RegulaTome: a corpus of typed, directed, and signed relations between biomedical entities in the scientific literature
Database · 2024
DOI: 10.1093/database/baae095 ↗Kurz gefasst
Fachartikel in der Zeitschrift Database, 2024. Verfasst von Katerina Nastou und 5 weiteren Autor:innen. Beteiligte Einrichtung: Novo Nordisk Foundation Center for Protein Research, University of Copenhagen, Blegdamsvej 3, Copenhagen 2200, Denmark. Hauptthemen laut MEDLINE: Data Mining. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 Marie Sklodowska-Curie Actions, Research Council of Finland, Novo Nordisk Fonden.
Abstract (Originalsprache)
In the field of biomedical text mining, the ability to extract relations from the literature is crucial for advancing both theoretical research and practical applications. There is a notable shortage of corpora designed to enhance the extraction of multiple types of relations, particularly focusing on proteins and protein-containing entities such as complexes and families, as well as chemicals. In this work, we present RegulaTome, a corpus that overcomes the limitations of several existing biomedical relation extraction (RE) corpora, many of which concentrate on single-type relations at the sentence level. RegulaTome stands out by offering 16 961 relations annotated in >2500 documents, making it the most extensive dataset of its kind to date. This corpus is specifically designed to cover a broader spectrum of >40 relation types beyond those traditionally explored, setting a new benchmark in the complexity and depth of biomedical RE tasks. Our corpus both broadens the scope of detected relations and allows for achieving noteworthy accuracy in RE. A transformer-based model trained on this corpus has demonstrated a promising F1-score (66.6%) for a task of this complexity, underscoring the effectiveness of our approach in accurately identifying and categorizing a wide array of biological relations. This achievement highlights RegulaTome’s potential to significantly contribute to the development of more sophisticated, efficient, and accurate RE systems to tackle biomedical tasks. Finally, a run of the trained RE system on all PubMed abstracts and PMC Open Access full-text documents resulted in >18 million relations, extracted from the entire biomedical literature.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Novo Nordisk Foundation Center for Protein Research, University of Copenhagen, Blegdamsvej 3, Copenhagen 2200, Denmark.
- TurkuNLP Group, Department of Computing, University of Turku, Vesilinnantie 5, Turku 20014, Finland.
- Textimi, 1-37-13 Kitazawa, Tokyo, Setagaya-ku 155-0031, Japan.
ORCID-Profile: Katerina Nastou, Farrokh Mehryary
Förderung
- H2020 Marie Sklodowska-Curie Actions
- Research Council of Finland
- Novo Nordisk Fonden
Zitieren
APA
Nastou, K., Mehryary, F., Ohta, T., Luoma, J., Pyysalo, S., & Jensen, L. J. (2024). RegulaTome: a corpus of typed, directed, and signed relations between biomedical entities in the scientific literature. Database. https://doi.org/10.1093/database/baae095
Vancouver
Nastou K, Mehryary F, Ohta T, Luoma J, Pyysalo S, Jensen LJ. RegulaTome: a corpus of typed, directed, and signed relations between biomedical entities in the scientific literature. Database. 2024. doi:10.1093/database/baae095
BibTeX
@article{Nastou2024,
author = {Nastou, Katerina and Mehryary, Farrokh and Ohta, Tomoko and Luoma, Jouni and Pyysalo, Sampo and Jensen, Lars Juhl},
title = {RegulaTome: a corpus of typed, directed, and signed relations between biomedical entities in the scientific literature},
journal = {Database},
year = {2024},
doi = {10.1093/database/baae095}
}
EUVIMED