Phylogenomic datasets provide both precision and accuracy in estimating the timescale of placental mammal phylogeny

Abstract

The fossil record suggests a rapid radiation of placental mammals following the Cretaceous-Paleogene (K-Pg) mass extinction 65 million years ago (Ma); nevertheless, molecular time estimates, while highly variable, are generally much older. Early molecular studies suffer from inadequate dating methods, reliance on the molecular clock, and simplistic and over-confident interpretations of the fossil record. More recent studies have used Bayesian dating methods that circumvent those issues, but the use of limited data has led to large estimation uncertainties, precluding a decisive conclusion on the timing of mammalian diversifications. Here we use a powerful Bayesian method to analyse 36 nuclear genomes and 274 mitochondrial genomes (20.6 million base pairs), combined with robust but flexible fossil calibrations. Our posterior time estimates suggest that marsupials diverged from eutherians 168-178 Ma, and crown Marsupialia diverged 64-84 Ma. Placentalia diverged 88-90 Ma, and present-day placental orders (except Primates and Xenarthra) originated in a ∼20 Myr window (45-65 Ma) after the K-Pg extinction. Therefore we reject a pre K-Pg model of placental ordinal diversification. We suggest other infamous instances of mismatch between molecular and palaeontological divergence time estimates will be resolved with this same approach.

Figure 1.

The tree of 36 mammal species showing fossil calibrations. Calibration bounds are soft; that is, the probability that the true divergence time is outside the bounds is small but non-zero. Internal nodes are numbered from 37 to 71. The tree topology follows the literature [26,27]. The ‘dagger’ symbol shows a species which is extinct.

Figure 2.

The timetree of mammals. (a) Blue horizontal bars represent the posterior 95% CI for the node ages. Red horizontal bars represent fossil calibrations: U for upper (maximum), L for lower (minimum) and B for both. The number of species analysed is presented within brackets: red for nuclear and black for mitochondrial genomes. The two mammal orders that diversified before the K–Pg event are shown in orange. All orders within Afrotheria and Marsupialia diversified after the K–Pg event. The tree topology follows [26,27]. (b) The three possible topologies concerning the divergence of early Placentalia.

Figure 3.

Calibrations, prior and posterior densities. The marginal posterior density of divergence times estimated from the 14 346 nuclear genes is shown in black. The marginal prior density of times is shown in purple. The fossil calibrations are shown as dashed lines in red (minimum bound), green (maximum bound) and blue (joint). Nodes with no calibrations (41, 42, 45, 46, 48, 50, 52, 56 and 66) have their marginal priors generated using the birth–death process conditioned on the ages of the calibration nodes [25] (see the electronic supplementary material, text). Note how the marginal prior densities may differ from the corresponding fossil calibration densities. All densities are scaled so that their maximum is one. Time scale is in million years ago. Clade ages are the ages of the corresponding crown groups.

Figure 4.

Infinite-sites plot. The 95% CI width is plotted against the mean of the divergence time. (a) Prior calculated from a MCMC without sequence data on the 36-species tree. (b) Posterior calculated using 14 632 nuclear genes in 20 partitions, 36 species. (c) Posterior from combined analysis of 14 632 nuclear genes in 20 partitions and 12 mitochondrial genes for 274 species in one partition. In (c), black dots indicate nodes shared with the 36-species tree, and grey dots indicate nodes that are exclusive to the 274-species tree. Only black dots are used to fit the line and calculate R.