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

Identification of biological activity profiles using substructural analysis and genetic algorithms

V J Gillet1, P Willett, J Bradshaw

  • 1Department of Information Studies, University of Sheffield, Western Bank, United Kingdom. V.GILLET@SHEFFIELD.AC.UK

Journal of Chemical Information and Computer Sciences
|April 16, 1998
PubMed
Summary

This study introduces a substructural analysis method to predict drug activity using molecular features. The approach effectively distinguishes active from inactive compounds, improving drug discovery efficiency.

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

AAT-App+: A double-blind, pilot randomised controlled trial of a novel personalised smartphone intervention to reduce hazardous and harmful alcohol consumption among middle-older adults.

Addictive behaviors·2025
Same author

The Effect of SPECTROM Training on Support Staff Knowledge of Psychotropic Medicine and Attitude Towards Behaviours That Challenge in Adults With Intellectual Disabilities to Help Implement the STOMP Initiative.

Journal of intellectual disability research : JIDR·2025
Same author

Characterization of early skill profiles for infants across varying genetic likelihoods for neurodevelopmental disorders.

Infant behavior & development·2025
Same author

Author Correction: A dense ring of the trans-Neptunian object Quaoar outside its Roche limit.

Nature·2024
Same author

The collective impact of childhood abuse, psychache, and interpersonal needs on suicidal ideation among individuals with bipolar disorder: A discriminant analysis.

Child abuse & neglect·2023
Same author

A dense ring of the trans-Neptunian object Quaoar outside its Roche limit.

Nature·2023

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Drug discovery

Background:

  • Predicting biological activity of molecules is crucial for drug discovery.
  • Existing methods may not fully leverage simple structural features for activity prediction.
  • Databases like the World Drug Index and SPRESI provide valuable active and inactive compound data.

Purpose of the Study:

  • To develop and validate a substructural analysis approach for calculating biological activity profiles.
  • To assess the effectiveness of simple structural descriptors in discriminating active from inactive compounds.
  • To enhance the prediction accuracy using a genetic algorithm for profile weight optimization.

Main Methods:

  • Substructural analysis to identify and quantify generic molecular features (e.g., hydrogen-bond donors/acceptors, rotatable bonds, molecular weight, 2 kappa alpha descriptors).

Related Experiment Videos

  • Calculation of biological activity profiles based on the differential occurrence of these features in active (World Drug Index) and inactive (SPRESI database) molecules.
  • Application of a genetic algorithm to optimize the weights within the calculated activity profiles.

    • Main Results:

    • The substructural analysis approach effectively discriminates between active and inactive compounds using simple descriptors.
    • Biological activity profiles demonstrate significant predictive power for compound activity.
    • The integration of a genetic algorithm further enhances the discriminatory effectiveness of the profiles.

    Conclusions:

    • Substructural analysis provides a computationally efficient method for predicting biological activity.
    • Simple molecular descriptors, when analyzed appropriately, are powerful indicators of compound activity.
    • The developed method, enhanced by genetic algorithms, offers a valuable tool for accelerating drug discovery and development.