EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Detecting introgression from phylogenetic invariant site patterns using machine learning

Patrick F McKenzie iD, Deren A R Eaton iD

Applications in Plant Sciences · 2026-05 · 14 (3)

DOI: 10.1002/aps3.70061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applications in Plant Sciences, online erschienen am 19.06.2026. Verfasst von Patrick F McKenzie und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Botany and Plant Pathology Oregon State University Corvallis 97331 Oregon USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Division of Environmental Biology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Premise Detecting historical introgression among populations or species from genomic data is a common goal in evolutionary genetics. Most current methods fall into two major categories: network inference and admixture inference. Network inference (e.g., SNaQ) is computationally challenging and typically requires first reducing large genomic datasets into a less informative collection of inferred gene trees. In contrast, admixture inference (e.g., ABBA‐BABA tests) can accommodate enormous single‐nucleotide polymorphism (SNP) datasets but is restricted to examining subsets of four to five samples at a time. Here, we demonstrate a new approach to evaluate SNP frequencies among quartet samples under a phylogenetic hypothesis (similar to ABBA‐BABA tests), while examining all quartet information simultaneously (similar to the network inference methods). Methods and Results To do this, our method simcat trains a neural network machine learning model on coalescent simulations to discriminate between introgression scenarios based on learned SNP frequency patterns. We demonstrate the accuracy of simcat to classify introgression events from simulations, evaluate its sensitivity to variation in species tree parameters, and demonstrate its application to an empirical dataset of oak trees ( Quercus ser. Virentes ). Conclusions Our approach represents a first step towards leveraging machine learning to expand phylogenetic invariants–based methods beyond the scale of quartets to a larger phylogenetic context.

Schlagwörter

Stichwörter der Autor:innen

Pythonadmixturecoalescentevolutionmachine learningneural networkphylogenetic network

Autor:innen und Institutionen

  • Department of Botany and Plant Pathology Oregon State University Corvallis 97331 Oregon USA.
  • Department of Organismic and Evolutionary Biology, Arnold Arboretum Harvard University Boston 02131 Massachusetts USA.
  • Department of Ecology, Evolution, and Environmental Biology Columbia University New York 10027 New York USA.

ORCID-Profile: Patrick F McKenzie, Deren A R Eaton

Förderung

  • Division of Environmental Biology

Zitieren

APA

McKenzie, P. F., & Eaton, D. A. R. (2026). Detecting introgression from phylogenetic invariant site patterns using machine learning. Applications in Plant Sciences, 14(3). https://doi.org/10.1002/aps3.70061

Vancouver

McKenzie PF, Eaton DAR. Detecting introgression from phylogenetic invariant site patterns using machine learning. Applications in Plant Sciences. 2026;14(3). doi:10.1002/aps3.70061

BibTeX
@article{McKenzie2026,
  author = {McKenzie, Patrick F and Eaton, Deren A R},
  title = {Detecting introgression from phylogenetic invariant site patterns using machine learning},
  journal = {Applications in Plant Sciences},
  year = {2026},
  volume = {14},
  number = {3},
  doi = {10.1002/aps3.70061}
}
Kostenlos starten →