A web-database of mammalian morphology and a reanalysis of placental phylogeny

Abstract

Background: Recent publications concerning the interordinal phylogeny of placental mammals have converged on a common signal, consisting of four major radiations with some ambiguity regarding the placental root. The DNA data with which these relationships have been reconstructed are easily accessible from public databases; access to morphological characters is much more difficult. Here, I present a graphical web-database of morphological characters focusing on placental mammals, in tandem with a combined-data phylogenetic analysis of placental mammal phylogeny.

Results: The results reinforce the growing consensus regarding the extant placental mammal clades of Afrotheria, Xenarthra, Euarchontoglires, and Laurasiatheria. Unweighted parsimony applied to all DNA sequences and insertion-deletion (indel) characters of extant taxa alone support a placental root at murid rodents; combined with morphology this shifts to Afrotheria. Bayesian analyses of morphology, indels, and DNA support both a basal position for Afrotheria and the position of Cretaceous eutherians outside of crown Placentalia. Depending on treatment of third codon positions, the affinity of several fossils (Leptictis,Paleoparadoxia, Plesiorycteropus and Zalambdalestes) vary, highlighting the potential effect of sequence data on fossils for which such data are missing.

Conclusion: The combined dataset supports the location of the placental mammal root at Afrotheria or Xenarthra, not at Erinaceus or rodents. Even a small morphological dataset can have a marked influence on the location of the root in a combined-data analysis. Additional morphological data are desirable to better reconstruct the position of several fossil taxa; and the graphic-rich, web-based morphology data matrix presented here will make it easier to incorporate more taxa into a larger data matrix.

Figure 1

Optimal MP topologies, all data. Strict (A) and Adams (B) consensuses of 4 trees (49750 steps) resulting from combined morphology-DNA-indel dataset, all changes treated equally. Numbers indicate bootstrap support values (only reported above 50); asterisks indicate support of 100. Daggers indicate extinct taxa.

Figure 2

Optimal MP topologies, third positions removed. Strict consensus of 4 trees (27858 steps) resulting from combined morphology-DNA-indel dataset, excluding third positions from protein-coding genes. Numbers indicate bootstrap support values (only reported above 50); asterisks indicate support of 100. Daggers indicate extinct taxa.

Figure 3

Bayesian tree. Majority rule consensus of 15500 trees (1.6 million generations, sampled every 100, first 500 discarded as "burn-in") generated by MrBayes 3.1 [33]. Numbers indicate Bayesian posterior probability values; asterisks indicate support of 100. Daggers indicate extinct taxa.

Figure 4

Optimal MP topologies for Recent taxa alone. The analysis of morphology-DNA-indels (A) yields a single tree of 49588 steps with the placental root within Afrotheria. Using DNA-indels alone (B) yields two trees at 48530 steps with placental root at murid rodents. Numbers indicate bootstrap support values (only reported above 50); asterisks indicate support of 100.