Molecular and fossil evidence place the origin of cichlid fishes long after Gondwanan rifting

Abstract

Cichlid fishes are a key model system in the study of adaptive radiation, speciation and evolutionary developmental biology. More than 1600 cichlid species inhabit freshwater and marginal marine environments across several southern landmasses. This distributional pattern, combined with parallels between cichlid phylogeny and sequences of Mesozoic continental rifting, has led to the widely accepted hypothesis that cichlids are an ancient group whose major biogeographic patterns arose from Gondwanan vicariance. Although the Early Cretaceous (ca 135 Ma) divergence of living cichlids demanded by the vicariance model now represents a key calibration for teleost molecular clocks, this putative split pre-dates the oldest cichlid fossils by nearly 90 Myr. Here, we provide independent palaeontological and relaxed-molecular-clock estimates for the time of cichlid origin that collectively reject the antiquity of the group required by the Gondwanan vicariance scenario. The distribution of cichlid fossil horizons, the age of stratigraphically consistent outgroup lineages to cichlids and relaxed-clock analysis of a DNA sequence dataset consisting of 10 nuclear genes all deliver overlapping estimates for crown cichlid origin centred on the Palaeocene (ca 65-57 Ma), substantially post-dating the tectonic fragmentation of Gondwana. Our results provide a revised macroevolutionary time scale for cichlids, imply a role for dispersal in generating the observed geographical distribution of this important model clade and add to a growing debate that questions the dominance of the vicariance paradigm of historical biogeography.

Keywords: biogeography; dispersal; fossil record; molecular clock; vicariance.

Figure 1.

Congruent molecular and palaeontological time scales place the origin of cichlid fishes in the Late Cretaceous–Eocene interval, substantially post-dating Gondwanan rifting. (a) Molecular phylogeny for Cichlidae calibrated using fossils belonging to non-cichlid groups (full phylogeny provided in electronic supplementary material, figures S1 and S2). (b) Bayesian point estimates and 95% CIs for the timing of cichlid origin based on the distribution of cichlid fossils and the availability of freshwater sedimentary deposits of Triassic–Recent age on Gondwanan landmasses that bear articulated fish remains. The top estimate is derived from the record of landmasses inhabited by extant cichlids, and the bottom estimate is derived from the record of all Gondwanan landmasses. The density of all Gondwanan horizons bearing articulated freshwater fish fossils is indicated by the histogram at the bottom of the figure (densities including disarticulated material are given in electronic supplementary material). Grey bars indicate total horizon density. Pink bars indicate the density of the subset of fossil fish horizons that bear cichlids. (c) Bayesian point estimates and 95% CIs for the timing of cichlid origin based on successive fossil outgroups to the clade. The two estimates reflect competing hypotheses for the earliest fossil examples of some outgroups. The top estimate is based on the oldest proposed outgroup ages and the bottom estimate is based on the youngest proposed outgroup ages. Cichlid illustrations, from top to bottom: Etroplus, Crenicichla, Astronotus, Hemichromis, Steatocranus, Altolamprologus and Tropheus. Continental arrangements based on palaeogeographic reconstructions by R. Blakey, originally presented in [7].