Attention-based cross domain graph neural network for prediction of drug-drug interactions

Drug-drug interactions (DDI) may lead to adverse reactions in human body and accurate prediction of DDI can mitigate the medical risk. Currently, most of computer-aided DDI prediction methods construct models based on drug-associated features or DDI network, ignoring the potential information contained in drug-related biological entities such as targets and genes. Besides, existing DDI network-based models could not make effective predictions for drugs without any known DDI records. To address the above limitations, we propose an attention-based cross domain graph neural network (ACDGNN) for DDI prediction, which considers the drug-related different entities and propagate information through cross domain operation. Different from the existing methods, ACDGNN not only considers rich information contained in drug-related biomedical entities in biological heterogeneous network, but also adopts cross-domain transformation to eliminate heterogeneity between different types of entities. ACDGNN can be used in the prediction of DDIs in both transductive and inductive setting. By conducting experiments on real-world dataset, we compare the performance of ACDGNN with several state-of-the-art methods. The experimental results show that ACDGNN can effectively predict DDIs and outperform the comparison models.

Automated summary

Drug-drug interactions (DDI) can cause adverse reactions in the body, and accurate prediction of DDI can reduce medical risks. Existing prediction methods mainly focus on drug-related features or DDI networks, neglecting the potential information in drug-related biological entities. To overcome this limitation, we propose an attention-based cross domain graph neural network (ACDGNN) that considers different drug-related entities and uses cross-domain operation to propagate information. ACDGNN demonstrates superior performance in predicting DDIs compared to state-of-the-art models.