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

You might also read

Related Articles

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

Sort by
Same author

Evaluating the Impact of Blood-Brain Barrier-Penetrant ACE Inhibitors on HIV-Associated Neurocognitive Disorders.

Journal of acquired immune deficiency syndromes (1999)·2026
Same author

AI-based mining of biomedical literature: Applications for drug repurposing for the treatment of dementia.

Artificial intelligence in medicine·2025
Same author

Exposure to angiotensin-converting enzyme inhibitors that cross the blood-brain barrier and the risk of dementia among people with HIV.

AIDS (London, England)·2024
Same author

AI-based mining of biomedical literature: Applications for drug repurposing for the treatment of dementia.

Research square·2024
Same author

AI-based mining of biomedical literature: Applications for drug repurposing for the treatment of dementia.

bioRxiv : the preprint server for biology·2024
Same author

Exposure to angiotensin-converting enzyme inhibitors that cross the blood-brain barrier and the risk of dementia among patients with human immunodeficiency virus.

medRxiv : the preprint server for health sciences·2024

Related Experiment Video

Updated: Jun 24, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K

Dyport: dynamic importance-based biomedical hypothesis generation benchmarking technique.

Ilya Tyagin1, Ilya Safro2

  • 1Center for Bioinformatics and Computational Biology, University of Delaware, Newark, DE, 19713, USA. tyagin@udel.edu.

BMC Bioinformatics
|June 13, 2024
PubMed
Summary
This summary is machine-generated.

A new framework called Dyport evaluates biomedical hypothesis generation systems. It assesses hypothesis accuracy and potential impact, addressing a key challenge in automated scientific discovery.

Keywords:
BenchmarkingHypothesis GenerationLink PredictionLiterature-based DiscoveryNatural Language Processing

More Related Videos

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila
00:06

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

Published on: August 20, 2019

13.6K
In Vivo Modeling of the Morbid Human Genome using Danio rerio
12:31

In Vivo Modeling of the Morbid Human Genome using Danio rerio

Published on: August 24, 2013

20.7K

Related Experiment Videos

Last Updated: Jun 24, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K
In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila
00:06

In Vivo Functional Study of Disease-associated Rare Human Variants Using Drosophila

Published on: August 20, 2019

13.6K
In Vivo Modeling of the Morbid Human Genome using Danio rerio
12:31

In Vivo Modeling of the Morbid Human Genome using Danio rerio

Published on: August 24, 2013

20.7K

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Artificial Intelligence in Medicine

Background:

  • Automated hypothesis generation (HG) leverages machine learning to find hidden connections in public data.
  • Evaluating HG systems at scale remains a significant challenge in the field.
  • The need for robust evaluation methods is critical for advancing AI-driven biomedical research.

Purpose of the Study:

  • To introduce Dyport, a novel benchmarking framework for evaluating biomedical hypothesis generation systems.
  • To address the limitations of current evaluation methods by incorporating knowledge dynamics, semantics, and impact.
  • To provide a flexible and scalable solution for verifying the quality of HG systems.

Main Methods:

  • Developed Dyport, a benchmarking framework utilizing curated datasets for realistic system testing.
  • Integrated biomedical knowledge into a dynamic graph structure.
  • Implemented a method to quantify the importance and potential impact of generated hypotheses, extending traditional link prediction benchmarks.

Main Results:

  • Demonstrated the applicability of Dyport on various link prediction systems using biomedical semantic knowledge graphs.
  • Showcased Dyport's ability to evaluate not only hypothesis accuracy but also their potential biomedical research impact.
  • Validated the framework's effectiveness in assessing HG systems under realistic conditions.

Conclusions:

  • Dyport offers an open-source solution for evaluating biomedical hypothesis generation systems.
  • The framework considers knowledge dynamics, semantics, and impact for comprehensive assessment.
  • Dyport aims to enhance the scope of scientific discovery by improving HG system verification.