التفاصيل البيبلوغرافية
العنوان: |
Extracting Drug-Protein Relation from Literature Using Ensembles of Biomedical Transformers. |
المؤلفون: |
Das A; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Li Z; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Wei Q; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Li J; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Huang LC; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Hu Y; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Li R; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Zheng WJ; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston., Xu H; School of Biomedical Informatics, University of Texas Health Science Center at Houston; Yale University; Melax Technologies, Houston. |
المصدر: |
Studies in health technology and informatics [Stud Health Technol Inform] 2024 Jan 25; Vol. 310, pp. 639-643. |
نوع المنشور: |
Journal Article |
اللغة: |
English |
بيانات الدورية: |
Publisher: IOS Press Country of Publication: Netherlands NLM ID: 9214582 Publication Model: Print Cited Medium: Internet ISSN: 1879-8365 (Electronic) Linking ISSN: 09269630 NLM ISO Abbreviation: Stud Health Technol Inform |
أسماء مطبوعة: |
Original Publication: Amsterdam ; Washington, DC : IOS Press, 1991- |
مواضيع طبية MeSH: |
Electric Power Supplies* , Knowledge Bases*, PubMed |
مستخلص: |
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. |
فهرسة مساهمة: |
Keywords: BERT; Deep Learning; Drug-protein relation extraction; Ensemble Learning; Pubmed abstracts |
تواريخ الأحداث: |
Date Created: 20240125 Date Completed: 20240126 Latest Revision: 20240126 |
رمز التحديث: |
20240126 |
DOI: |
10.3233/SHTI231043 |
PMID: |
38269887 |
قاعدة البيانات: |
MEDLINE |