UFBoot2: Improving the Ultrafast Bootstrap Approximation

Abstract

The standard bootstrap (SBS), despite being computationally intensive, is widely used in maximum likelihood phylogenetic analyses. We recently proposed the ultrafast bootstrap approximation (UFBoot) to reduce computing time while achieving more unbiased branch supports than SBS under mild model violations. UFBoot has been steadily adopted as an efficient alternative to SBS and other bootstrap approaches. Here, we present UFBoot2, which substantially accelerates UFBoot and reduces the risk of overestimating branch supports due to polytomies or severe model violations. Additionally, UFBoot2 provides suitable bootstrap resampling strategies for phylogenomic data. UFBoot2 is 778 times (median) faster than SBS and 8.4 times (median) faster than RAxML rapid bootstrap on tested data sets. UFBoot2 is implemented in the IQ-TREE software package version 1.6 and freely available at http://www.iqtree.org.

Keywords: maximum likelihood; model violation; phylogenetic inference; polytomies; ultrafast bootstrap.

Fig. 1.

Accuracy of the standard bootstrap (SBS), RAxML rapid bootstrap (RBS), ultrafast bootstrap (UFBoot2) and UFBoot2 with correction (UFBoot2 + NNI) for (A) correctly specified models and (B) severely misspecified models. The y-axis depicts the percentage of all branches with support value $x$ (across all reconstructed trees) that occur in the true tree. Curves above the diagonal indicate underestimation of branch supports whereas curves below the diagonal indicate overestimation. For each point $(x,y)$ in the curve representing the accuracy of bootstrap method M, x is an inferred bootstrap value by method M whereas y measures the probability of branches assigned by M with support value x to be true branches, that is, occurring on the true tree. Specifically, let $X^{+}$ ($X^{-}$) be the set of branches with support value $x$ in all trees and present (absent) in the true tree. The $y$ value is computed as the ratio between ${|X}^{+}|$ and $|X$|, where $\left|X\right|={|X}^{+}|+{|X}^{-}|$.

Fig. 2.

Maximum-likelihood tree inferred under the edge-unlinked partition model. Numbers attached to the branches show the UFBoot2 bootstrap supports using MSA-site, gene, and gene-site resampling strategies (omitted when all three supports are 100%).