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 on HEPTs by supervised stochastic resonance.

Weimin Guo1, Xiaofang Hu, Ningping Chu

  • 1School of Environmental Science and Technology, Shanghai Jiao Tong University, Shanghai 200240, PR China. wmguo@sjtu.edu.cn

Bioorganic & Medicinal Chemistry Letters
|April 1, 2006
PubMed
Summary

This study introduces supervised stochastic resonance (SSR) for quantitative structure-activity relationship (QSAR) analysis, improving model stability and prediction by treating errors as noise to enhance relevant molecular descriptors.

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

Quercetin attenuates peritoneal fibrosis by upregulating ferroptosis-related glutathione peroxidase 4 (GPX4) and solute carrier family 7 member 11 (SLC7A11) in MeT-5A and rat models: Supported by clinical mRNA expression data.

Peritoneal dialysis international : journal of the International Society for Peritoneal Dialysis·2026
Same author

Lifelong Consumption of Freeze-Dried Parabacteroides Distasonis Improves Gut Barrier Integrity and Extends Lifespan and Health Span in Drosophila Melanogaster.

Aging and disease·2026
Same author

Improving the Performance of Low-Carbon Ultra-High-Performance Concrete Through the Incorporation of Recycled Coarse Aggregate.

Materials (Basel, Switzerland)·2026
Same author

Discovery and characterization of a novel chromosomally encoded aminoglycoside <i>O</i>-nucleotidyltransferase gene, designated <i>ant(9)-Ie</i>, in a strain of <i>Providencia</i>.

Frontiers in cellular and infection microbiology·2026
Same author

Correction: Identification of avian polyomavirus and its pathogenicity to SPF chickens.

Frontiers in microbiology·2026
Same author

Restorative campus landscapes and student engagement: Dual affective pathways linking environmental perception to learning and social interaction.

Acta psychologica·2026

Area of Science:

  • Medicinal Chemistry
  • Computational Chemistry
  • Cheminformatics

Background:

  • Quantitative structure-activity relationship (QSAR) models are crucial for drug discovery.
  • Errors in physicochemical properties can significantly impact QSAR model accuracy and variable selection.
  • Existing QSAR methods often overlook errors-in-variables, limiting predictive power.

Purpose of the Study:

  • To introduce a novel approach, supervised stochastic resonance (SSR), for QSAR studies.
  • To address the challenge of errors-in-variables in QSAR model development.
  • To enhance the stability and predictivity of QSAR models for HEPT analogues.

Main Methods:

  • Developed and applied supervised stochastic resonance (SSR) based on stochastic resonance (SR) theory.

Related Experiment Videos

  • Treated experimental errors and abundant variables as noise, and relevant descriptors as signals.
  • Utilized nonlinear systems where signal and noise interact to enhance the signal.

    • Main Results:

    • SSR effectively improved the correlation between relevant molecular descriptors and HEPT analogue activity.
    • QSAR models developed using SSR demonstrated comparable stability and predictivity to existing methods.
    • The approach successfully enhanced the signal (relevant variables) amidst noise (errors and irrelevant variables).

    Conclusions:

    • Supervised stochastic resonance (SSR) is an efficient and promising new method for QSAR studies.
    • SSR offers a robust way to handle errors-in-variables, leading to improved QSAR model performance.
    • This technique holds potential for advancing drug design and discovery through more accurate predictive modeling.