Hybridization and extensive mitochondrial introgression among fire salamanders in peninsular Italy

Abstract

Discordance between mitochondrial and nuclear patterns of population genetic structure is providing key insights into the eco-evolutionary dynamics between and within species, and their assessment is highly relevant to biodiversity monitoring practices based on DNA barcoding approaches. Here, we investigate the population genetic structure of the fire salamander Salamandra salamandra in peninsular Italy. Both mitochondrial and nuclear markers clearly identified two main population groups. However, nuclear and mitochondrial zones of geographic transition between groups were located 600 km from one another. Recent population declines in central Italy partially erased the genetic imprints of past hybridization dynamics. However, the overall pattern of genetic variation, together with morphological and fossil data, suggest that a rampant mitochondrial introgression triggered the observed mitonuclear discordance, following a post-glacial secondary contact between lineages. Our results clearly show the major role played by reticulate evolution in shaping the structure of Salamandra salamandra populations and, together with similar findings in other regions of the species' range, contribute to identify the fire salamander as a particularly intriguing case to investigate the complexity of mechanisms triggering patterns of mitonuclear discordance in animals.

Figure 1

Geographic location of the 21 sampled populations of S. salamandra, and its approximate species’ distribution in Italy (light green; following). Maps and diagrams were drawn using the software Canvas 11 (ACD Systems of America, Inc.). Photo: D. Canestrelli.

Figure 2

Population genetic structure of S. salamandra in Italy. (A) mtDNA haplotype genealogy generated using HaplotypeViewer, based on the ML phylogenetic tree, and geographic distribution of the main haplotype groups. Circle sizes are proportional to haplotype frequency (see inset, lower right), whereas missing intermediate haplotypes are shown as dots. Population samples are coloured as pie diagrams, showing the geographic distribution of the main haplogroups. (B) Mean values of the DIC statistic (averaged over 10 runs) estimated for models with K ranging from 2 to 9. (C–F) Results of the Bayesian clustering analyses carried out with TESS and BAPS for values of K between 2 and 5. Bar-plots show individual admixture proportions for the genetic clusters inferred using TESS. Populations assigned to the same cluster by BAPS are marked by distinct colours on the maps. Maps and diagrams were drawn using the software Canvas 11 (ACD Systems of America, Inc.).