Intelligent Bioinformatics Laboratory, Wuhan University of Technology, Wuhan 430070, China.
Intelligent Bioinformatics Laboratory, Wuhan University of Technology, Wuhan 430070, China.
Comput Biol Chem. 2022 Oct;100:107730. doi: 10.1016/j.compbiolchem.2022.107730. Epub 2022 Jul 14.
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.
为了更方便地操作知识图谱（KGs），提出并广泛使用了知识图谱嵌入（KGE）。然而，由于知识提取方法的性能问题，实体之间的关系通常是不完整的，这也导致了 KGs 的稀疏性，使得 KGE 方法难以获得可靠的表示。相关研究在生物医学领域并没有过多关注这一挑战，也没有充分将领域知识融入到 KGE 方法中。为了缓解这个问题，我们尝试将实体的分子结构信息纳入 KGE。具体来说，我们采用了两种策略来获取实体的向量表示：基于文本结构的和基于图结构的。然后，我们将这两种表示拼接在一起作为 KGE 模型的输入。为了验证我们的模型，我们构建了一个 KCCR 知识图谱，并验证了模型在实体预测、关系预测和药物-药物相互作用预测任务中的优势。据我们所知，这是首次将分子结构信息融入 KGE 方法。值得注意的是，研究人员可以尝试通过融合其他特征注释，如基因本体论和蛋白质结构，来改进基于 KGE 的工作。
