MKGE: Knowledge graph embedding with molecular structure information. (October 2022)

• Record Type: Journal Article
• Authors: Zhang, Yi; Li, Zhouhan; Duan, Biao; Qin, Lei; Peng, Jing
• Is Part Of: Computational biology and chemistry. Volume 100(2022)
• Publication Date: 2022-10
• Subjects: Knowledge graph embedding -- Link prediction -- Molecular representation learning -- Drug-drug interaction prediction; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2022.107730
• Languages: English
• ISSNs: 1476-9271

Abstract

Abstract: To easier manipulate Knowledge Graphs (KGs), knowledge graph embedding (KGE) is proposed and wildly used. However, the relations between entities are usually incomplete due to the performance problems of knowledge extraction methods, which also leads to the sparsity of KGs and make it difficult for KGE methods to obtain reliable representations. Related research has not paid much attention to this challenge in the biomedicine field and has not sufficiently integrated the domain knowledge into KGE methods. To alleviate this problem, we try to incorporate the molecular structure information of the entity into KGE. Specifically, we adopt two strategies to obtain the vector representations of the entities: text-structure-based and graph-structure-based. Then, we spliced the two together as the input of the KGE models. To validate our model, we construct a KCCR knowledge graph and validate the model's superiority in entity prediction, relation prediction, and drug-drug interaction prediction tasks. To the best of our knowledge, this is the first time that molecular structure information has been integrated into KGE methods. It is worth noting that researchers can try to improve the work based on KGE by fusing other feature annotations such as Gene Ontology and protein structure. Highlights: Predicting drug-drug interaction is critical to clinical medication. The molecular structure information is effective for knowledge graph embedding methods. Obtain the molecular representations by two strategies based on text and graph.