Deep learning from phylogenies to uncover the epidemiological dynamics of outbreaks

Voznica, Jakub; Zhukova, Anna; Bošková, Veronika; Saulnier, Emma; Lemoine, Frédéric; Moslonka‐Lefebvre, Mathieu; Gascuel, Olivier

doi:10.1038/s41467-022-31511-0

Cited by 47 publications

(66 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rammer & Seidl, 2019), or by emulating them (Wang et al, 2019). Moreover, ML can also be used to predict the parameters of complex stochastic models (Roy et al, 2022;Voznica et al, 2022), and thus act as a likelihood-free calibration method, similar to approximate Bayesian computation (Hartig et al, 2011).…”

Section: New Applications For ML In Eandementioning

confidence: 99%

Machine learning and deep learning—A review for ecologists

2023

View full text Add to dashboard Cite

The popularity of machine learning (ML), deep learning (DL) and artificial intelligence (AI) has risen sharply in recent years. Despite this spike in popularity, the inner workings of ML and DL algorithms are often perceived as opaque, and their relationship to classical data analysis tools remains debated. Although it is often assumed that ML and DL excel primarily at making predictions, ML and DL can also be used for analytical tasks traditionally addressed with statistical models. Moreover, most recent discussions and reviews on ML focus mainly on DL, failing to synthesise the wealth of ML algorithms with different advantages and general principles. Here, we provide a comprehensive overview of the field of ML and DL, starting by summarizing its historical developments, existing algorithm families, differences to traditional statistical tools, and universal ML principles. We then discuss why and when ML and DL models excel at prediction tasks and where they could offer alternatives to traditional statistical methods for inference, highlighting current and emerging applications for ecological problems. Finally, we summarize emerging trends such as scientific and causal ML, explainable AI, and responsible AI that may significantly impact ecological data analysis in the future. We conclude that ML and DL are powerful new tools for predictive modelling and data analysis. The superior performance of ML and DL algorithms compared to statistical models can be explained by their higher flexibility and automatic data‐dependent complexity optimization. However, their use for causal inference is still disputed as the focus of ML and DL methods on predictions creates challenges for the interpretation of these models. Nevertheless, we expect ML and DL to become an indispensable tool in ecology and evolution, comparable to other traditional statistical tools.

show abstract

Section: New Applications For ML In Eandementioning

confidence: 99%

Machine learning and deep learning—A review for ecologists

2023

View full text Add to dashboard Cite

show abstract

“…While this approach allows us to avoid many of the limitations associated with summary approaches (i.e., approaches that infer a species tree from gene trees), inference could be improved by incorporating both sequence data and inferred gene trees. Recent studies have explored approaches for encoding phylogenetic trees as data in machine learning frameworks (Voznica et al, 2022; Sophia et al, 2022). Future explorations of GANs in phylogenetics may benefit from considering gene tree structures in lieu of or in addition to sequence data.…”

Section: Discussionmentioning

confidence: 99%

Phylogenetic inference using Generative Adversarial Networks

Smith

Hahn

2022

Preprint

View full text Add to dashboard Cite

Motivation:The application of machine learning approaches in phylogenetics has been impeded by the vast model space associated with inference. In particular, supervised machine learning approaches require data from across this space to train models. Because of this requirement, previous approaches have typically been limited to inferring relationships among unrooted quartets of taxa, where there are only three possible topologies. Here, we explore the potential of generative adversarial networks (GANs) to address this limitation. GANs consist of a generator and a discriminator: at each step, the generator aims to create data that is similar to real data, while the discriminator attempts to distinguish generated and real data. By using an evolutionary model as the generator, we use GANs to make evolutionary inferences, and, since a new model can be considered at each iteration, heuristic searches of complex model spaces are possible. Thus, GANs offer a potential solution to the challenges of applying machine learning to inferring phylogenetic relationships.Results:We developed phyloGAN, a GAN that infers phylogenetic relationships among species. phyloGAN takes as input a concatenated alignment, or a set of gene alignments, and then infers a phylogenetic tree either considering or ignoring gene tree heterogeneity. phyloGAN performs well for up to ten taxa in the concatenation case, and performs well for six taxa when considering gene tree heterogeneity. Future developments to the network should aim to make the exploration of this more complex model space more efficient to reduce run times and to enable the consideration of larger trees.Availability:phyloGAN is available on github: https://github.com/meganlsmith/phyloGAN/.

show abstract

“…The resulting trees and location metadata generated by our pipeline were converted to a modified cblv format (Voznica et al 2022), which we refer to as the cblv+S (+State of character, e.g . location) format.…”

Section: Methodsmentioning

confidence: 99%

“…Here we extend new methods of deep learning from phylogenetic trees (Voznica et al 2021; Lambert et al 2022) to explore their potential when applied to phylogeographic problems in geospatial epidemiology. Phylodynamics of birth-death-sampling processes that include migration among locations have been under development for more than a decade (Stadler 2010; Stadler et al 2012; Kühnert et al 2014, 2016; Scire et al 2020; Gao et al 2021, 2022).…”

Section: Introductionmentioning

confidence: 99%

Deep learning and likelihood approaches for viral phylogeography converge on the same answers whether the inference model is right or wrong

Thompson

Liebeskind

Scully

et al. 2023

Preprint

View full text Add to dashboard Cite

Analysis of phylogenetic trees has become an essential tool in epidemiology. Likelihood-based methods fit models to phylogenies to draw inferences about the phylodynamics and history of viral transmission. However, these methods are computationally expensive, which limits the complexity and realism of phylodynamic models and makes them ill-suited for informing policy decisions in real-time during rapidly developing outbreaks. Likelihood-free methods using deep learning are pushing the boundaries of inference beyond these constraints. In this paper, we extend, compare and contrast a recently developed deep learning method for likelihood-free inference from trees. We trained multiple deep neural networks using phylogenies from simulated outbreaks that spread among five locations and found they achieve similar levels of accuracy to Bayesian inference under the true simulation model. We compared robustness to model misspecification of a trained neural network to that of a Bayesian method. We found that both models had comparable performance, converging on similar biases. We also trained and tested a neural network against phylogeographic data from a recent study of the SARS-Cov-2 pandemic in Europe and obtained similar estimates of epidemiological parameters and the location of the common ancestor in Europe. Along with being as accurate and robust as likelihood-based methods, our trained neural networks are on average over 3 orders of magnitude faster. Our results support the notion that neural networks can be trained with simulated data to accurately mimic the good and bad statistical properties of the likelihood functions of generative phylogenetic models.

show abstract

Deep learning from phylogenies to uncover the epidemiological dynamics of outbreaks

Cited by 47 publications

References 49 publications

Machine learning and deep learning—A review for ecologists

Machine learning and deep learning—A review for ecologists

Phylogenetic inference using Generative Adversarial Networks

Deep learning and likelihood approaches for viral phylogeography converge on the same answers whether the inference model is right or wrong

Contact Info

Product

Resources

About