Interpreting Supervised Machine Learning Inferences in Population Genomics Using Haplotype Matrix Permutations
Molecular Biology and Evolution · 2025
DOI: 10.1093/molbev/msaf250 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecular Biology and Evolution, 2025. Verfasst von Linh N Tran und 2 weiteren Autor:innen. Beteiligte Einrichtung: Genetics Graduate Interdisciplinary Program, University of Arizona, Tucson, AZ 85721, USA. Hauptthemen laut MEDLINE: Haplotypes, Supervised Machine Learning, Genetics, Population, Metagenomics. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, National Institute of General Medical Sciences.
Abstract (Originalsprache)
Supervised machine learning methods, such as convolutional neural networks (CNNs), that use haplotype matrices as input data have become powerful tools for population genomics inference. However, these methods often lack interpretability, making it difficult to understand which population genetics features drive their predictions—a critical limitation for method development and biological interpretation. Here, we introduce a systematic permutation approach that progressively disrupts population genetics features within input test haplotype matrices, including linkage disequilibrium, haplotype structure, and allele frequencies. By measuring performance degradation after each permutation, the importance of each feature can be assessed. We applied our approach to three published CNNs for positive selection and demographic history inference. We found that the positive selection inference CNN ImaGene critically depends on haplotype structure and linkage disequilibrium patterns, while the demographic inference CNN relies primarily on allele frequency information. Surprisingly, another positive selection inference CNN, disc-pg-gan, achieved high accuracy using only simple allele count information, suggesting its training regime may not adequately challenge the model to learn complex population genetic signatures. Our approach provides a straightforward, model-agnostic, and biologically-motivated framework for interpreting any haplotype matrix-based method, offering insights that can guide both method development and application in population genomics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Genetics Graduate Interdisciplinary Program, University of Arizona, Tucson, AZ 85721, USA.
- Department of Molecular & Cellular Biology, University of Arizona, Tucson, AZ 85721, USA.
ORCID-Profile: Linh N Tran, David Castellano, Ryan N Gutenkunst
Förderung
- NIGMS NIH HHS
- National Institute of General Medical Sciences
Zitieren
APA
Tran, L. N., Castellano, D., & Gutenkunst, R. N. (2025). Interpreting Supervised Machine Learning Inferences in Population Genomics Using Haplotype Matrix Permutations. Molecular Biology and Evolution. https://doi.org/10.1093/molbev/msaf250
Vancouver
Tran LN, Castellano D, Gutenkunst RN. Interpreting Supervised Machine Learning Inferences in Population Genomics Using Haplotype Matrix Permutations. Molecular Biology and Evolution. 2025. doi:10.1093/molbev/msaf250
BibTeX
@article{Tran2025,
author = {Tran, Linh N and Castellano, David and Gutenkunst, Ryan N},
title = {Interpreting Supervised Machine Learning Inferences in Population Genomics Using Haplotype Matrix Permutations},
journal = {Molecular Biology and Evolution},
year = {2025},
doi = {10.1093/molbev/msaf250}
}
EUVIMED