Deep Learning From Phylogenies To Uncover The Epidemiological Dynamics Of Outbreaks - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Article Dans Une Revue Nature Communications Année : 2022

Deep Learning From Phylogenies To Uncover The Epidemiological Dynamics Of Outbreaks

Apprentissage profond de phylogénies pour révéler la dynamique des flambées épidémiques

Résumé

Widely applicable, accurate and fast inference methods in phylodynamics are needed to fully profit from the richness of genetic data in uncovering the dynamics of epidemics. Standard methods, including maximum-likelihood and Bayesian approaches, generally rely on complex mathematical formulae and approximations, and do not scale with dataset size. We develop a likelihood-free, simulation-based approach, which combines deep learning with (1) a large set of summary statistics measured on phylogenies or (2) a complete and compact representation of trees, which avoids potential limitations of summary statistics and applies to any phylodynamics model. Our method enables both model selection and estimation of epidemiological parameters from very large phylogenies. We demonstrate its speed and accuracy on simulated data, where it performs better than the state-of-the-art methods. To illustrate its applicability, we assess the dynamics induced by superspreading individuals in an HIV dataset of men-having-sex-with-men in Zurich. Our tool PhyloDeep is available on github.com/evolbioinfo/phylodeep.
Fichier principal
Vignette du fichier
PhyloDeep_NatureCom_VoznicaEtalGascuel_2022.pdf (4.11 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-03861407 , version 1 (19-11-2022)

Licence

Paternité

Identifiants

Citer

J. Voznica, A. Zhukova, V. Boskova, E. Saulnier, F. Lemoine, et al.. Deep Learning From Phylogenies To Uncover The Epidemiological Dynamics Of Outbreaks. Nature Communications, 2022, 13 (1), pp.3896. ⟨10.1038/s41467-022-31511-0⟩. ⟨hal-03861407⟩
63 Consultations
54 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More