Proceedings chapter
Open access

Drug-protein relation extraction using ensemble of transformer-based language models

Presented at Online, November 8-10, 2021
First online date2021

Drug-protein interactions have become a crucial component to study potential side effects, discover new uses for existing drugs, to name a few applications. We describe our approach based on transformer-based language models to predict relations between chemical and gene entities in DrugProt corpus. Sliding window is used to detect the relation in a passage for the individual models, and then they are combined using majority vote. Our model achieved 60% of F1-score (88% of recall and 45% of precision) in the track 1: text mining drug and chemical- protein interactions at BioCreative VII. Ensemble of transformer-based language models provides a baseline performance for drug-protein interaction extraction

  • Transformers
  • Relation extraction
  • Ensemble
  • BERT
Citation (ISO format)
COPARA ZEA, Jenny Linet, TEODORO, Douglas. Drug-protein relation extraction using ensemble of transformer-based language models. In: Proceedings of the BioCreative VII Challenge Evaluation Workshop. Online. [s.l.] : [s.n.], 2021. p. 89–93.
Main files (1)
Proceedings chapter (Published version)
  • PID : unige:162727

Technical informations

Creation06/01/2022 8:30:00 PM
First validation06/01/2022 8:30:00 PM
Update time03/16/2023 7:11:14 AM
Status update03/16/2023 7:11:14 AM
Last indexation05/06/2024 11:22:05 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack