Yang Yang, Zheng Zixuan, Xu Yuyang, Wei Huifang, Yan Wenying
Computing Science and Artificial Intelligence College, Suzhou City University, No. 1188 Wuzhong Avenue, Wuzhong District Suzhou, Suzhou 215004, China.
Suzhou Key Lab of Multi-modal Data Fusion and Intelligent Healthcare, No. 1188 Wuzhong Avenue, Wuzhong District Suzhou, Suzhou 215004, China.
Brief Bioinform. 2024 Nov 22;26(1). doi: 10.1093/bib/bbaf025.
The automatic and accurate extraction of diverse biomedical relations from literature constitutes the core elements of medical knowledge graphs, which are indispensable for healthcare artificial intelligence. Currently, fine-tuning through stacking various neural networks on pre-trained language models (PLMs) represents a common framework for end-to-end resolution of the biomedical relation extraction (RE) problem. Nevertheless, sequence-based PLMs, to a certain extent, fail to fully exploit the connections between semantics and the topological features formed by these connections. In this study, we presented a graph-driven framework named BioGSF for RE from the literature by integrating shortest dependency paths (SDP) with entity-pair graph through the employment of the graph neural network model. Initially, we leveraged dependency relationships to obtain the SDP between entities and incorporated this information into the entity-pair graph. Subsequently, the graph attention network was utilized to acquire the topological information of the entity-pair graph. Ultimately, the obtained topological information was combined with the semantic features of the contextual information for relation classification. Our method was evaluated on two distinct datasets, namely S4 and BioRED. The outcomes reveal that BioGSF not only attains the superior performance among previous models with a micro-F1 score of 96.68% (S4) and 96.03% (BioRED), but also demands the shortest running times. BioGSF emerges as an efficient framework for biomedical RE.
从文献中自动准确地提取各种生物医学关系是医学知识图谱的核心要素，而医学知识图谱对于医疗保健人工智能来说不可或缺。目前，通过在预训练语言模型（PLM）上堆叠各种神经网络进行微调，是解决生物医学关系提取（RE）问题的端到端通用框架。然而，基于序列的PLM在一定程度上未能充分利用语义之间的联系以及由这些联系形成的拓扑特征。在本研究中，我们提出了一种名为BioGSF的图驱动框架，用于通过利用图神经网络模型将最短依赖路径（SDP）与实体对图相结合，从文献中进行关系提取。首先，我们利用依赖关系来获取实体之间的SDP，并将此信息纳入实体对图中。随后，利用图注意力网络获取实体对图的拓扑信息。最后，将获得的拓扑信息与上下文信息的语义特征相结合进行关系分类。我们的方法在两个不同的数据集S4和BioRED上进行了评估。结果表明，BioGSF不仅在先前模型中表现优异，在S4数据集上的微F1分数为96.68%，在BioRED数据集上为96.03%，而且运行时间最短。BioGSF成为一种高效的生物医学关系提取框架。
