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 Experiment Videos

Non-Negative Matrix Factorization for Drug Repositioning: Experiments with the repoDB Dataset.

Gokhan Bakal1, Halil Kilicoglu2, Ramakanth Kavuluru1

  • 1University of Kentucky, Lexington, KY.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|April 21, 2020
PubMed
Summary

This study introduces a novel computational drug repositioning approach using non-negative matrix factorization (NMF) to identify new drug-disease indications. The method achieves high recall and precision on the repoDB benchmark dataset.

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

Goals and strategies for the indexing of publication types and study designs.

Database : the journal of biological databases and curation·2026
Same author

SPIRIT-CONSORT-ELM: Element-Level Assessment of Randomized Controlled Trial Reporting Using Large Language Models.

medRxiv : the preprint server for health sciences·2026
Same author

Study Design Indexing in Transition: A Focused Comparison of manual NLM Indexing vs. Transformer-based Automated Models.

medRxiv : the preprint server for health sciences·2026
Same author

Advancing Whole-Person Health through Informatics: A Narrative Review of Knowledge Resources for Complementary and Integrative Health.

The Journal of nutrition·2026
Same author

Relation Extraction with Instance-Adapted Predicate Descriptions.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same author

Knowledge-Driven Cross-Document Relation Extraction.

Findings of ACL. ACL·2026

Area of Science:

  • Computational biology
  • Pharmacology
  • Bioinformatics

Background:

  • Drug repositioning leverages existing drugs for new therapeutic indications, driven by data availability.
  • A key challenge is the lack of realistic negative datasets for benchmarking drug-disease associations.
  • The repoDB dataset was created to address this gap, using FDA approvals and failed trials.

Purpose of the Study:

  • To present the first drug repositioning effort directly testing against the repoDB dataset.
  • To evaluate the efficacy of non-negative matrix factorization (NMF) for recovering known drug-disease indications.

Main Methods:

  • Utilized hand-curated drug-disease indications from the Unified Medical Language System (UMLS) Metathesaurus.
  • Employed automatically extracted relations from the SemMedDB database.

Related Experiment Videos

  • Applied non-negative matrix factorization (NMF) for matrix completion and hypothesis generation.

    • Main Results:

    • Achieved 96% recall and 80% precision in recovering known drug-disease indications from repoDB.
    • Demonstrated the effectiveness of NMF in identifying drug-disease pairs.

    Conclusions:

    • Computational methods, particularly NMF, can effectively exploit curated knowledge for drug repositioning.
    • Hand-curated knowledge bases and matrix completion techniques show promise for generating novel therapeutic hypotheses.