Heterogeneous models place the root of the placental mammal phylogeny

Abstract

Heterogeneity among life traits in mammals has resulted in considerable phylogenetic conflict, particularly concerning the position of the placental root. Layered upon this are gene- and lineage-specific variation in amino acid substitution rates and compositional biases. Life trait variations that may impact upon mutational rates are longevity, metabolic rate, body size, and germ line generation time. Over the past 12 years, three main conflicting hypotheses have emerged for the placement of the placental root. These hypotheses place the Atlantogenata (common ancestor of Xenarthra plus Afrotheria), the Afrotheria, or the Xenarthra as the sister group to all other placental mammals. Model adequacy is critical for accurate tree reconstruction and by failing to account for these compositional and character exchange heterogeneities across the tree and data set, previous studies have not provided a strongly supported hypothesis for the placental root. For the first time, models that accommodate both tree and data set heterogeneity have been applied to mammal data. Here, we show the impact of accurate model assignment and the importance of data sets in accommodating model parameters while maintaining the power to reject competing hypotheses. Through these sophisticated methods, we demonstrate the importance of model adequacy, data set power and provide strong support for the Atlantogenata over other competing hypotheses for the position of the placental root.

Keywords: evolutionary models; heterogeneous modeling; mammal phylogeny; phylogenetic reconstruction; placental root.

Fig. 1.

Three major rooting hypotheses for placental mammals. The three major competing hypotheses for the position of the root are depicted. (A) The Afrotheria root, (B) the Xenarthra root, and (C) the Atlantogenata root.

Fig. 2.

Fit of alternative models applied to 66TaxonSet_nuc, and posterior predictive simulations for the homogeneous model and heterogeneous model of “best-fit” for 66TaxonSet_nuc. Models are shown on x axis. The specifications of each model, that is, the number of rate matrices and composition vectors, are given inside the bar that represents that model. The y axis shows the ln L score, the higher the bar the worse the fit of the model. Inset (A) shows posterior predictive simulations for the homogeneous model (1GTR + 1C + I + 4Γ). Inset (B) shows posterior predictive simulation for the best-fit heterogeneous model (3GTR + 5C + I + 4Γ). The black bar graphs in insets (A) and (B) represent the posterior predictive simulations of these models on 66TaxonSet_nuc, and the arrow in each inset represents the χ² position in the simulation for the real data.

Fig. 3.

Mammal phylogeny reconstructed using two independent approaches. Phylogeny reconstruction carried out using CAT-GTR model on the 39TaxonSet_aa in PhlyoBayes v3.2 and on 39TaxonSet_day using the heterogeneous model 2GTR + 4C + 4Γ in P4. The support values for both methods are given at each node: the numerator is the Bayesian support value for nodes based on CAT-GTR in PhyloBayes; the denominator is the support value based on the 2GTR + 4C + 4Γ model in P4. Support values for the 2GTR + 4C + 4Γ model are shown where they are in agreement with the CAT-GTR model topology. The color scheme represents the major groups of mammals: red, Euarchontoglires; blue, Laurasiatheria; green, Afrotheria; purple, Xenarthra; gray, Marsupials (* represents compositionally heterogeneous taxa). Gallus gallus and Ornithorhynchus anatinus were both compositionally heterogeneous but were excluded in this figure to retain clarity of placental mammal branch lengths.