Extracting Drug-Protein Relation from Literature Using Ensembles of Biomedical Transformers

• Published in: Studies in health technology and informatics Vol. 310; p. 639
• Main Authors: Das, Avisha, Li, Zhao, Wei, Qiang, Li, Jianfu, Huang, Liang-Chin, Hu, Yan, Li, Rongbin, Zheng, Wenjin Jim, Xu, Hua
• Format: Journal Article
• Language: English
• Published: Netherlands 25.01.2024
• Subjects: Electric Power Supplies; Knowledge Bases; PubMed; Ensemble Learning; BERT; Drug-protein relation extraction; Pubmed abstracts; Deep Learning
• ISSN: 1879-8365
• DOI: 10.3233/SHTI231043

Automatic extraction of relations between drugs/chemicals and proteins from ever-growing biomedical literature is required to build up-to-date knowledge bases in biomedicine. To promote the development of automated methods, BioCreative-VII organized a shared task - the DrugProt track, to recognize drug-protein entity relations from PubMed abstracts. We participated in the shared task and leveraged deep learning-based transformer models pre-trained on biomedical data to build ensemble approaches to automatically extract drug-protein relation from biomedical literature. On the main corpora of 10,750 abstracts, our best system obtained an F1-score of 77.60% (ranked 4th among 30 participating teams), and on the large-scale corpus of 2.4M documents, our system achieved micro-averaged F1-score of 77.32% (ranked 2nd among 9 system submissions). This demonstrates the effectiveness of domain-specific transformer models and ensemble approaches for automatic relation extraction from biomedical literature.