Birth–death (BD) models are widely used in combination with species phylogenies to study past diversification dynamics. Current inference approaches typically rely on likelihood-based methods. These methods are not generalizable, as a new likelihood formula must be established each time a new model is proposed; for some models, such a formula is not even tractable. Deep learning can bring solutions in such situations, as deep neural networks can be trained to learn the relation between simulations and parameter values as a regression problem. In this paper, we adapt a recently developed deep learning method from pathogen phylodynamics to the case of diversification inference, and we extend its applicability to the case of the inference of state-dependent diversification models from phylogenies associated with trait data. We demonstrate the accuracy and time efficiency of the approach for the time-constant homogeneous BD model and the Binary-State Speciation and Extinction model. Finally, we illustrate the use of the proposed inference machinery by reanalyzing a phylogeny of primates and their associated ecological role as seed dispersers. Deep learning inference provides at least the same accuracy as likelihood-based inference while being faster by several orders of magnitude, offering a promising new inference approach for the deployment of future models in the field.
A bstract: To infer the processes that gave rise to past speciation and extinction rates across taxa, space and time, we often formulate hypotheses in the form of stochastic diversification models and estimate their parameters from extant phylogenies using Maximum Likelihood or Bayesian inference. Unfortunately, however, likelihoods can easily become intractable, limiting our ability to consider more complicated diversification processes. Recently, it has been proposed that deep learning (DL) could be used in this case as a likelihood-free inference technique. Here, we explore this idea in more detail, with a particular focus on understanding the ideal network architecture and data representation for using DL in phylogenetic inference. We evaluate the performance of different neural network architectures (DNN, CNN, RNN, GNN) and phylogeny representations (summary statistics, Lineage Through Time or LTT, phylogeny encoding and phylogeny graph) for inferring rates of the Constant Rate Birth-Death (CRBD) and the Binary State Speciation and Extinction (BISSE) models. We find that deep learning methods can reach similar or even higher accuracy than Maximum Likelihood Estimation, provided that network architectures and phylogeny representations are appropriately tuned to the respective model. For example, for the CRBD model we find that CNNs and RNNs fed with LTTs outperform other combinations of network architecture and phylogeny representation, presumably because the LTT is a sufficient and therefore less redundant statistic for homogenous BD models. For the more complex BiSSE model, however, it was necessary to feed the network with both topology and tip states information to reach acceptable performance. Overall, our results suggest that deep learning provides a promising alternative for phylogenetic inference, but that data representation and architecture have strong effects on the inferential performance.
Understanding how organisms adapt to environmental changes is a major question in evolution and ecology. In particular, the role of ancestral variation in rapid adaptation remains unclear because its trace on genetic variation, known as soft selective sweep, is often hardly recognizable from genome-wide selection scans. Here, we investigate the evolution of chemosensory genes in Drosophila yakuba mayottensis, a specialist subspecies on toxic noni (Morinda citrifolia) fruits on the island of Mayotte. We combine population genomics analyses and behavioral assays to evaluate the level of divergence in chemosensory genes and perception of noni chemicals between specialist and generalist subspecies of D. yakuba. We identify a signal of soft selective sweep on a handful of genes, with the most diverging ones involving a cluster of gustatory receptors expressed in bitter-sensing neurons. Our results highlight the potential role of ancestral genetic variation in promoting host plant specialization in herbivorous insects and identify a number of candidate genes underlying behavioral adaptation.
Birth-death models are widely used in combination with species phylogenies to study past diversification dynamics. Current inference approaches typically rely on likelihood-based methods. These methods are not generalizable, as a new likelihood formula must be established each time a new model is proposed; for some models such formula is not even tractable. Deep learning can bring solutions in such situations, as deep neural networks can be trained to learn the relation between simulations and parameter values as a regression problem. In this paper, we adapt a recently developed deep learning method from pathogen phylodynamics to the case of diversification inference, and we extend its applicability to the case of the inference of state-dependent diversification models from phylogenies associated with trait data. We demonstrate the accuracy and time efficiency of the approach for the time constant homogeneous birth-death model and the Binary-State Speciation and Extinction model. Finally, we illustrate the use of the proposed inference machinery by reanalyzing a phylogeny of primates and their associated ecological role as seed dispersers. Deep learning inference provides at least the same accuracy as likelihood-based inference while being faster by several orders of magnitude, offering a promising new inference approach for deployment of future models in the field.
A common approach to infer the processes that gave rise to past speciation and extinction rates across taxa, space and time is to formulate hypotheses in the form of probabilistic diversification models and estimate their parameters from extant phylogenies using Maximum Likelihood or Bayesian inference. A drawback of this approach is that likelihoods can easily become computationally intractable, limiting our ability to extend current diversification models with new hypothesized mechanisms. Neural networks have been proposed as a likelihood-free alternative for parameter inference of stochastic models, but so far there is little experience in using this method for diversification models, and the quality of the results is likely to depend on finding the right network architecture and data representation. As phylogenies are essentially graphs, graph neural networks (GNNs) appear to be the most natural architecture but previous results on their performance are conflicting, with some studies reporting poor accuracy of GNNs in practice. Here, we show that this underperformance was likely caused by optimization issues and inappropriate pooling operations that flatten the information along the phylogeny and make it harder to extract relevant information about the diversification parameters. When equipped with PhyloPool, a new time-informed pooling procedure, GNNs show similar or better performance compared to all other architectures and data representations (including Maximum Likelihood Estimation) that we tested for two common diversification models, the Constant Rate Birth-Death and the Binary State Speciation and Extinction. We conclude that GNNs could serve as a generic tool for estimating diversification parameters of complex diversification models with intractable likelihoods.