BoskR - Testing Adequacy of Diversification Models Using Tree Shape

Abstract

The study of diversification largely relies on model-based approaches, estimating rates of speciation and extinction from phylogenetic trees. While a plethora of different models exist - all with different features, strengths and weaknesses - there is increasing concern about the reliability of the inference we gain from them. Apart from simply finding the model with the best fit for the data, we should find ways to assess a models suitability to describe the data in an absolute sense. The R package BoskR implements a simple way of judging a models adequacy for a given phylogeny using metrics for tree shape, assuming that a model is inadequate for a phylogeny if it produces trees that are consistently dissimilar in shape from the tree that should be analyzed. Tree shape is assessed via metrics derived from the trees modified graph Laplacian spectrum, as provided by RPANDA. We exemplify the use of the method using simulated and empirical example phylogenies. BoskR was mostly able to correctly distinguish trees simulated under clearly different models and revealed that not all models are adequate for the empirical example trees. We believe the metrics of tree shape to be an intuitive and relevant means of assessing diversification model adequacy. Furthermore, by implementing the approach in an openly available R package, we enable and encourage researchers to adopt adequacy testing into their workflow.