Deep Learning from Phylogenies for Diversification Analyses
Systematic Biology · 2023
DOI: 10.1093/sysbio/syad044 ↗Kurz gefasst
Fachartikel in der Zeitschrift Systematic Biology, 2023. Verfasst von Sophia Lambert und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institut de Biologie de l'École Normale Supérieure, École Normale Supérieure, CNRS, INSERM, Université Paris Sciences et Lettres, 46 Rue d'Ulm, 75005…. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 109 Literaturangaben. Gefördert von: PSL IRIS Science des données, données de la science and the Fondation pour la Recherche Médicale, Ecole Normale Supérieure Paris-Saclay, ED Frontières de l'Innovation en Recherche et Education, Programme Bettencourt.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institut de Biologie de l'École Normale Supérieure, École Normale Supérieure, CNRS, INSERM, Université Paris Sciences et Lettres, 46 Rue d'Ulm, 75005 Paris, France.
- Institute of Ecology and Evolution, Department of Biology, 5289 University of Oregon, Eugene, OR 97403, USA.
- Institut Pasteur, Université Paris Cité, Unité Bioinformatique Evolutive, 25-28 Rue du Dr Roux, 75015 Paris, France.
- Unité de Biologie Computationnelle, USR 3756 CNRS, 25-28 Rue du Dr Roux, 75015 Paris, France.
ORCID-Profile: Sophia Lambert, Jakub Voznica, Hélène Morlon
Förderung
- PSL IRIS Science des données, données de la science and the Fondation pour la Recherche Médicale
- Ecole Normale Supérieure Paris-Saclay
- ED Frontières de l'Innovation en Recherche et Education, Programme Bettencourt
- ED Frontières de l’Innovation en Recherche et Education, Programme Bettencourt
Zitieren
APA
Lambert, S., Voznica, J., & Morlon, H. (2023). Deep Learning from Phylogenies for Diversification Analyses. Systematic Biology. https://doi.org/10.1093/sysbio/syad044
Vancouver
Lambert S, Voznica J, Morlon H. Deep Learning from Phylogenies for Diversification Analyses. Systematic Biology. 2023. doi:10.1093/sysbio/syad044
BibTeX
@article{Lambert2023,
author = {Lambert, Sophia and Voznica, Jakub and Morlon, Hélène},
title = {Deep Learning from Phylogenies for Diversification Analyses},
journal = {Systematic Biology},
year = {2023},
doi = {10.1093/sysbio/syad044}
}
EUVIMED