BioEGRE: a linguistic topology enhanced method for biomedical relation extraction based on BioELECTRA and graph pointer neural network

• Published in: BMC bioinformatics 2023-12, Vol.24 (1), p.486-486, Article 486
• Main Authors: Zheng, Xiangwen, Wang, Xuanze, Luo, Xiaowei, Tong, Fan, Zhao, Dongsheng
• Format: Article
• Language: English
• Subjects: Analysis; Artificial neural networks; BioELECTRA; Biomedical relation extraction; Computational linguistics; CT imaging; Data mining; Deep learning; Evaluation; Graph pointer neural network; Graphs; Information management; Knowledge; Language; Language processing; Linguistics; Medical research; Medicine, Experimental; Methods; Natural language interfaces; Network topologies; Neural networks; Performance enhancement; Performance evaluation; Representations; SciSpaCy; Semantics; Sentences; Syntax; Text mining; Topological features; Topology
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-023-05601-9

Automatic and accurate extraction of diverse biomedical relations from literature is a crucial component of bio-medical text mining. Currently, stacking various classification networks on pre-trained language models to perform fine-tuning is a common framework to end-to-end solve the biomedical relation extraction (BioRE) problem. However, the sequence-based pre-trained language models underutilize the graphical topology of language to some extent. In addition, sequence-oriented deep neural networks have limitations in processing graphical features. In this paper, we propose a novel method for sentence-level BioRE task, BioEGRE (BioELECTRA and Graph pointer neural net-work for Relation Extraction), aimed at leveraging the linguistic topological features. First, the biomedical literature is preprocessed to retain sentences involving pre-defined entity pairs. Secondly, SciSpaCy is employed to conduct dependency parsing; sentences are modeled as graphs based on the parsing results; BioELECTRA is utilized to generate token-level representations, which are modeled as attributes of nodes in the sentence graphs; a graph pointer neural network layer is employed to select the most relevant multi-hop neighbors to optimize representations; a fully-connected neural network layer is employed to generate the sentence-level representation. Finally, the Softmax function is employed to calculate the probabilities. Our proposed method is evaluated on three BioRE tasks: a multi-class (CHEMPROT) and two binary tasks (GAD and EU-ADR). The results show that our method achieves F1-scores of 79.97% (CHEMPROT), 83.31% (GAD), and 83.51% (EU-ADR), surpassing the performance of existing state-of-the-art models. The experimental results on 3 biomedical benchmark datasets demonstrate the effectiveness and generalization of BioEGRE, which indicates that linguistic topology and a graph pointer neural network layer explicitly improve performance for BioRE tasks.