Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Leaky Scanning

Leaky Scanning

During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R...

Genomics

Genomics

Genomics is the science of genomes: it is the study of all the genetic material of an organism. In humans, the genome consists of information carried in 23 pairs of chromosomes in the nucleus, as well as mitochondrial DNA. In genomics, both coding and non-coding DNA is sequenced and analyzed. Genomics allows a better understanding of all living things, their evolution, and their diversity. It has a myriad of uses: for example, to build phylogenetic trees, to improve productivity and...

You might also read

Related Articles

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

Sort by

Same author

Knowledge Graph Augmented Large Language Models for Disease Prediction.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026

Same author

Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026

Same author

ClinNoteAgents: An LLM Multi-Agent System for Predicting and Interpreting Heart Failure 30-Day Readmission from Clinical Notes.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026

Same author

Clinical Evaluation of the Revised Biological and Clinical Staging Criteria for Alzheimer Disease in China.

Neurology·2026

Same author

Why Empirical Risk Minimization Performs Well for Open Set Domain Adaptation: A Theoretical Analysis From Causal View.

IEEE transactions on neural networks and learning systems·2026

Same author

First-principles multiscale modeling of cerebral hemodynamics enables personalized predictions of human brain temperature.

Scientific reports·2026

Same journal

BioSift: A Dataset for Filtering Biomedical Abstracts for Drug Repurposing and Clinical Meta-Analysis.

International ACM SIGIR Conference on Research and Development in Information Retrieval. Annual International ACMSIGIR Conference on Research & Development in Information Retrieval·2024

Same journal

HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting.

International ACM SIGIR Conference on Research and Development in Information Retrieval. Annual International ACMSIGIR Conference on Research & Development in Information Retrieval·2024

Same journal

Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training.

International ACM SIGIR Conference on Research and Development in Information Retrieval. Annual International ACMSIGIR Conference on Research & Development in Information Retrieval·2024

See all related articles

Search research articles

Related Experiment Video

Updated: May 25, 2025

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

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

Published on: December 6, 2024

PromptLink: Leveraging Large Language Models for Cross-Source Biomedical Concept Linking.

Yuzhang Xie¹, Jiaying Lu¹, Joyce Ho¹

¹Emory University, USA.

International ACM SIGIR Conference on Research and Development in Information Retrieval. Annual International ACMSIGIR Conference on Research & Development in Information Retrieval

|February 28, 2025

Summary

This summary is machine-generated.

PromptLink effectively links biomedical concepts across diverse data sources using large language models (LLMs). This novel framework enhances accuracy by prompting LLMs to utilize their knowledge and self-reflect on predictions.

Keywords:

Biomedical Concept Linking Few-Shot Prompting Large Language Models for Resource-Constrained Field Retrieve & Re-Rank

More Related Videos

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

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

Published on: October 13, 2023

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

Related Experiment Videos

Last Updated: May 25, 2025

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

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

Published on: December 6, 2024

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

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

Published on: October 13, 2023

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

Area of Science:

Biomedical Informatics
Natural Language Processing
Artificial Intelligence

Background:

Linking biomedical concepts across data sources is crucial for integrative analysis but hindered by naming discrepancies.
Existing methods (rule-based, thesauri, traditional ML) have limited generalizability and prior knowledge.
Large Language Models (LLMs) offer rich prior knowledge but face challenges like cost, context limits, and reliability.

Purpose of the Study:

To introduce PromptLink, a novel framework for biomedical concept linking that effectively leverages LLMs.
To address the limitations of existing concept linking methods by utilizing LLM capabilities.
To develop a generic and adaptable framework for concept linking across various data types.

Main Methods:

PromptLink employs a biomedical-specialized pre-trained model to generate LLM-compatible candidate concepts.
A two-stage prompting strategy is used with an LLM: first to elicit knowledge, then to enhance prediction reliability through self-reflection.
The framework is designed to be generic, requiring no additional prior knowledge, context, or training data.

Main Results:

PromptLink demonstrated effectiveness in concept linking tasks between electronic health record (EHR) datasets and a biomedical knowledge graph (KG).
The two-stage prompting approach significantly improved the reliability of LLM-based concept linking.
Empirical results validated the framework's ability to perform concept linking across diverse data sources.

Conclusions:

PromptLink offers a powerful and generic solution for biomedical concept linking, overcoming limitations of previous approaches.
Leveraging LLMs with a novel prompting strategy enhances the accuracy and reliability of cross-data source concept alignment.
The framework's adaptability makes it suitable for a wide range of biomedical data integration challenges.