The perfect storm: Gene tree estimation error, incomplete lineage sorting, and ancient gene flow explain the most recalcitrant ancient angiosperm clade, Malpighiales

The genomic revolution offers renewed hope of resolving rapid radiations in the Tree of Life. The development of the multispecies coalescent (MSC) model and improved gene tree estimation methods can better accommodate gene tree heterogeneity caused by incomplete lineage sorting (ILS) and gene tree estimation error stemming from the short internal branches. However, the relative influence of these factors in species tree inference is not well understood. Using anchored hybrid enrichment, we generated a data set including 423 single-copy loci from 64 taxa representing 39 families to infer the species tree of the flowering plant order Malpighiales. This order includes nine of the top ten most unstable nodes in angiosperms, which have been hypothesized to arise from the rapid radiation during the Cretaceous. Here, we show that coalescent-based methods do not resolve the backbone of Malpighiales and concatenation methods yield inconsistent estimations, providing evidence that gene tree heterogeneity is high in this clade. Despite high levels of ILS and gene tree estimation error, our simulations demonstrate that these two factors alone are insufficient to explain the lack of resolution in this order. To explore this further, we examined triplet frequencies among empirical gene trees and discovered some of them deviated significantly from those attributed to ILS and estimation error, suggesting gene flow as an additional and previously unappreciated phenomenon promoting gene tree variation in Malpighiales. Finally, we applied a novel method to quantify the relative contribution of these three primary sources of gene tree heterogeneity and demonstrated that ILS, gene tree estimation error, and gene flow contributed to 15%, 52%, and 32% of the variation, respectively. Together, our results suggest that a perfect storm of factors likely influence this lack of resolution, and further indicate that recalcitrant phylogenetic relationships like the backbone of Malpighiales may be better represented as phylogenetic networks. Thus, reducing such groups solely to existing models that adhere strictly to bifurcating trees greatly oversimplifies reality, and obscures our ability to more clearly discern the process of evolution.基因组学革命为解决生命之树中的快速辐射演化难题带来了新的希望。多物种溯祖（multispecies coalescent, MSC）模型的发展与改良的基因树推断方法，能够更好地适配由不完全谱系分选（incomplete lineage sorting, ILS）以及短内分支引发的基因树推断误差所导致的基因树异质性。然而，目前学界对这些因素在物种树推断中的相对影响仍缺乏充分了解。本研究采用锚定杂交富集（anchored hybrid enrichment）技术，生成了包含423个单拷贝基因座的数据集，该数据集涵盖了隶属于39个科的64个类群，用以推断被子植物金虎尾目（Malpighiales）的物种树。该类群包含被子植物中10个最不稳定节点中的9个，这些节点被认为起源于白垩纪时期的快速辐射演化事件。本研究结果显示，基于溯祖的方法无法解析金虎尾目的主干系统发育关系，而串联法（concatenation methods）得到的推断结果并不一致，这表明该演化支（clade）内存在较高水平的基因树异质性。尽管存在高水平的不完全谱系分选与基因树推断误差，我们的模拟实验表明，仅这两种因素不足以解释该类群系统发育关系难以解析的现象。为进一步探究这一问题，我们对实测基因树的三联体频率（triplet frequencies）进行了分析，发现其中部分频率与仅由不完全谱系分选和推断误差导致的理论频率存在显著偏差，这提示基因流（gene flow）是另一种此前未被重视的、可导致金虎尾目基因树变异的现象。最后，我们应用一种全新方法量化了这三种主要基因树异质性来源的相对贡献比例，结果显示不完全谱系分选、基因树推断误差与基因流分别解释了15%、52%与32%的基因树变异。综合来看，我们的研究结果表明，多重因素的共同作用很可能导致了该类群系统发育关系的难解性，同时进一步表明，像金虎尾目主干这类难以解析的系统发育关系或许更适合用系统发育网络（phylogenetic networks）来表征。因此，若仅将这类类群套用严格遵循二歧分叉树的现有模型，会极大地简化真实的演化过程，从而阻碍我们更清晰地认识演化进程。