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

Variable selection and model validation of 2D and 3D molecular descriptors.

Anthony Nicholls1, Norah E MacCuish, John D MacCuish

  • 1OpenEye Scientific Software, Inc., Santa Fe, NM 87507, USA. anthony@www.eyesopen.com

Journal of Computer-Aided Molecular Design
|February 26, 2005
PubMed
Summary

Molecular shape, electrostatics, and 2D fingerprints are key for drug discovery. This study details their use in quantitative structure-activity relationship (QSAR) analysis for identifying active compounds.

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

We are not doing enough: Truth-telling and Aboriginal and Torres Strait Islander history in Australian Public Health.

PLOS global public health·2025
Same author

Exploration of Cryptic Pockets Using Enhanced Sampling Along Normal Modes: A Case Study of KRAS <sup>G12D</sup>.

Journal of chemical information and modeling·2024
Same author

Convergent validity and reliability of a novel repeated agility protocol in junior rugby league players.

F1000Research·2021
Same author

Virtual Screening in the Cloud: How Big Is Big Enough?

Journal of chemical information and modeling·2019
Same author

The Effect of a Resistance Training Session on Physiological and Thermoregulatory Measures of Sub-maximal Running Performance in the Heat in Heat-Acclimatized Men.

Sports medicine - open·2019
Same author

Leaving us with fond memories, smiles, SMILES and, alas, tears: a tribute to David Weininger, 1952-2016.

Journal of computer-aided molecular design·2018

Area of Science:

  • Computational chemistry
  • Medicinal chemistry
  • Drug discovery

Background:

  • Identifying active compounds is crucial in drug discovery.
  • Quantitative structure-activity relationship (QSAR) analysis relies on molecular descriptors.

Purpose of the Study:

  • To explore variable selection and importance in QSAR.
  • To apply molecular shape, electrostatics, and 2D fingerprints in QSAR analysis.

Main Methods:

  • Utilized molecular shape, electrostatics, and 2D structural fingerprints as variables.
  • Employed similarity searching against known ligand crystal structures.
  • Validated findings using k-fold cross-validation and common classifiers.
  • Developed a methodology for hypothesis generation when crystal structures are unknown.

Related Experiment Videos

Main Results:

  • Established molecular shape, electrostatics, and 2D fingerprints as important discriminators of active and inactive compounds.
  • Demonstrated the effectiveness of these variables in similarity searching and hypothesis generation.
  • Validated the predictive power of the QSAR models.

Conclusions:

  • Molecular shape, electrostatics, and 2D fingerprints are vital for QSAR.
  • The proposed methods enhance compound classification and hypothesis generation in drug discovery.