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

Ligand Binding and Linkage00:49

Ligand Binding and Linkage

Allosteric proteins have more than one ligand binding site; the binding of a ligand to any of these sites influences the binding of ligands to the other sites. When a protein is allosteric, its binding sites are called coupled or linked.  In the case of enzymes, the site that binds to the substrate is known as the active site and the other site is known as the regulatory site. When a ligand binds to the regulatory site, this leads to conformational changes in the protein that can influence the...
Ligand Binding and Linkage00:49

Ligand Binding and Linkage

Allosteric proteins have more than one ligand binding site; the binding of a ligand to any of these sites influences the binding of ligands to the other sites. When a protein is allosteric, its binding sites are called coupled or linked.  In the case of enzymes, the site that binds to the substrate is known as the active site and the other site is known as the regulatory site. When a ligand binds to the regulatory site, this leads to conformational changes in the protein that can influence the...
Ligand Binding Sites02:40

Ligand Binding Sites

Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Transducer Mechanism: Enzyme-Linked Receptors01:27

Transducer Mechanism: Enzyme-Linked Receptors

Enzyme-linked receptors are cell-surface receptors acting as an enzyme or associating with an enzyme intracellularly. They make excellent drug targets. Drugs can bind to the extracellular ligand-binding domain or directly affect their enzymatic domain and alter their activity.
Major types that are helpful drug targets include:
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
lncRNA - Long Non-coding RNAs02:39

lncRNA - Long Non-coding RNAs

In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA (lncRNA)...

You might also read

Related Articles

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

Sort by
Same author

An acidophilic GH12 xyloglucanase from <i>Trichoderma asperellum</i> produces prebiotic oligosaccharides that promote probiotic growth.

Frontiers in nutrition·2026
Same author

Predicting survival in oral squamous cell carcinoma via integrated analysis of tumor budding and tertiary lymphoid structures.

Frontiers in oncology·2026
Same author

Imaging of two-dimensional ion-beam profiles using a scanning Faraday cup array combined with a 128-channel picoammeter system.

The Review of scientific instruments·2026
Same author

Acoustic measurement methods and spatiotemporal distribution patterns of microbubble spectra in water under artificial aeration conditions.

Ultrasonics·2026
Same author

Treatment options for long head of biceps tendon tenodesis.

Frontiers in surgery·2026
Same author

Guiding Fast Ion Beam by Suppressing Secondary Ions.

Physical review letters·2026

Related Experiment Video

Updated: Jul 16, 2026

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

BioRENLI: enhancing large language models for biomedical relation extraction through preference-aligned natural

Junliang Liu1, Ling Luo1, Dinghao Pan1

  • 1School of Computer Science and Technology, Dalian University of Technology, Dalian, 116023 Liaoning China.

Health Information Science and Systems
|July 15, 2026
PubMed
Summary

BioRENLI enhances biomedical relation extraction (RE) using preference-aligned natural language inference (NLI). This framework improves accuracy by training large language models (LLMs) to distinguish between correct and incorrect relation predictions.

Keywords:
Biomedical relation extractionDirect preference optimizationLarge language modelsNatural language inference

Related Experiment Videos

Last Updated: Jul 16, 2026

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

Area of Science:

  • Computational biology
  • Natural language processing
  • Biomedical informatics

Background:

  • Biomedical relation extraction (RE) identifies relationships between entities in biomedical texts.
  • Current RE methods using text classification struggle to leverage large language models (LLMs).
  • Directly fine-tuning LLMs for RE leads to confusion between similar relation types and unsupported predictions.

Purpose of the Study:

  • To propose BioRENLI, a novel LLM-based framework for biomedical RE.
  • To address limitations of existing RE approaches, including LLM underutilization and label ambiguity.
  • To improve the accuracy and reliability of biomedical relation extraction.

Main Methods:

  • BioRENLI reformulates RE as a natural language inference (NLI) task.
  • Candidate relations are converted into natural language hypotheses for NLI prediction (Entailment/Contradiction).
  • Direct Preference Optimization (DPO) is used to mitigate label ambiguity by preferring correct NLI decisions.

Main Results:

  • BioRENLI significantly outperforms supervised fine-tuned LLM variants on ChemProt and DDI datasets.
  • The framework shows consistent improvements in both full-supervision and low-resource settings.
  • BioRENLI remains competitive with established BERT-based baselines.

Conclusions:

  • BioRENLI effectively enhances biomedical RE by integrating preference-aligned NLI with LLMs.
  • The proposed method successfully reduces unsupported entailment predictions and improves relation classification accuracy.
  • This approach offers a promising direction for advancing automated biomedical knowledge discovery.