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

Quantitative structure-activity relationship studies using Gaussian processes.

F R Burden1

  • 1School of Chemistry, Monash University, Victoria 3800, Australia. frank.burden@sci.monash.edu.au

Journal of Chemical Information and Computer Sciences
|June 21, 2001
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

Modelling and predicting the biological effects of nanomaterials.

SAR and QSAR in environmental research·2014
Same author

A quantitative structure--activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks.

Chemical research in toxicology·2000
Same author

Use of automatic relevance determination in QSAR studies using Bayesian neural networks.

Journal of chemical information and computer sciences·2000
Same author

Robust QSAR models using Bayesian regularized neural networks.

Journal of medicinal chemistry·1999
Same author

Cross-validatory selection of test and validation sets in multivariate calibration and neural networks as applied to spectroscopy.

The Analyst·1998
Same author

Holographic neural networks as nonlinear discriminants for chemical applications.

Journal of chemical information and computer sciences·1998
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
See all related articles

A novel Gaussian process method (GPM) simplifies quantitative structure-activity relationship (QSAR) modeling by requiring no input parameters and only one hyperparameter for optimal solutions. This approach is demonstrated on receptor binding and toxicity datasets.

Area of Science:

  • Computational Chemistry
  • cheminformatics
  • Machine Learning

Background:

  • Quantitative Structure-Activity Relationship (QSAR) modeling is crucial for drug discovery and toxicology.
  • Traditional QSAR methods often require extensive parameterization and complex optimization.
  • There is a need for more efficient and user-friendly QSAR modeling techniques.

Purpose of the Study:

  • To introduce and apply a Gaussian Process Method (GPM) for QSAR model development.
  • To demonstrate the GPM's ability to overcome common challenges in QSAR modeling.
  • To showcase the GPM's utility across diverse biological and chemical datasets.

Main Methods:

  • Development and implementation of a Gaussian Process Method (GPM).
  • Application of GPM to generate QSAR models without requiring input parameters.

Related Experiment Videos

  • Utilizing a single hyperparameter for optimal solution finding.

    • Main Results:

    • The GPM successfully generated QSAR models for compound activity at benzodiazepine and muscarinic receptors.
    • The GPM was also applied to a dataset of substituted benzene toxicity in Tetrahymena Pyriformis.
    • The method demonstrated potential for simplifying QSAR model production.

    Conclusions:

    • Gaussian Process Method (GPM) offers a simplified and effective approach to QSAR modeling.
    • The GPM's parameter-free nature and single hyperparameter make it advantageous.
    • This method shows promise for broad applications in chemical and biological research.