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

Virtual screening of molecular databases using a support vector machine.

Robert N Jorissen1, Michael K Gilson

  • 1Center for Advanced Research in Biotechnology, University of Maryland Biotechnology Institute, 9600 Gudelsky Drive, Rockville, Maryland 20850, USA.

Journal of Chemical Information and Modeling
|June 1, 2005
PubMed
Summary
This summary is machine-generated.

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

Microbiology testing around the time of antibiotic initiation among residents of long-term care facilities.

The Journal of antimicrobial chemotherapy·2026
Same author

Quantifying Spatially Resolved Hydration Thermodynamics Using Grid Inhomogeneous Solvation Theory [Article v1.0].

Living journal of computational molecular science·2026
Same author

Reporting aged care quality data monthly, quarterly, or annually? A cross-sectional study of 349 613 residents and 2803 long-term care facilities.

International journal for quality in health care : journal of the International Society for Quality in Health Care·2026
Same author

Structure-Based Experimental Datasets for Benchmarking Protein Simulation Force Fields [Article v1.0].

Living journal of computational molecular science·2026
Same author

Transitions of Care Among Older People Entering Residential Aged Care Homes.

Australasian journal on ageing·2025
Same author

Relative BAT: An Automated Tool for Relative Binding Free Energy Calculations by the Separated Topologies Approach.

Journal of chemical information and modeling·2025

This study enhances virtual screening using a modified Support Vector Machine (SVM) algorithm. The novel approach effectively enriches active compounds with new chemical structures.

Area of Science:

  • Computational chemistry and cheminformatics
  • Machine learning applications in drug discovery

Background:

  • Support Vector Machine (SVM) is a powerful classification algorithm with strong generalization capabilities.
  • Virtual screening is crucial for identifying molecules with desired biological activity.
  • Traditional SVM applications focus on classification, not necessarily enrichment of active compounds.

Purpose of the Study:

  • To adapt the SVM algorithm for enhanced virtual screening, focusing on enriching active molecules.
  • To develop a novel method for ranking molecules based on predicted activity.
  • To compare the effectiveness of the modified SVM against existing binary fingerprint-based methods.

Main Methods:

  • Application of a modified Support Vector Machine (SVM) algorithm for molecule ranking.

Related Experiment Videos

  • Development of a simple and novel criterion for selecting molecular descriptors.
  • Utilization of cross-validation for optimizing SVM parameters.
  • Comparison with binary fingerprint-based methods like binary kernel discrimination.

    • Main Results:

    • The modified SVM approach prioritizes enrichment of active compounds over simple classification.
    • The method demonstrates superior effectiveness in identifying active compounds with novel chemical scaffolds.
    • The criterion for molecular descriptor selection is both simple and effective.

    Conclusions:

    • The modified SVM method offers a more effective strategy for virtual screening enrichment.
    • This approach can identify novel active compounds that might be missed by traditional methods.
    • The study highlights the potential of tailored SVM applications in drug discovery pipelines.