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

Database mining applied to central nervous system (CNS) activity.

M Pintore1, O Taboureau, F Ros

  • 1Laboratory of Chemometrics and BioInformatics, University of Orléans, BP 6759, F-45067 Orleans Cedex 2, France.

European Journal of Medicinal Chemistry
|July 20, 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

Enforcing Dirichlet boundary conditions in physics-informed neural networks and variational physics-informed neural networks.

Heliyon·2023
Same author

Classification-based QSARs for predicting dietary biomagnification in fish.

SAR and QSAR in environmental research·2022
Same author

Transcriptome Analysis of Plasmodium falciparum Isolates From Benin Reveals Specific Gene Expression Associated With Cerebral Malaria.

The Journal of infectious diseases·2022
Same author

Prospective external validation of IOTA three-step strategy for characterizing and classifying adnexal masses and retrospective assessment of alternative two-step strategy using simple-rules risk.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2018
Same author

Effects of treated industrial wastewaters and temperatures on growth and enzymatic activities of duckweed (Lemna minor L.).

Ecotoxicology and environmental safety·2018
Same author

Letter To the Editor: 'Comment J'ai Vaincu la Douler et l'Inflammation Chronique Par l'Alimentation' by J Lagacè.

Translational medicine @ UniSa·2013

This study introduces a hybrid system combining Self-Organizing Maps (SOM) and fuzzy clustering (FC) for analyzing central nervous system (CNS) compounds. The novel approach accurately predicts compound activity classes, aiding drug discovery efforts.

Area of Science:

  • Computational Chemistry
  • Cheminformatics
  • Artificial Intelligence in Drug Discovery

Background:

  • Analyzing large datasets of biologically active compounds is crucial for identifying new drug candidates.
  • Understanding structure-activity relationships requires advanced computational methods to interpret complex chemical spaces.
  • Existing methods for classifying compounds based on receptor activity can be limited in scope and predictive power.

Purpose of the Study:

  • To develop and validate a hybrid computational system for classifying central nervous system (CNS) active compounds.
  • To leverage Self-Organizing Maps (SOM) and fuzzy clustering (FC) for objective interpretation of compound hyperspace.
  • To assess the predictive accuracy of the SOM/FC system in classifying compounds across eight distinct receptor activity classes.

Related Experiment Videos

Main Methods:

  • Utilized a dataset of 389 CNS active compounds from the RBI database.
  • Applied Self-Organizing Maps (SOM), a type of Kohonen Artificial Neural Network, for dimensionality reduction and visualization.
  • Integrated fuzzy clustering (FC) with SOM to delineate compound clusters and enable objective map interpretation.
  • Validated the hybrid SOM/FC system using a training set (259 compounds) and a test set (130 compounds).

Main Results:

  • SOM generated 2D maps representing compound distribution in a hyperspace defined by molecular descriptors.
  • Specific regions on the SOM maps correlated with unique receptor types, while other zones showed nested activity classes.
  • The SOM/FC hybrid system demonstrated simultaneous prediction of compound activity classes.
  • The system achieved an 81% accuracy in correctly predicting the experimental activity class for compounds in the test set.

Conclusions:

  • The hybrid SOM/FC system provides a robust and objective method for analyzing and classifying CNS active compounds.
  • This approach enhances the understanding of structure-activity relationships by mapping compound distribution in chemical hyperspace.
  • The validated predictive ability of the system supports its application in accelerating drug discovery and development for CNS targets.