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

Novel method for the display of multivariate data using neural networks.

D J Livingstone1, G Hesketh, D Clayworth

  • 1SmithKline Beecham Pharmaceuticals, The Frythe, Welwyn, Herts, UK.

Journal of Molecular Graphics
|June 1, 1991
PubMed
Summary

A neural network effectively reduces complex molecular data into 2D plots for biological activity classification. This method offers comparable or superior results to existing dimension reduction techniques.

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

Measurement of the Positive Muon Anomalous Magnetic Moment to 127 ppb.

Physical review letters·2025
Same author

A compact frozen-spin trap for the search for the electric dipole moment of the muon.

The European physical journal. C, Particles and fields·2025
Same author

Measurement of the Positive Muon Anomalous Magnetic Moment to 0.20 ppm.

Physical review letters·2023
Same author

Odderon Exchange from Elastic Scattering Differences between pp and pp[over ¯] Data at 1.96 TeV and from pp Forward Scattering Measurements.

Physical review letters·2021
Same author

Measurement of the Positive Muon Anomalous Magnetic Moment to 0.46 ppm.

Physical review letters·2021
Same author

Measurement of the Effective Weak Mixing Angle in pp[over ¯]→Z/γ^{*}→ℓ^{+}ℓ^{-} Events.

Physical review letters·2018

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning

Background:

  • Physicochemical properties of biologically active molecules contain relevant information for activity classification.
  • Dimensionality reduction is crucial for visualizing and analyzing high-dimensional datasets.

Purpose of the Study:

  • To apply a neural network for dimensionality reduction of multivariate physicochemical data.
  • To generate two-dimensional (2D) displays of complex molecular datasets.
  • To compare the neural network's performance against established dimension reduction techniques.

Main Methods:

  • Utilized a neural network for dimensionality reduction.
  • Applied computational chemistry methods to calculate molecular properties.
  • Compared results with linear and nonlinear dimension reduction techniques.

Related Experiment Videos

Main Results:

  • The neural network successfully reduced data dimensionality, producing 2D plots.
  • The generated plots were comparable to, and in one instance superior to, results from other methods.
  • Demonstrated the utility of the neural network for visualizing and potentially classifying biologically active compounds.

Conclusions:

  • Neural network-based dimensionality reduction is a viable and effective method for analyzing molecular data.
  • This technique offers advantages for visualizing complex datasets in cheminformatics and drug discovery.
  • The approach facilitates the classification of compounds based on their biological activity through enhanced data visualization.