EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Phylogenetic Methods Meet Deep Learning

Svitlana Braichenko iD, Rui Borges iD, Carolin Kosiol iD

Genome Biology and Evolution · 30.09.2025 · 17 (10)

DOI: 10.1093/gbe/evaf177 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genome Biology and Evolution, online erschienen am 19.09.2025. Verfasst von Svitlana Braichenko und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Genetics and Cancer, University of Edinburgh, Edinburgh EH4 2XU, UK. Hauptthemen laut MEDLINE: Deep Learning, Phylogeny. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Biotechnology and Biological Sciences Research Council, Austrian Science Fund (FWF), Medical Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) has been widely used in various scientific fields, but its integration into phylogenetics has been slower, primarily due to the complex nature of phylogenetic data. The studies that apply DL to sequencing data often limit analyses to four-taxon trees. Many of these studies serve as “proof of principle” and perform similarly to traditional phylogeny reconstruction methods. New ways of using training data, such as encoding with compact bijective ladderized vectors or transformers, enable the handling of much larger trees and genomic data sets. This short perspective focuses on the application of DL in phylogenetics, introducing prevalent DL architectures. We highlight potential problems in the field by discussing the risks of using simulation-based training data and emphasize the importance of reproducibility and robustness in computational estimates. Finally, we explore promising research areas, including the combination of phylogenetics and population genetics in DL, the analysis of neighbor dependencies, and the potential to significantly reduce computational cost compared to traditional methods. This perspective illustrates the potential of DL in complementing traditional phylogeny reconstruction methods and aiding the advancement of phylogenetic analysis, especially in performing computationally demanding tasks such as model selection or estimating branch support values.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPhylogenyHumansGenomics

Stichwörter der Autor:innen

machine learningneural networkphylodynamics and diversification studiesphylogenetics

Autor:innen und Institutionen

  • Institute of Genetics and Cancer, University of Edinburgh, Edinburgh EH4 2XU, UK.
  • School of Mathematics and Statistics, Mathematical Institute, University of St Andrews, St Andrews KY16 9SS, UK.
  • Institut für Populationsgenetik, Vetmeduni Vienna, Wien 1210, Austria.
  • Centre for Biological Diversity, School of Biology, University of St Andrews, Fife KY16 9TH, UK.

ORCID-Profile: Svitlana Braichenko, Rui Borges, Carolin Kosiol

Förderung

  • Biotechnology and Biological Sciences Research Council
  • Austrian Science Fund (FWF)
  • Medical Research Council

Zitieren

APA

Braichenko, S., Borges, R., & Kosiol, C. (2025). Phylogenetic Methods Meet Deep Learning. Genome Biology and Evolution, 17(10). https://doi.org/10.1093/gbe/evaf177

Vancouver

Braichenko S, Borges R, Kosiol C. Phylogenetic Methods Meet Deep Learning. Genome Biology and Evolution. 2025;17(10). doi:10.1093/gbe/evaf177

BibTeX
@article{Braichenko2025,
  author = {Braichenko, Svitlana and Borges, Rui and Kosiol, Carolin},
  title = {Phylogenetic Methods Meet Deep Learning},
  journal = {Genome Biology and Evolution},
  year = {2025},
  volume = {17},
  number = {10},
  doi = {10.1093/gbe/evaf177}
}
Kostenlos starten →