Termite dispersal is influenced by their diet

Abstract

Termites feed on vegetal matter at various stages of decomposition. Lineages of wood- and soil-feeding termites are distributed across terrestrial ecosystems located between 45°N and 45°S of latitude, a distribution they acquired through many transoceanic dispersal events. While wood-feeding termites often live in the wood on which they feed and are efficient at dispersing across oceans by rafting, soil-feeders are believed to be poor dispersers. Therefore, their distribution across multiple continents requires an explanation. Here, we reconstructed the historical biogeography and the ancestral diet of termites using mitochondrial genomes and δ¹³C and δ¹⁵N stable isotope measurements obtained from 324 termite samples collected in five biogeographic realms. Our biogeographic models showed that wood-feeders are better at dispersing across oceans than soil-feeders, further corroborated by the presence of wood-feeders on remote islands devoid of soil-feeders. However, our ancestral range reconstructions identified 33 dispersal events among biogeographic realms, 18 of which were performed by soil-feeders. Therefore, despite their lower dispersal ability, soil-feeders performed several transoceanic dispersals that shaped the distribution of modern termites.

Keywords: Isoptera; biogeography; ecology; feeding group; mitogenomes; stable isotopes.

Figure 1.

Macroevolutionary dietary shifts in the Termitidae were identified from centred and scaled δ¹⁵N values. (a) Location of the eight adaptive shifts (with posterior probability > 0.30) on the phylogeny of Termitidae (see electronic supplementary material, figure S7 for the location of all shifts). The shifts are indicated by circles, whose size reflects the posterior probability that a regime shift of θ occurred on that branch. Branch colours reflect convergent regimes in the adaptive optimum θ. (b–f) Phenograms of δ¹⁵N values with the posterior density of optima (curve in red) for (b) all lineages and for (c–f) the main dietary shifts. Shifts mostly reflect the interplay between the main termitid lineages with their diet.

Figure 2.

Biogeographic dispersals and diet of the Termitidae. Bayesian phylogenetic chronogram inferred from full mitochondrial genomes, without the third codon positions. Time scale is in millions of years, and node bars represent 95% credibility estimates of node time. Clades comprising species from a single biogeographic realm were collapsed (the full reconstruction is available in the electronic supplementary material, figure S3). Five biogeographic realms were recognized in this study (modified from [39]): circle colours indicate the biogeographic origin (full when the scaled likelihood of the most likely ancestral realm was above 95%, emptied otherwise), while text colours indicate the distribution of extant species. Dispersal events are indicated by stars, and their colours reflect the inferred diet of the dispersing termites (in brown, wood-feeders; in black, soil-feeders; in purple, fungus-growing termites which probably dispersed via a land bridge). Red stars indicate conflicts between the diet reconstruction methods (figure 3). The four major adaptive shifts identified by bayou (figure 1) are indicated with arrows. The diet of included extant species is indicated along the phylogeny (see electronic supplementary material, figure S3 for details).

Figure 3.

Ancestral diets were inferred at dispersal events between biogeographic realms. Smoothed density estimates of wood- and soil-feeders in extant termite species (left), and inferred diet in dispersing ancestors (right; n = 33 identified events). Ancestral reconstructions were performed from centred and scaled δ¹⁵N values (n = 33). Dashed lines represent the Bayesian standard intervals of wood-feeders (in brown; feeding on wood, microepiphytes, litter or grass) and soil-feeders (in black; humus, nest or soil) determined with SIBER and SIAR (purple stars indicate fungus-growing termites). Red stars indicate conflicts between reconstruction methods (continuous isotope data or discrete categories; conflict when the scaled likelihood for the most likely state was below 95% within the corresponding Bayesian standard intervals). Dispersal events are numbered, and empty circles indicate that the scaled likelihood of the most likely realm was below 95% (figure 2 for details).