Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May 30:16:1578140.
doi: 10.3389/fphar.2025.1578140. eCollection 2025.

Harnessing dual variational autoencoders to decode microbe roles in diseases for traditional medicine discovery

Qing Ye  1 , Yaxin Sun  1   2   3
Affiliations

Harnessing dual variational autoencoders to decode microbe roles in diseases for traditional medicine discovery

Qing Ye et al. Front Pharmacol. .

Abstract

Traditional medicine encompasses a rich trove of knowledge and practices for disease prevention, diagnosis, and treatment. However, it faces challenges such as poorly defined compositions of preparations and limited high-quality efficacy data. The development of artificial intelligence presents new opportunities for traditional medicine research and applications, especially in predicting MDAs (MDAs), which is of great significance for understanding disease mechanisms and developing new treatments. This study proposes a MDAs prediction method based on double variational autoencoders (DVAMDA). This method innovatively integrates double variational autoencoders and multi-information fusion techniques. Firstly, the graph SAGE encoder is utilized to preliminarily extract the local and global structural information of nodes. Subsequently, the double variational autoencoders are employed to separately extract the latent probability distribution information of the initial input data and the graph-specific property information from the output of the graph SAGE encoder. Then, these different sources of information are fused to provide rich and powerful feature support for subsequent prediction tasks. Finally, the Hadamard product operation and a deep neural network are used to predict MDAs. Experimental results on the HMDAD and Disbiome datasets show that the DVAMDA model performs outstandingly in multiple evaluation metrics. The findings of this research contribute to a deeper understanding of microbe-disease relationships and provide strong support for drug development in traditional medicine based on MDAs. The relevant data and code are publicly accessible at: https://github.com/yxsun25/DVAMDA.

Keywords: double variational autoencoders; microbe-disease association; multi-information fusion; prediction model; traditional medicine discovery.

PubMed Disclaimer

Conflict of interest statement

Author YS was employed by Zhejiang Aerospace Hengjia Data Technology Co., Ltd. The remaining author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

FIGURE 1
FIGURE 1
DVAMDA structure.
FIGURE 2
FIGURE 2
AUCs of the performance comparison on HMDAD database.
FIGURE 3
FIGURE 3
AUPRs of the performance comparison on HMDAD database.
FIGURE 4
FIGURE 4
AUCs of the performance comparison on Disbiome database.
FIGURE 5
FIGURE 5
AUPRs of the performance comparison on Disbiome database.
FIGURE 6
FIGURE 6
AUCs of the performance comparison on MMDA database.
FIGURE 7
FIGURE 7
AUPRs of the performance comparison on MMDA database.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Adamic L. A., Adar E. (2003). Friends and neighbors on the Web. Social Networks, 25 (3), 211–230. 10.1016/S0378-8733(03)00009-1 - DOI
    1. Chen H., Chen K. (2024). Predicting disease - associated microbes based on similarity fusion and deep learning. Briefings Bioinforma. 25 (6), bbae550. 10.1093/bib/bbae550 - DOI - PMC - PubMed
    1. Chen J., Tao R., Qiu Y., Yuan Q. (2024a). CMFHMDA: a prediction framework for human disease - microbe associations based on cross - domain matrix factorization. Briefings Bioinforma. 25 (6), bbae481. 10.1093/bib/bbae481 - DOI - PMC - PubMed
    1. Chen R., Xie G., Lin Z., Gu G., Yu Y., Yu J., et al. (2024b). Predicting microbe-disease associations based on a linear neighborhood label propagation method with multi-order similarity fusion learning. Interdiscip. Sci. Comput. Life Sci. 16, 345–360. 10.1007/s12539-024-00607-0 - DOI - PubMed
    1. Cheng E., Zhao J., Wang H., Song S., Xiong S., Sun Y. (2023). Dual network contrastive learning for predicting microbe -disease associations. IEEE/ACM Trans. Comput. Biol. Bioinforma. 20 (6), 3469–3481. 10.1109/TCBB.2022.3228617 - DOI

LinkOut - more resources