Jove
Visualize
Contact Us

Related Experiment Videos

Feature selection in quantitative structure-activity relationships.

W Patrick Walters1, Brain B Goldman

  • 1Vertex Pharmaceuticals Inc, 130 Waverley St, Cambridge, MA 02139, USA. pat_walters@vrtx.com

Current Opinion in Drug Discovery & Development
|May 17, 2005
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

Mapping the avoid-ome: a systematic open-science approach to predictive ADMET.

Nature communications·2026
Same author

The Open Molecular Software Foundation (OMSF) and the Growing Role of Open Source Software in Molecular Modeling.

Journal of chemical information and modeling·2026
Same author

A Computational Community Blind Challenge on Pan-Coronavirus Drug Discovery Data.

Journal of chemical information and modeling·2026
Same author

Blind Challenges Let Us See the Path Forward for Predictive Models.

Journal of chemical information and modeling·2026
Same author

Correction: Enhanced Thompson sampling by roulette wheel selection for screening ultralarge combinatorial libraries.

Journal of cheminformatics·2025
Same author

Enhanced Thompson sampling by roulette wheel selection for screening ultralarge combinatorial libraries.

Journal of cheminformatics·2025
Same journal

Microreactors for continuous processing – How close to commercial utility?

Current opinion in drug discovery & development·2010
Same journal

Synthesis of polyketide natural products and analogs as promising anticancer agents.

Current opinion in drug discovery & development·2010
Same journal

Enantioselective synthesis of substituted oxindoles and spirooxindoles with applications in drug discovery.

Current opinion in drug discovery & development·2010
Same journal

Eliminating pharmaceutical impurities: Recent advances in detection techniques.

Current opinion in drug discovery & development·2010
Same journal

Stereoselective heterocycle synthesis through oxidative carbon-hydrogen bond activation.

Current opinion in drug discovery & development·2010
Same journal

Catalysis in aqueous media for the synthesis of drug-like molecules.

Current opinion in drug discovery & development·2010
See all related articles
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

Selecting the right molecular features is crucial for building accurate quantitative structure-activity relationship (QSAR) models. This review explores automated methods for identifying optimal descriptor sets, improving model performance.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Drug discovery

Background:

  • Quantitative structure-activity relationship (QSAR) models are essential in drug discovery and chemical research.
  • The performance of QSAR models heavily relies on the selection of molecular descriptors.
  • A vast number of molecular descriptors are available, making descriptor set selection challenging.

Purpose of the Study:

  • To review and summarize automated methods for selecting molecular descriptors in QSAR modeling.
  • To provide an overview of recent advancements in feature selection techniques for QSAR.

Main Methods:

  • Literature review of recent publications on automated feature selection for QSAR.
  • Categorization and description of various automated descriptor selection methodologies.

Related Experiment Videos

Main Results:

  • Several automated methods for identifying optimal molecular descriptor sets have been developed.
  • These methods aim to enhance the accuracy, stability, and interpretability of QSAR models.

Conclusions:

  • Automated feature selection is a critical area in QSAR modeling.
  • The reviewed methods offer valuable approaches for researchers to optimize descriptor sets and build more effective QSAR models.