MDPAGCN: Predicting Microbe-Drug Associations based on Dual Attention Graph Convolution

Clinical research highlights the interaction between human-residing microorganisms and drug efficacy/toxicity, making microbes innovative targets for antibacterial drug development. The growing availability of microbiome and drug data offers opportunities to use machine learning to predict microbedrug associations, enhancing research and development. Previous computational approaches typically learned microbe representations from the entire graph of microbe-drug associations. Drugs exhibit different mechanisms of action for various microbes, while learning drug representations remains static and agnostic to different microorganisms. When the same microbe interacts with different drugs, it becomes crucial to discern relevant contextual information. With this in mind, we introduce a novel method, MDPAGCN, which utilizes a dual-attention GCN to extract contextual information from microbe-drug pairs within larger microbe-drug association graphs. We then employ a graph convolutional network to learn feature representations for specific microbe-drug subgraphs. Treating microbe-drug associations as a graph classification task, we generate a fixed-size matrix that integrates graph representations using an attention pooling layer, and the graphs are classified using a fully connected module. Experimental results under different cross-validation settings show that our proposed method outperforms seven benchmark methods. A case study on the prediction of microbe-drug associations further demonstrates the effectiveness of our proposed MDPAGCN method.