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

A comparison of methods for modeling quantitative structure-activity relationships.

Jeffrey J Sutherland1, Lee A O'Brien, Donald F Weaver

  • 1Department of Chemistry, Queen's University, Kingston, Ontario K7L 3N6, Canada.

Journal of Medicinal Chemistry
|October 16, 2004
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

Computational Insights into the Antiviral Properties of the Antimicrobial Peptide β-Amyloid.

The journal of physical chemistry. B·2026
Same author

β-Alanine Is an Unexploited Neurotransmitter in the Pathogenesis and Treatment of Alzheimer's Disease.

NeuroSci·2026
Same author

The Cause-and-Consequence Relationships between Domestic Abuse and Alzheimer's Disease: Identification of Five Subtypes.

Current Alzheimer research·2026
Same author

Dementia Care Research and Psychosocial Factors.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same author

Basic Science and Pathogenesis.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same author

Marketing Science: A Missing Piece in the Fight Against Alzheimer's.

The Canadian journal of neurological sciences. Le journal canadien des sciences neurologiques·2025

Quantitative structure-activity relationship (QSAR) models were compared for drug discovery. HQSAR models performed comparably to CoMFA and CoMSIA, highlighting the importance of designed test sets for accurate predictive assessment.

Area of Science:

  • Computational chemistry
  • Medicinal chemistry
  • Drug discovery

Background:

  • Quantitative structure-activity relationship (QSAR) modeling is crucial for predicting drug efficacy.
  • Numerous QSAR methods exist, necessitating comparative studies for optimal model selection.
  • Assessing predictive accuracy requires robust validation strategies.

Purpose of the Study:

  • To evaluate and compare the predictive accuracy of various QSAR modeling techniques.
  • To assess the performance of different descriptor sets and algorithms across diverse biological targets.
  • To emphasize the importance of designed test sets for reliable QSAR model validation.

Main Methods:

  • Comparative analysis of QSAR methods including CoMFA, CoMSIA, EVA, HQSAR, and partial least squares (PLS).

Related Experiment Videos

  • Utilization of 2D, 2.5D, and 3D descriptors derived from molecular structures and charges.
  • Application of genetic function approximation, genetic PLS, and back-propagation neural networks.
  • Validation using designed test sets to assess predictive accuracy.

    • Main Results:

    • HQSAR models demonstrated comparable predictive performance to CoMFA and CoMSIA across multiple datasets.
    • Traditional 2D and 2.5D descriptors, when used with PLS, generally showed lower predictive accuracy.
    • Neural network ensembles utilizing 2.5D descriptors matched or exceeded the predictive power of PLS models.
    • Cross-validation estimates of interpolative accuracy often corresponded well, but test set accuracy revealed discrepancies.

    Conclusions:

    • HQSAR is a competitive QSAR modeling technique.
    • The choice of descriptors and modeling algorithms significantly impacts predictive accuracy.
    • Designed test sets are essential for a realistic evaluation of QSAR model generalizability and predictive power.