Mitochondrial phylogenomics of modern and ancient equids

Abstract

The genus Equus is richly represented in the fossil record, yet our understanding of taxonomic relationships within this genus remains limited. To estimate the phylogenetic relationships among modern horses, zebras, asses and donkeys, we generated the first data set including complete mitochondrial sequences from all seven extant lineages within the genus Equus. Bayesian and Maximum Likelihood phylogenetic inference confirms that zebras are monophyletic within the genus, and the Plains and Grevy's zebras form a well-supported monophyletic group. Using ancient DNA techniques, we further characterize the complete mitochondrial genomes of three extinct equid lineages (the New World stilt-legged horses, NWSLH; the subgenus Sussemionus; and the Quagga, Equus quagga quagga). Comparisons with extant taxa confirm the NWSLH as being part of the caballines, and the Quagga and Plains zebras as being conspecific. However, the evolutionary relationships among the non-caballine lineages, including the now-extinct subgenus Sussemionus, remain unresolved, most likely due to extremely rapid radiation within this group. The closest living outgroups (rhinos and tapirs) were found to be too phylogenetically distant to calibrate reliable molecular clocks. Additional mitochondrial genome sequence data, including radiocarbon dated ancient equids, will be required before revisiting the exact timing of the lineage radiation leading up to modern equids, which for now were found to have possibly shared a common ancestor as far as up to 4 Million years ago (Mya).

Figure 1. Phylogenetic RAxML trees (GTR+G+I) with 500 bootstraps and MrBayes (GTR+G+I) 50M generations on the full data set.

Posterior probabilities are given in proportions and bootstrap support as a percentage on each branch of interest. * Branch is supported by maximum posterior probability and bootstrap (1/100). A: Including outgroups and based on 5 partitions. B: Excluding outgroups and based on 4 partitions.

Figure 2. Node ages as estimated from BEAST analyses given in years and with 95% HPD.

Shown is the averaged results from the three analyses excluding outgroups (Table 2).