EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing biomedical relation extraction with directionality

Po-Ting Lai iD, Chih-Hsuan Wei iD, Shubo Tian iD, Robert Leaman iD, Zhiyong Lu iD

Bioinformatics · 01.07.2025 · 41 (Supplement_1) · i68-i76

DOI: 10.1093/bioinformatics/btaf226 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.07.2025. Verfasst von Po-Ting Lai und 4 weiteren Autor:innen. Beteiligte Einrichtung: National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, United States. Hauptthemen laut MEDLINE: Computational Biology, Data Mining. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, NLM NIH HHS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Summary Biological relation networks contain rich information for understanding the biological mechanisms behind the relationship of entities such as genes, proteins, diseases, and chemicals. The vast growth of biomedical literature poses significant challenges in updating the network knowledge. The recent Biomedical Relation Extraction Dataset (BioRED) provides valuable manual annotations, facilitating the development of machine learning and pre-trained language model approaches for automatically identifying novel document-level (inter-sentence context) relationships. Nonetheless, its annotations lack directionality (subject/object) for the entity roles, which is essential for studying complex biological networks. Herein, we annotate the entity roles of the relationships in the BioRED corpus and subsequently propose a novel multi-task language model with soft-prompt learning to jointly identify the relationship, novel findings, and entity roles. Our results include an enriched BioRED corpus with 10 864 directionality annotations. Moreover, our proposed method outperforms existing large language models, such as the state-of-the-art GPT-4 and Llama-3, on two benchmarking tasks. Availability and implementation Our source code and dataset are available at https://github.com/ncbi-nlp/BioREDirect.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyData MiningMachine LearningNatural Language ProcessingHumansDatabases, FactualAlgorithms

Autor:innen und Institutionen

  • National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, United States.

ORCID-Profile: Po-Ting Lai, Chih-Hsuan Wei, Shubo Tian, Robert Leaman, Zhiyong Lu

Förderung

  • NHLBI NIH HHS
  • NLM NIH HHS
  • NIH HHS
  • Division of Intramural Research
  • National Library of Medicine
  • National Institutes of Health

Zitieren

APA

Lai, P. T., Wei, C. H., Tian, S., Leaman, R., & Lu, Z. (2025). Enhancing biomedical relation extraction with directionality. Bioinformatics, 41(Supplement_1), i68-i76. https://doi.org/10.1093/bioinformatics/btaf226

Vancouver

Lai PT, Wei CH, Tian S, Leaman R, Lu Z. Enhancing biomedical relation extraction with directionality. Bioinformatics. 2025;41(Supplement_1):i68-i76. doi:10.1093/bioinformatics/btaf226

BibTeX
@article{Lai2025,
  author = {Lai, Po-Ting and Wei, Chih-Hsuan and Tian, Shubo and Leaman, Robert and Lu, Zhiyong},
  title = {Enhancing biomedical relation extraction with directionality},
  journal = {Bioinformatics},
  year = {2025},
  volume = {41},
  number = {Supplement_1},
  pages = {i68--i76},
  doi = {10.1093/bioinformatics/btaf226}
}
Kostenlos starten →