EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detecting Interspecific Positive Selection Using Convolutional Neural Networks

Charlotte West iD, Conor R Walker iD, Shayesteh Arasti iD, Viacheslav Vasilev iD, Xingze Xu iD, Nicola De Maio iD, Nick Goldman iD

Molecular Biology and Evolution · 2025

DOI: 10.1093/molbev/msaf154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Biology and Evolution, 2025. Verfasst von Charlotte West und 6 weiteren Autor:innen. Beteiligte Einrichtung: European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK. Hauptthemen laut MEDLINE: Neural Networks, Computer, Selection, Genetic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Molecular Biology Laboratory, National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional statistical methods using maximum likelihood and Bayesian inference can detect positive selection from an interspecific phylogeny and a codon sequence alignment based on model assumptions, but they are prone to false positives due to alignment errors and can lack power. These problems are particularly pronounced when faced with high levels of indels and divergence. To address these issues, we trained and tested convolutional neural network models on simulated data and achieved higher accuracy in detecting selection across a specific range of phylogenetic scenarios and evolutionary modes. This advantage is particularly evident when performing inference on noisy data prone to misalignments. Our method shows some ability to account for these errors, where most statistical frameworks fail to do so in a tractable manner. We explore the generalizability of our convolutional neural network models to unseen evolutionary scenarios and identify future avenues to achieve broader utility. Once trained, our convolutional neural network model is faster at test time, making it a scalable alternative to traditional statistical methods for large-scale, multigene analyses. In addition to binary classification (inference of the presence or absence of positive selection during the evolution of the sequences), we use saliency maps to understand what the model learns and observe how this could be leveraged for sitewise inference of positive selection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerSelection, GeneticPhylogenyModels, GeneticEvolution, MolecularConvolutional Neural Networks

Stichwörter der Autor:innen

AIconvolutional neural networkevolutionmachine learningpositive selectionselection

Autor:innen und Institutionen

  • European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton CB10 1SD, UK.
  • Department of Genetics, University of Cambridge, Cambridge CB2 3EH, UK.

ORCID-Profile: Charlotte West, Conor R Walker, Shayesteh Arasti, Viacheslav Vasilev, Xingze Xu, Nicola De Maio, Nick Goldman

Förderung

  • European Molecular Biology Laboratory
  • National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre
  • NIH HHS
  • Cambridge Mathematics Placements programme

Zitieren

APA

West, C., Walker, C. R., Arasti, S., Vasilev, V., Xu, X., De Maio, N., & Goldman, N. (2025). Detecting Interspecific Positive Selection Using Convolutional Neural Networks. Molecular Biology and Evolution. https://doi.org/10.1093/molbev/msaf154

Vancouver

West C, Walker CR, Arasti S, Vasilev V, Xu X, De Maio N, et al. Detecting Interspecific Positive Selection Using Convolutional Neural Networks. Molecular Biology and Evolution. 2025. doi:10.1093/molbev/msaf154

BibTeX
@article{West2025,
  author = {West, Charlotte and Walker, Conor R and Arasti, Shayesteh and Vasilev, Viacheslav and Xu, Xingze and De Maio, Nicola and Goldman, Nick},
  title = {Detecting Interspecific Positive Selection Using Convolutional Neural Networks},
  journal = {Molecular Biology and Evolution},
  year = {2025},
  doi = {10.1093/molbev/msaf154}
}
Kostenlos starten →