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

A comparative chemometric study of QSAR descriptors.

D Bonelli1, G Coata, G Cruciani

  • 1Dipartimento di Chimica, Università di Perugia, Italy.

Farmaco (Societa Chimica Italiana : 1989)
|March 1, 1990
PubMed
Summary

Quantitative Structure-Activity Relationship (QSAR) models were compared using traditional descriptors versus computer-generated electronic densities and principal properties. All descriptor sets demonstrated comparable predictive performance in Partial Least Squares (PLS) modeling.

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

Rational optimization of D3R/GSK-3β dual target-directed ligands as potential treatment for bipolar disorder: Design, synthesis, X-ray crystallography, molecular dynamics simulations, in vitro ADME, and in vivo pharmacokinetic studies.

European journal of medicinal chemistry·2025
Same author

Hazardous element inertisation in vitrified silicate ceramics: Effect of different matrices.

Journal of hazardous materials·2024
Same author

Necrodes littoralis (Coleoptera: Silphidae) visiting and breeding on a carcass in Italy.

Tropical biomedicine·2022
Same author

Time-Resolved Excited-State Analysis of Molecular Electron Dynamics by TDDFT and Bethe-Salpeter Equation Formalisms.

Journal of chemical theory and computation·2021
Same author

Hybrid theoretical models for molecular nanoplasmonics.

The Journal of chemical physics·2020
Same author

Cyto- and enzyme toxicities of ionic liquids modelled on the basis of VolSurf+ descriptors and their principal properties.

SAR and QSAR in environmental research·2019

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Quantitative Structure-Activity Relationship (QSAR) studies

Background:

  • QSAR models are crucial for predicting molecular activity.
  • Traditional molecular descriptors are widely used but can be computationally intensive.
  • Exploring alternative descriptor sets can enhance efficiency and predictive power.

Purpose of the Study:

  • To compare the predictive abilities of traditional QSAR descriptors with novel descriptor sets derived from computer chemistry.
  • To evaluate the efficacy of electronic densities and principal properties as QSAR descriptors.
  • To assess the performance of Partial Least Squares (PLS) modeling across different descriptor types.

Main Methods:

  • Utilized traditional molecular descriptors.

Related Experiment Videos

  • Generated alternative descriptor sets using computer chemistry tools: electronic densities and principal properties.
  • Employed Partial Least Squares (PLS) regression for predictive modeling.
  • Compared the prediction abilities of the different descriptor sets.

    • Main Results:

    • All three descriptor sets (traditional, electronic densities, principal properties) exhibited similar predictive abilities.
    • PLS modeling showed comparable performance regardless of the descriptor set used.
    • Computer-generated descriptors offer a viable alternative to traditional methods.

    Conclusions:

    • Electronic densities and principal properties are effective alternatives to traditional descriptors in QSAR modeling.
    • The choice of descriptor set does not significantly impact prediction accuracy when using PLS modeling.
    • This finding supports the use of computational chemistry tools for generating efficient QSAR descriptors.