Artificial Intelligence-Driven Graph Methods for Microbiome Research: A Systematic Review.
5 affiliations
- 1Biomedical Technology and Cell Therapy Research Laboratory, Department of Biomedical Engineering, Faculty of Medicine and Health Sciences, McGill University, Quebec, Canada.
- 2Computational Biology and Artificial Intelligence Laboratory, Department of Electrical and Computer Engineering, Faculty of Engineering, McGill University, Quebec, Canada.
- 3Mila - Québec AI Institute, McGill University, Quebec, Canada.
- 4Pharmaceutical Technology Department, Faculty of Pharmacy, Tanta University, Tanta, Egypt.
- 5Department of Quantitative Life Sciences, Faculty of Interfaculty Studies, McGill University, Quebec, Canada.
Abstract
The complexity of high-throughput sequencing data in microbiome research necessitates advanced analytical methods to decipher microbial community structures and interactions. Graph-based methods, which model taxa as nodes and their relationships as edges, have emerged as a powerful framework for this purpose. However, the rapid evolution of these techniques, from classical network analysis to modern graph representation learning, has created a fragmented and complex methodological landscape. This systematic review provides a comprehensive synthesis and structured overview of the field. We systematically review the literature and propose a three-part classification to categorize the primary contribution of each study: (1) novel methods for microbial network representation, (2) applications of classical graph analysis, and (3) the emerging use of graph representation learning for predictive modeling. We summarize the most frequent applications within each class, including keystone species identification, community clustering, and graph-based disease classification. Furthermore, we identify critical cross-cutting challenges, such as the lack of standardized tools and the need for improved model interpretability. By structuring the current landscape of graph-based methods, this review serves as a crucial guide for researchers to select appropriate models and highlights key gaps to direct future research.
Related
- Microbiome, anti-infectives, and artificial intelligence: Decoding host-microbe dynamics.
- Microbiome-driven precision psychiatry: integrating multi-omics, artificial intelligence, and personalized interventions along the gut-brain axis
- Microbiome Continuum: Connecting Environmental, Host-Associated and Engineered Microbiomes Through One Health and Artificial Intelligence.
- Autonomous biomedical research with an artificial intelligence agent
- Artificial intelligence in spatial transcriptomics: a review of methods, datasets, and directions.
BibTeX
@article{shumtim2026artificial,
title = {{Artificial Intelligence-Driven Graph Methods for Microbiome Research: A Systematic Review.}},
author = {Cedrique Shum-Tim and Paromita Islam and Jacqueline L Boyajian and Ahmed Abosalha and Amal Kassab and Madison Santos and Kinaan Aamir Khan and Kiri Stern and Amin Emad and Satya Prakash},
journal = {WIREs mechanisms of disease},
year = {2026},
month = oct,
doi = {10.1002/wsbm.70016},
url = {https://europepmc.org/article/MED/42953986},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial Intelligence-Driven Graph Methods for Microbiome Research: A Systematic Review.
AU - Cedrique Shum-Tim
AU - Paromita Islam
AU - Jacqueline L Boyajian
AU - Ahmed Abosalha
AU - Amal Kassab
AU - Madison Santos
AU - Kinaan Aamir Khan
AU - Kiri Stern
AU - Amin Emad
AU - Satya Prakash
PY - 2026
DA - 2026/10/29
JO - WIREs mechanisms of disease
DO - 10.1002/wsbm.70016
UR - https://europepmc.org/article/MED/42953986
AB - The complexity of high-throughput sequencing data in microbiome research necessitates advanced analytical methods to decipher microbial community structures and interactions. Graph-based methods, which model taxa as nodes and their relationships as edges, have emerged as a powerful framework for this purpose. However, the rapid evolution of these techniques, from classical network analysis to modern graph representation learning, has created a fragmented and complex methodological landscape. This systematic review provides a comprehensive synthesis and structured overview of the field. We systematically review the literature and propose a three-part classification to categorize the primary contribution of each study: (1) novel methods for microbial network representation, (2) applications of classical graph analysis, and (3) the emerging use of graph representation learning for predictive modeling. We summarize the most frequent applications within each class, including keystone species identification, community clustering, and graph-based disease classification. Furthermore, we identify critical cross-cutting challenges, such as the lack of standardized tools and the need for improved model interpretability. By structuring the current landscape of graph-based methods, this review serves as a crucial guide for researchers to select appropriate models and highlights key gaps to direct future research.
SN - 2692-9368
ER -