Phyloformer: Fast, Accurate, and Versatile Phylogenetic Reconstruction with Deep Neural Networks
Molecular Biology and Evolution · 01.04.2025 · 42 (4)
DOI: 10.1093/molbev/msaf051 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecular Biology and Evolution, online erschienen am 11.03.2025. Verfasst von Luca Nesterenko und 4 weiteren Autor:innen. Beteiligte Einrichtung: Laboratoire de Biométrie et Biologie Évolutive, Université Lyon 1, Villeurbanne, France. Hauptthemen laut MEDLINE: Phylogeny, Neural Networks, Computer, Software, Deep Learning. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Agence Nationale de la Recherche, IDRIS.
Abstract (Originalsprache)
Phylogenetic inference aims at reconstructing the tree describing the evolution of a set of sequences descending from a common ancestor. The high computational cost of state-of-the-art maximum likelihood and Bayesian inference methods limits their usability under realistic evolutionary models. Harnessing recent advances in likelihood-free inference and geometric deep learning, we introduce Phyloformer, a fast and accurate method for evolutionary distance estimation and phylogenetic reconstruction. Sampling many trees and sequences under an evolutionary model, we train the network to learn a function that enables predicting a tree from a multiple sequence alignment. On simulated data, we compare Phyloformer to FastME—a distance method—and two maximum likelihood methods: FastTree and IQTree. Under a commonly used model of protein sequence evolution and exploiting graphics processing unit (GPU) acceleration, Phyloformer outpaces all other approaches and exceeds their accuracy in the Kuhner–Felsenstein metric that accounts for both the topology and branch lengths. In terms of topological accuracy alone, Phyloformer outperforms FastME, but falls behind maximum likelihood approaches, especially as the number of sequences increases. When a model of sequence evolution that includes dependencies between sites is used, Phyloformer outperforms all other methods across all metrics on alignments with fewer than 80 sequences. On 3,801 empirical gene alignments from five different datasets, Phyloformer matches the topological accuracy of the two maximum likelihood implementations. Our results pave the way for the adoption of sophisticated realistic models for phylogenetic inference.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratoire de Biométrie et Biologie Évolutive, Université Lyon 1, Villeurbanne, France.
- Laboratory of Computational and Quantitative Biology, Sorbonne Université, Paris, France.
ORCID-Profile: Luca Nesterenko, Luc Blassel, Philippe Veber, Bastien Boussau, Laurent Jacob
Förderung
- Agence Nationale de la Recherche
- IDRIS
Zitieren
APA
Nesterenko, L., Blassel, L., Veber, P., Boussau, B., & Jacob, L. (2025). Phyloformer: Fast, Accurate, and Versatile Phylogenetic Reconstruction with Deep Neural Networks. Molecular Biology and Evolution, 42(4). https://doi.org/10.1093/molbev/msaf051
Vancouver
Nesterenko L, Blassel L, Veber P, Boussau B, Jacob L. Phyloformer: Fast, Accurate, and Versatile Phylogenetic Reconstruction with Deep Neural Networks. Molecular Biology and Evolution. 2025;42(4). doi:10.1093/molbev/msaf051
BibTeX
@article{Nesterenko2025,
author = {Nesterenko, Luca and Blassel, Luc and Veber, Philippe and Boussau, Bastien and Jacob, Laurent},
title = {Phyloformer: Fast, Accurate, and Versatile Phylogenetic Reconstruction with Deep Neural Networks},
journal = {Molecular Biology and Evolution},
year = {2025},
volume = {42},
number = {4},
doi = {10.1093/molbev/msaf051}
}
EUVIMED