Motivation: Recently, research on independently utilizing either explicit knowledge from knowledge graphs or implicit knowledge from biomedical literature for AI drug discovery has been growing rapidly. These approaches have greatly improved the prediction accuracy of AI models on multiple downstream tasks. However, integrating explicit and implicit knowledge independently hinders their understanding of molecules. Results: We propose DeepEIK, a unified deep learning framework that incorporates both explicit and implicit knowledge for AI drug discovery. We adopt feature fusion to process the multi-modal inputs, and leverage the attention mechanism to denoise the text information. Experiments show that DeepEIK significantly outperforms state-of-the-art methods on crucial tasks in AI drug discovery including drug-target interaction prediction, drug property prediction and protein-protein interaction prediction. Further studies show that benefiting from explicit and implicit knowledge, our framework achieves a deeper understanding of molecules and shows promising potential in facilitating drug discovery applications.

翻译：动机：近年来，独立利用知识图谱中的显性知识或生物医学文献中的隐性知识进行AI药物发现的研究快速增长。这些方法在多个下游任务中显著提升了AI模型的预测精度。然而，独立整合显性与隐性知识限制了模型对分子的理解。结果：我们提出DeepEIK，一个统一的深度学习框架，融合显性与隐性知识用于AI药物发现。采用特征融合处理多模态输入，并利用注意力机制对文本信息去噪。实验表明，DeepEIK在AI药物发现的关键任务（包括药物-靶标相互作用预测、药物性质预测和蛋白质-蛋白质相互作用预测）中显著优于现有最先进方法。进一步研究表明，得益于显性与隐性知识，我们的框架实现了对分子的更深层次理解，展现出促进药物发现应用的巨大潜力。