ModelRevelator: Fast phylogenetic model estimation via deep learning

Abstract

Selecting the best model of sequence evolution for a multiple sequence alignment (MSA) constitutes the first step of phylogenetic tree reconstruction. Common approaches for inferring nucleotide models typically apply maximum likelihood (ML) methods, with discrimination between models determined by one of several information criteria. This requires tree reconstruction and optimisation which can be computationally expensive. We demonstrate that neural networks can be used to perform model selection, without the need to reconstruct trees, optimise parameters, or calculate likelihoods. We introduce ModelRevelator, a model selection tool underpinned by two deep neural networks. The first neural network, NNmodelfind, recommends one of six commonly used models of sequence evolution, ranging in complexity from JC to GTR. The second, NNalphafind, recommends whether or not a Γ--distributed rate heterogeneous model should be incorporated, and if so, provides an estimate of the shape parameter, ɑ. Users can simply input an MSA into ModelRevelator, and swiftly receive output recommending the evolutionary model, inclusive of the presence or absence of rate heterogeneity, and an estimate of ɑ. We show that ModelRevelator performs comparably with likelihood-based methods over a wide range of parameter settings, with significant potential savings in computational effort. Further, we show that this performance is not restricted to the alignments on which the networks were trained, but is maintained even on unseen empirical data. ModelRevelator will be made freely available in the forthcoming version of IQ-Tree (http://www.iqtree.org), and we expect it will provide a valuable alternative for phylogeneticists, especially where traditional methods of model selection are computationally prohibitive.

Machine learning can be as good as maximum likelihood when reconstructing phylogenetic trees and determining the best evolutionary model on four taxon alignments

“…Burgstaller-Muehlbacher et al (2021) analysed images of alignments of 8, 16, 64, 128, 256 and 1024 taxa with CNNs to determine the best model of sequence evolution and to estimate the shape parameter of the gamma distribution. They compared the model prediction accuracies with those of ModelFinder with BIC and found comparable accuracies between the methods.…”

Applications of Machine Learning in Phylogenetics

“…Another major consideration is how to encode input data for neural networks. Most commonly, encoded alignments (Suvorov & Schrider, 2022;Suvorov et al, 2020;Zou et al, 2020), or summary statistics (Abadi et al, 2020;Burgstaller-Muehlbacher et al, 2023) have been used as input. When using encoded alignments, a primary challenge is scalability to longer alignments or more taxa.…”

“…A later model, ModelRevelator (Burgstaller-Muehlbacher et al, 2023) aims to infer the correct generating model of nucleotide substitution using two neural networks. The first network, NNmodelfinder, takes as input a set of statistics calculated from pairwise alignments and predicts the best substitution model from a set of six possible models.…”

AliSim-HPC: parallel sequence simulator for phylogenetics

“…However, many applications require simulations of a vast number of large MSAs. For example, training new machine learning applications for phylogenetics (Suvorov and Schrider, 2022; Burgstaller-Muehlbacher et al ., 2021; Abadi et al ., 2020; Suvorov et al ., 2020) requires millions of simulated MSAs. Due to its sequential implementation, AliSim becomes very slow, taking several days or weeks to simulate millions of alignments.…”