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

Neural networks applied to quantitative structure-activity relationship analysis.

T Aoyama1, Y Suzuki, H Ichikawa

  • 1Hitachi Computer Engineering Co. Ltd., Kanagawa, Japan.

Journal of Medicinal Chemistry
|September 1, 1990
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

Osteopontin-immunoreactive primary sensory neurons in the rat spinal and trigeminal nervous systems.

Brain research·2000
Same author

The significance of atherogenic indices in patients on hemodialysis.

American journal of nephrology·2000
Same author

Effect of vitamin E on aspirin-induced gastric mucosal injury in rats.

Digestive diseases and sciences·2000
Same author

Biodistribution of gadolinium incorporated in lipid emulsions intraperitoneally administered for neutron-capture therapy with tumor-bearing hamsters.

Biological & pharmaceutical bulletin·2000
Same author

The effect of neonatal capsaicin on the c-Fos-like immunoreactivity induced in subnucleus oralis neurons by noxious intraoral stimulation.

Brain research·2000
Same author

Endothelial cells exposed to anoxia/reoxygenation are hyperadhesive to T-lymphocytes: kinetics and molecular mechanisms.

Microcirculation (New York, N.Y. : 1994)·2000

Neural networks offer a powerful new approach for quantitative structure-activity relationship (QSAR) analysis, outperforming traditional linear methods. This study demonstrates their potential for routine QSAR work.

Area of Science:

  • * Computational Chemistry
  • * Cheminformatics
  • * Machine Learning

Background:

  • * Quantitative Structure-Activity Relationship (QSAR) analysis is crucial for drug discovery and chemical research.
  • * Traditional linear methods like multiregression have limitations in capturing complex relationships.
  • * Exploring advanced computational techniques is essential for improving QSAR model accuracy.

Purpose of the Study:

  • * To investigate the application of neural networks in QSAR analysis.
  • * To compare the performance of neural networks against linear multiregression analysis.
  • * To elucidate the mathematical underpinnings of neural network operations in QSAR.

Main Methods:

  • * Development and application of a neural network model for QSAR.

Related Experiment Videos

  • * Comparative analysis using linear multiregression as a benchmark.
  • * Mathematical description of the operational relationship between neural networks and multiregression.

    • Main Results:

    • * Neural networks demonstrate significant potential as a tool for routine QSAR analysis.
    • * The study found that neural networks can surpass the performance of linear multiregression.
    • * Mathematical relationships between the two methods were successfully described.

    Conclusions:

    • * Neural networks represent a viable and advanced alternative to traditional QSAR methods.
    • * The findings suggest that neural networks can enhance the predictive power and scope of QSAR studies.
    • * This work supports the integration of neural networks into standard QSAR workflows.