Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Multi-pass Transmembrane Proteins and β-barrels01:09

Multi-pass Transmembrane Proteins and β-barrels

5.3K
In multi-pass transmembrane proteins, the polypeptide chain crosses the membrane more than once. The transmembrane polypeptide chain either forms an α-helix or β-strand structure. α-Helix containing multi-pass transmembrane proteins are ubiquitous, whereas β-strand containing ones are mainly found in gram-negative bacteria, mitochondria, and chloroplasts.
α-Helix containing multi-pass transmembrane proteins
Multi-pass transmembrane proteins such as...
5.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Named Entity Recognition in Chinese Clinical Text Using Deep Neural Network.

Studies in health technology and informatics·2015
Same author

Treatment of gummy smile: Nasal septum dysplasia as etiologic factor and therapeutic target.

Journal of plastic, reconstructive & aesthetic surgery : JPRAS·2015
Same author

Mesoporous TiO2/Zn2Ti3O8 hybrid films synthesized by polymeric micelle assembly.

Chemical communications (Cambridge, England)·2015
Same author

Inhibition of HIV Expression and Integration in Macrophages by Methylglyoxal-Bis-Guanylhydrazone.

Journal of virology·2015
Same author

Ease of adoption of clinical natural language processing software: An evaluation of five systems.

Journal of biomedical informatics·2015
Same author

Identifying risk factors for heart disease over time: Overview of 2014 i2b2/UTHealth shared task Track 2.

Journal of biomedical informatics·2015

Related Experiment Video

Updated: Jun 24, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

692

A Study of Biomedical Relation Extraction Using GPT Models.

Jeffrey Zhang1, Maxwell Wibert1, Huixue Zhou2

  • 1Section for Biomedical Informatics and Data Science, School of Medicine, Yale University, New Haven, USA.

AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science
|June 3, 2024
PubMed
Summary

Large language models like GPT-4 show promise for biomedical relation extraction (RE), achieving high F1-scores. Performance is comparable to BioBERT and PubMedBERT in some cases.

Keywords:
GPT-3.5-turboGPT-4Prompt engineeringgenerative pre-trained transformerrelation extraction

More Related Videos

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

544

Related Experiment Videos

Last Updated: Jun 24, 2025

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

692
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

544

Area of Science:

  • Biomedical Natural Language Processing
  • Artificial Intelligence in Healthcare

Background:

  • Relation Extraction (RE) is crucial for understanding biomedical knowledge.
  • Large Language Models (LLMs) are increasingly used for NLP tasks.

Purpose of the Study:

  • To evaluate GPT-3.5-turbo and GPT-4 for biomedical relation extraction.
  • To compare performance across different dataset versions (masked, unmasked, and expanded abbreviations).

Main Methods:

  • Utilized GPT-3.5-turbo and GPT-4 via chat completion API.
  • Experimented with three versions of EU-ADR, GAD, and ChemProt datasets.
  • Developed specific prompts tailored to each dataset version.

Main Results:

  • GPT-3.5-turbo achieved F1-scores ranging from 0.498 to 0.809.
  • GPT-4 reached a highest F1-score of 0.84.
  • Performance of LLMs was comparable to BioBERT and PubMedBERT in certain experimental setups.

Conclusions:

  • GPT-4 demonstrates strong capabilities in biomedical relation extraction.
  • The prompt engineering and dataset variations influenced model performance.
  • LLMs offer a competitive alternative for RE tasks in the biomedical domain.