]. Dembo’s original trees have been pruned to preserve only the species for which dental data are available. The length of the Neanderthal branch has been shortened to reflect the age of the SH branch. (D) Upper and lower postcanine dentition of one representative SH individual (upper dentition is represented on the left). Photo credit: A. Muela, photographs taken at Institute of Health Carlos III.

Fig. 2. Branch-specific evolutionary rates obtained through the analysis of phylogeny-1.

(A) Evolutionary rates obtained when setting the SH–modern human divergence time at 0.5 Ma ago. (B) Rates obtained when setting this divergence at 0.9 Ma ago, which is the scenario associated with the minimum SD of all the rates across the tree. (C) Rates obtained when setting divergence at 1.4 Ma ago. SH–modern human divergence times older than 1.4 Ma ago result in even higher rates for the branch antedating the SH–modern human separation, referred to in the following figures as the LCA branch. Evolutionary rates are provided above each branch (gray for rates that remain roughly constant in all scenarios, and black for rates associated with the Neanderthal–modern human clade, which are affected by changes in the SH–modern human divergence time).

Fig. 3. Relationship between the evolutionary rate at the SH branch and at the LCA branch.

Relationship observed when analyzing the first phylogenetic scenario (phylogeny-1). Evolutionary rates at both branches show an inverse and nonlinear relationship such that very high rates at the SH branch are associated with very low rates at the LCA branch and vice versa. This effect can be visualized in Fig. 2, which shows how these rates change depending on the assumed SH–modern human divergence time.

Fig. 4. Variation of evolutionary rates obtained through the analysis of 100 trees.

(A) Densitree showing the sample of 100 randomly selected trees used in the calculations. (B) Boxplot comparing the maximum evolutionary rate (gray), the LCA rate (orange), and the SH rate (teal) in the 100 phylogenies. (C) Evolutionary rates obtained in the analysis of each of the 100 phylogenies showing the maximum rate across the tree (gray), the LCA rate (orange), and the SH rate (teal). Phylogenies in (C) are sorted according to their maximum evolutionary rate. The plot shows that the LCA rate is the maximum rate in a majority of phylogenies (59 of 100), whereas the SH rate is the maximum rate only in three phylogenies. In all other cases, the maximum rate is found in other branches (in most cases, in the P. boisei branch).

Fig. 5. Most likely Neanderthal–modern human divergence time based on the analysis of phylogeny-1.

(A) Comparison of observed SDs of all the rates across the hominin phylogeny (red points) with the distributions of SDs obtained when simulating evolution over the same tree at a constant rate. (B) Comparison of evolutionary rates at the SH branch (teal), LCA branch (orange), and all the other branches (gray) obtained for the different SH–modern human divergence times. (C) Comparison of the SH rate (teal line) with the 95% interval of rates obtained for this branch through the analysis of 100 phylogenies (gray box). (D) Comparison of the LCA rate (orange line) with the 95% interval obtained for that branch through the analysis of 100 phylogenies (gray box). Black dashed lines bracket the most likely divergence times according to each analysis. Red dashed lines indicate the minimum and maximum values obtained through all the analyses and bracket the most likely divergence time when all results are considered together. Equivalent results based on the analysis of phylogeny-2 are provided in fig. S5.