The Asian plethodontid salamander preserves historical genetic imprints of recent northern expansion

Abstract

The Korean Peninsula, located at the southern tip of Northeast Asia, has never been covered by ice sheets and was a temperate refugium during the Pleistocene. Karsenia koreana, the sole Asian plethodontid salamander species, occurs only on the southern half of the Korean Peninsula and is thought to have found various climatic refugia. Despite its phylogenetic and biogeographic importance, no population-level genetic analysis has been performed on this species. Here we study the population genetic structure of K. koreana using mitochondrial and microsatellite loci to understand the recent historical dispersion process that shaped its current distribution. Overall, the genetic distance between populations correlated well with the spatial distance, and the genetic structure among populations showed signs of a unilateral northward expansion from a southernmost refugium population. Given the distinct genetic structure formed among the populations, the level of historical gene flow among populations appears to have been very low. As the estimated effective population size of K. koreana was also small, these results suggest that the small, restricted populations of K. koreana are extremely vulnerable to environmental changes that may require high levels of genetic diversity to cope with. Thus, special management strategies are needed to preserve these remnant populations.

Figure 1

The 11 populations from geographically separate localities of Karsenia koreana throughout the Korean Peninsula in this study; the foundational Digital Elevation Model (DEM) file was obtained from http://www.biz-gis.com. Altitude is indicated by the relative darkness, with black being higher elevations. Sites designated as numbers on the map represent the following populations: 1: DaeJeon (DJ), 2: GongJu (GJ), 3: BoEun (BE), 4: JeCheon (JC), 5: PyeongChang (PC), 6: JeongSeon (JS), 7: SamCheock (SC), 8: HapCheon (HC), 9: JinAn (JA), 10: JeongEup (JE) and 11: GwangYang (GY). For the detailed sampling information, see Table 1.

Figure 2

Haplotype network among Karsenia koreana populations estimated using concatenated sequences of cytochrome c oxidase I and cytochrome b. Different colors are assigned to each population, and the size of a circle is proportional to the haplotype frequency. Mutation steps are indicated by vertical lines, or numbers in case of more than five. Population codes follow Table 1.

Figure 3

Time-calibrated Bayesian tree reconstructed using BEAST based on the concatenated sequences of cytochrome c oxidase I and cytochrome b, given with a geological time scale chart under the time scale bar (abbreviations: PS: Pleistocene, Quat.: Quaternary). At each major node, median divergence date is represented in Ma (million years ago) and the posterior probability of the date is indicated in brackets. The insets show Bayesian skyline plots of 0–2.3 Ma range (top left) and the 0–0.1 Ma range is magnified (top right). X and Y axes represent time (Ma) and log-scale effective population size (Nfe), respectively. Population codes follow Table 1.

Figure 4

Isolation by distance plot among Karsenia koreana populations estimated based on microsatellite genotyping results. X and Y axis indicate geographic distance (km) and Slatkin's linearized F_ST (F_ST / ( 1 − F_ST )), respectively.

Figure 5

Bayesian genetic structure among Karsenia koreana populations estimated based on the microsatellite data using Structure. Since the program could not identify one optimal number of genetic clusters, four serial plots from K = 2 to 5 are presented. Population codes follow Table 1.