Detecting introgression from phylogenetic invariant site patterns using machine learning
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.
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
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}
}
EUVIMED