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

Comparison of ranking methods for virtual screening in lead-discovery programs.

David Wilton1, Peter Willett, Kevin Lawson

  • 1Krebs Institute for Biomolecular Research and Department of Information Studies, University of Sheffield, Sheffield S10 2TN, UK. d.j.wilton@sheffield.ac.uk

Journal of Chemical Information and Computer Sciences
|March 26, 2003
PubMed
Summary

Rank-based virtual screening methods help prioritize compounds in drug discovery. Binary kernel discrimination showed the best performance for prioritizing active molecules in screening applications.

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

Searching chemical databases in the pre-history of cheminformatics.

Journal of cheminformatics·2024
Same author

Scholarly communication between health informatics and information systems: A bibliometric study.

Health informatics journal·2024
Same author

Outcome of the Wagner Cone femoral component for difficult anatomical conditions during total hip arthroplasty.

International orthopaedics·2022
Same author

A bibliometric analysis of the Journal of Molecular Graphics and Modelling: An update.

Journal of molecular graphics & modelling·2022
Same author

Commentary: the first twelve years of the Journal of chemoinformatics.

Journal of cheminformatics·2022
Same author

Anatomy, Classification, and Management of Ankle Fractures Involving the Posterior Malleolar Fragment: A Literature Review.

Foot & ankle orthopaedics·2022

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Drug discovery

Background:

  • Lead discovery programs require efficient methods for prioritizing compounds.
  • Virtual screening methods are crucial for identifying potential drug candidates.
  • Availability of structural and bioactivity data is key for training screening models.

Purpose of the Study:

  • To evaluate several rank-based virtual screening methods for compound prioritization.
  • To compare the effectiveness of different molecular representations and analysis techniques.
  • To identify the most promising method for chemical screening applications.

Main Methods:

  • Utilized fragment bit-string and high-level molecular features for compound representation.
  • Applied methods including binary kernel discrimination, similarity searching, substructural analysis, support vector machine, and trend vector analysis.

Related Experiment Videos

  • Assessed method performance by the degree of clustering of active test set molecules.

    • Main Results:

    • Binary kernel discrimination consistently produced superior rankings compared to other methods.
    • The tested methods were applied to NCI AIDS and Syngenta corporate databases.
    • Effectiveness was measured by the position of active compounds in the ranked lists.

    Conclusions:

    • Binary kernel discrimination is a highly effective method for virtual screening.
    • This approach shows significant potential for applications in chemical screening and lead discovery.
    • Rank-based methods, particularly binary kernel discrimination, can enhance the efficiency of drug discovery programs.