Drug repositioning/repurposing is a very important approach towards identifying novel treatments for diseases in drug discovery. Recently, large-scale biological datasets are increasingly available for pharmaceutical research and promote the development of drug repositioning, but efficiently utilizing these datasets remains challenging. In this paper, we develop a novel multimodal framework, termed GraphPK (Graph-based Prior Knowledge) for improving in silico drug repositioning via using the prior knowledge from a drug knowledge graph. First, we construct a knowledge graph by integrating relevant bio-entities (drugs, diseases, etc.) and associations/interactions among them, and apply the knowledge graph embedding technique to extract prior knowledge of drugs and diseases. Moreover, we make use of the known drug-disease association, and obtain known association-based features from an association bipartite graph through graph embedding, and also take into account biological domain features, i.e., drug chemical structures and disease semantic similarity. Finally, we design a multimodal neural network to combine three types of features from the knowledge graph, the known associations and the biological domain, and build the prediction model for predicting drug-disease associations. Massive experiments show that our method outperforms other state-of-the-art methods in terms of most metrics, and the ablation analysis regarding the three types of features reveals that prior knowledge from knowledge graphs can not only lift the predictive power of in silico drug repositioning, but also enhance the model's robustness to different scenarios. The results of case studies offer support that GraphPK has the potential for actual use.

中文翻译：

---

利用知识图谱中的先验知识改进计算机药物重新定位的多模式框架

药物重新定位/再利用是在药物发现中确定疾病新疗法的非常重要的方法。最近，大规模生物数据集越来越多地可用于药物研究并促进药物重新定位的发展，但有效利用这些数据集仍然具有挑战性。在本文中，我们开发了一种新颖的多模式框架，称为 GraphPK（基于图的先验知识），用于改进通过使用药物知识图中的先验知识进行计算机药物重新定位。首先，我们通过整合相关的生物实体（药物、疾病等）以及它们之间的关联/相互作用来构建知识图谱，并应用知识图谱嵌入技术来提取药物和疾病的先验知识。此外，我们利用已知的药物-疾病关联，通过图嵌入从关联二分图中获得已知的基于关联的特征，同时考虑生物领域特征，即药物化学结构和疾病语义相似性。最后，我们设计了一个多模态神经网络，将知识图谱、已知关联和生物领域的三类特征结合起来，构建了预测药物-疾病关联的预测模型。在计算机模拟药物重新定位，还增强了模型对不同场景的鲁棒性。案例研究的结果支持 GraphPK 具有实际应用的潜力。