Graph2MDA: a multi-modal variational graph embedding model for predicting microbe-drug associations

TL;DR

Graph2MDA is a novel variational graph autoencoder-based model that predicts microbe-drug associations by integrating multi-modal features, outperforming existing methods and revealing meaningful biological insights.

Contribution

The paper introduces Graph2MDA, a new multi-modal variational graph embedding approach for microbe-drug association prediction, leveraging diverse biological features and deep learning.

Findings

Outperforms six state-of-the-art methods on three datasets.

Learned latent representations show meaningful clustering aligned with drug classifications.

Predicted associations validated by literature with 75-95% accuracy.

Abstract

Accumulated clinical studies show that microbes living in humans interact closely with human hosts, and get involved in modulating drug efficacy and drug toxicity. Microbes have become novel targets for the development of antibacterial agents. Therefore, screening of microbe-drug associations can benefit greatly drug research and development. With the increase of microbial genomic and pharmacological datasets, we are greatly motivated to develop an effective computational method to identify new microbe-drug associations. In this paper, we proposed a novel method, Graph2MDA, to predict microbe-drug associations by using variational graph autoencoder (VGAE). We constructed multi-modal attributed graphs based on multiple features of microbes and drugs, such as molecular structures, microbe genetic sequences, and function annotations. Taking as input the multi-modal attribute graphs, VGAE was trained to learn the informative and interpretable latent representations of each node and the whole graph, and then a deep neural network classifier was used to predict microbe-drug associations. The hyperparameter analysis and model ablation studies showed the sensitivity and robustness of our model. We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods. We also explored the meaningness of the learned latent representations of drugs and found that the drugs show obvious clustering patterns that are significantly consistent with drug ATC classification. Moreover, we conducted case studies on two microbes and two drugs and found 75\%-95\% predicted associations have been reported in PubMed literature. Our extensive performance evaluations validated the effectiveness of our proposed method.\