Bears in a forest of gene trees: phylogenetic inference is complicated by incomplete lineage sorting and gene flow

Abstract

Ursine bears are a mammalian subfamily that comprises six morphologically and ecologically distinct extant species. Previous phylogenetic analyses of concatenated nuclear genes could not resolve all relationships among bears, and appeared to conflict with the mitochondrial phylogeny. Evolutionary processes such as incomplete lineage sorting and introgression can cause gene tree discordance and complicate phylogenetic inferences, but are not accounted for in phylogenetic analyses of concatenated data. We generated a high-resolution data set of autosomal introns from several individuals per species and of Y-chromosomal markers. Incorporating intraspecific variability in coalescence-based phylogenetic and gene flow estimation approaches, we traced the genealogical history of individual alleles. Considerable heterogeneity among nuclear loci and discordance between nuclear and mitochondrial phylogenies were found. A species tree with divergence time estimates indicated that ursine bears diversified within less than 2 My. Consistent with a complex branching order within a clade of Asian bear species, we identified unidirectional gene flow from Asian black into sloth bears. Moreover, gene flow detected from brown into American black bears can explain the conflicting placement of the American black bear in mitochondrial and nuclear phylogenies. These results highlight that both incomplete lineage sorting and introgression are prominent evolutionary forces even on time scales up to several million years. Complex evolutionary patterns are not adequately captured by strictly bifurcating models, and can only be fully understood when analyzing multiple independently inherited loci in a coalescence framework. Phylogenetic incongruence among gene trees hence needs to be recognized as a biologically meaningful signal.

Keywords: Ursidae; coalescence; introgressive hybridization; multi-locus analyses; phylogenetic network; species tree.

Fig. 1.

Statistical parsimony networks for five autosomal intron markers and 5.9 kb of Y-chromosomal sequence in bears. Circle areas are proportional to haplotype frequencies and inferred intermediate states are shown as black dots. For some loci, spectacled bear and giant panda haplotypes were too divergent to be connected at the 95% credibility limit. Likewise, in the Y-chromosomal data set, sun bear haplotypes were connected at the 94% credibility limit. Haplotype networks for nine additional autosomal intron markers are shown in supplementary figure S1, Supplementary Material online.

Fig. 2.

(A) Cloudogram of species trees from *BEAST analysis, based on 14 autosomal introns and 5.9 kb of Y-chromosomal sequence (90,000 species trees). The consensus tree of the most frequently occurring topology in the posterior distribution is superimposed onto the cloudogram in blue. Blue dots at nodes indicate posterior support >0.96 in the maximum-clade-credibility tree. Frequency of different topologies occurring in the posterior distribution is illustrated by width and intensity of grey branches. Variation in density along the x axis portrays variation in time estimates of divergences. (B) Gene tree of 5.9-kb Y-chromosomal sequence from BEAST. Note that in a *BEAST analysis of the 14 autosomal introns alone, the same topology was obtained, with low statistical support (P < 0.95) for a clade of Asian black bears, sun bears, and sloth bears (data not shown). (C) Gene tree of mitochondrial genome data (protein-coding regions, excluding ND6) from BEAST. Black dots at nodes indicate posterior support >0.95. (D) Schematic scenarios for interspecific gene flow that could explain discordance between mitochondrial and nuclear phylogenies. Blue arrows: Nuclear gene flow, brown arrows: Introgression of mtDNA. Light blue and light brown arrows indicate gene flow identified in previous studies (Hailer et al. 2012, 2013; Miller et al. 2012; Cahill et al. 2013; Liu et al. 2014). Note that IMa2 identified additional introgression signals from Asian black into sloth bears (supplementary fig. S3B, Supplementary Material online).

Fig. 3.

Consensus network of 14 autosomal gene trees obtained from a *BEAST analysis of 14 nuclear introns. All splits found in at least two gene trees (2/14, threshold = 0.14) are shown. n, number of individuals analyzed per species.