Toward better drug discovery with knowledge graph. (February 2022)

• Record Type: Journal Article
• Authors: Zeng, Xiangxiang; Tu, Xinqi; Liu, Yuansheng; Fu, Xiangzheng; Su, Yansen
• Is Part Of: Current opinion in structural biology. Volume 72(2022)
• Page Start: 114
• Page End: 126
• Publication Date: 2022-02
• Subjects: Molecular biology -- Periodicals; 570
• DOI: 10.1016/j.sbi.2021.09.003
• Languages: English
• ISSNs: 0959-440X

Abstract

Abstract: Drug discovery is the process of new drug identification. This process is driven by the increasing data from existing chemical libraries and data banks. The knowledge graph is introduced to the domain of drug discovery for imposing an explicit structure to integrate heterogeneous biomedical data. The graph can provide structured relations among multiple entities and unstructured semantic relations associated with entities. In this review, we summarize knowledge graph-based works that implement drug repurposing and adverse drug reaction prediction for drug discovery. As knowledge representation learning is a common way to explore knowledge graphs for prediction problems, we introduce several representative embedding models to provide a comprehensive understanding of knowledge representation learning. Highlights: Knowledge graph (KG) has been leveraged to assist and accelerate data-driven drug discovery. The main contribution of KG is providing structured relations among multiple entities and unstructured semantic relations. Prediction of potential interaction like drug–drug interaction is modeled as a link prediction problem based on the KG. KG-based works in drug discovery mainly focus on drug repurposing and adverse drug reaction prediction.