PhyloMix: enhancing microbiome-trait association prediction through phylogeny-mixing augmentation
Bioinformatics · 2025
DOI: 10.1093/bioinformatics/btaf014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Yifan Jiang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, N2L 3G1, Canada. Hauptthemen laut MEDLINE: Phylogeny, Microbiota, Software, Computational Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Canadian NSERC Discovery.
Abstract (Originalsprache)
Motivation Understanding the associations between traits and microbial composition is a fundamental objective in microbiome research. Recently, researchers have turned to machine learning (ML) models to achieve this goal with promising results. However, the effectiveness of advanced ML models is often limited by the unique characteristics of microbiome data, which are typically high-dimensional, compositional, and imbalanced. These characteristics can hinder the models’ ability to fully explore the relationships among taxa in predictive analyses. To address this challenge, data augmentation has become crucial. It involves generating synthetic samples with artificial labels based on existing data and incorporating these samples into the training set to improve ML model performance. Results Here, we propose PhyloMix, a novel data augmentation method specifically designed for microbiome data to enhance predictive analyses. PhyloMix leverages the phylogenetic relationships among microbiome taxa as an informative prior to guide the generation of synthetic microbial samples. Leveraging phylogeny, PhyloMix creates new samples by removing a subtree from one sample and combining it with the corresponding subtree from another sample. Notably, PhyloMix is designed to address the compositional nature of microbiome data, effectively handling both raw counts and relative abundances. This approach introduces sufficient diversity into the augmented samples, leading to improved predictive performance. We empirically evaluated PhyloMix on six real microbiome datasets across five commonly used ML models. PhyloMix significantly outperforms distinct baseline methods including sample-mixing-based data augmentation techniques like vanilla mixup and compositional cutmix, as well as the phylogeny-based method TADA. We also demonstrated the wide applicability of PhyloMix in both supervised learning and contrastive representation learning. Availability and implementation The Apache-licensed source code is available at (https://github.com/batmen-lab/phylomix).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, N2L 3G1, Canada.
- School of Life Sciences, Arizona State University, Tempe, AZ, 85281, United States.
ORCID-Profile: Yang Young Lu
Förderung
- Canadian NSERC Discovery
Zitieren
APA
Jiang, Y., Liao, D., Zhu, Q., & Lu, Y. Y. (2025). PhyloMix: enhancing microbiome-trait association prediction through phylogeny-mixing augmentation. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf014
Vancouver
Jiang Y, Liao D, Zhu Q, Lu YY. PhyloMix: enhancing microbiome-trait association prediction through phylogeny-mixing augmentation. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf014
BibTeX
@article{Jiang2025,
author = {Jiang, Yifan and Liao, Disen and Zhu, Qiyun and Lu, Yang Young},
title = {PhyloMix: enhancing microbiome-trait association prediction through phylogeny-mixing augmentation},
journal = {Bioinformatics},
year = {2025},
doi = {10.1093/bioinformatics/btaf014}
}
EUVIMED