DMSG-VBM: Deep Multi-Source Graph-Enhanced Variational Bayesian Model for Predicting Higher-Order Microbe-Drug-Disease Associations
ACS Synthetic Biology · 29.10.2026
DOI: 10.1021/acssynbio.6c00335 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Synthetic Biology, online erschienen am 29.10.2026. Verfasst von Yingjun Ma und 4 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Gefördert von: Ministry of Education of the People's Republic of China, Natural Science Foundation of Xiamen Municipality, Hubei University of Arts and Science.
Abstract (Originalsprache)
Exploring potential relationships among drugs, microbes, and diseases is critical for advancing disease prevention and drug development. Several computational models have been developed to predict high-order interactions in multi-omics biological systems. However, negative sampling-based methods risk generating false negatives, whereas tensor decomposition approaches typically require extensive hyperparameter tuning and exhibit limited flexibility when handling complex data architectures. To address these limitations, we propose DMSG-VBM, a Bayesian Logistic Tensor Decomposition model incorporating multi-source graph deep learning. The model employs multi-source graph deep learning to generate prior expectations of latent variables while establishing an attention mechanism to facilitate the integration of multi-source features. Furthermore, DMSG-VBM integrates tensor-based Bayesian inference with multi-source graph deep learning within a probabilistic graphical model and adopts a variational expectation-maximization algorithm for adaptive inference of model parameters and latent variables. Experimental results across four scenarios on two benchmark datasets demonstrate that DMSG-VBM achieves superior performance in triplet prediction compared to other state-of-the-art methods, for both balanced and extremely imbalanced scenarios. Additionally, it exhibits higher hit rates in predictive tasks involving novel drugs, novel microbes, and novel diseases. Case studies further substantiate that DMSG-VBM effectively predicts potential associations among drugs, microbes, and diseases. The codes and dataset are available at: https://github.com/Mayingjun20179/DMSG-VBM.
Förderung
- Ministry of Education of the People's Republic of China
- Natural Science Foundation of Xiamen Municipality
- Hubei University of Arts and Science
- Hubei Provincial Department of Education
Zitieren
APA
Ma, Y., Zeng, H., Zhong, J., Liu, Y., & Ma, Y. (2026). DMSG-VBM: Deep Multi-Source Graph-Enhanced Variational Bayesian Model for Predicting Higher-Order Microbe-Drug-Disease Associations. ACS Synthetic Biology. https://doi.org/10.1021/acssynbio.6c00335
Vancouver
Ma Y, Zeng H, Zhong J, Liu Y, Ma Y. DMSG-VBM: Deep Multi-Source Graph-Enhanced Variational Bayesian Model for Predicting Higher-Order Microbe-Drug-Disease Associations. ACS Synthetic Biology. 2026. doi:10.1021/acssynbio.6c00335
BibTeX
@article{Ma2026,
author = {Ma, Yingjun and Zeng, Huiqin and Zhong, Junjiang and Liu, Yunfang and Ma, Yuanyuan},
title = {DMSG-VBM: Deep Multi-Source Graph-Enhanced Variational Bayesian Model for Predicting Higher-Order Microbe-Drug-Disease Associations},
journal = {ACS Synthetic Biology},
year = {2026},
doi = {10.1021/acssynbio.6c00335}
}
EUVIMED