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

Predictive QSAR modeling workflow, model applicability domains, and virtual screening.

Alexander Tropsha1, Alexander Golbraikh

  • 1Laboratory for Molecular Modeling and, Carolina Center for Exploratory Cheminformatics Research, CB 7360 School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. alex_tropsha@unc.edu

Current Pharmaceutical Design
|January 29, 2008
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

Machine Learning Models with a Reject Option to Minimize Prediction Error: Application to Optical Properties of Dye Molecules.

Research square·2026
Same author

The ROBOKOP v1.0 knowledge graph system for exploring relationships between biomedical entities.

Scientific reports·2026
Same author

Binding Free Energies without Alchemy.

ArXiv·2026
Same author

CACHE Challenge #3: Targeting the Nsp3 Macrodomain of SARS-CoV-2.

Journal of chemical information and modeling·2026
Same author

Adaptive Machine Learning Framework for Optimizing the Affinity Purification of Adeno-Associated Viral Vectors.

Biotechnology and bioengineering·2026
Same author

Medicines, Diseases, Indications, and Contraindications (MeDIC): a foundational resource to support drug repurposing.

Nucleic acids research·2025
Same journal

Corrigendum to: miRNA in Diagnosis and Therapeutics of Tuberculosis: Importance in Latent and Brain Associated Pathologies.

Current pharmaceutical design·2026
Same journal

Combining Network Pharmacology, Machine Learning, Molecular Docking, and Experimental Validation to Explore the Mechanism of Danggui-Shaoyao-San in treating Rheumatoid arthritis.

Current pharmaceutical design·2026
Same journal

Clinical Utilization of Beers Criteria and STOPP-START Algorithm in Elderly Patients: Emphasis on Neuropsychiatric Medications.

Current pharmaceutical design·2026
Same journal

Halofantrine Upregulates ATP6V0D2 and Induces Cytotoxic Autophagy in GBM Models.

Current pharmaceutical design·2026
Same journal

Multi-Component Synergy in Hepatic Trauma Repair: Network Pharmacology and Molecular Docking Decipher Panax Notoginseng's PI3K-Akt Pathway Activation.

Current pharmaceutical design·2026
Same journal

Network Pharmacology Analysis and Animal Experiment Validation of Penthorum chinense Pursh in Treating Cholestatic Liver Disease.

Current pharmaceutical design·2026
See all related articles

Quantitative Structure Activity Relationship (QSAR) modeling is shifting from retrospective evaluation to predictive forecasting. Modern QSAR approaches enable accurate prediction of compound properties and identification of novel bioactive molecules.

Area of Science:

  • Medicinal Chemistry
  • Computational Chemistry
  • Drug Discovery

Background:

  • Quantitative Structure Activity Relationship (QSAR) modeling traditionally focused on retrospective analysis of existing data.
  • Model extrapolation for predicting novel compound activity was largely hypothetical.
  • Modern QSAR approaches offer potential for robust, validated predictive models.

Purpose of the Study:

  • To critically review modern QSAR modeling strategies and outputs.
  • To present a data-analytical workflow for combinatorial QSAR model development and validation.
  • To demonstrate the predictive power of QSAR in identifying novel biologically active compounds.

Main Methods:

  • Development of a data-analytical workflow for combinatorial QSAR.

Related Experiment Videos

  • Utilizing all possible binary combinations of descriptor sets and statistical modeling techniques.
  • Rigorous model validation and definition of applicability domains.
  • Virtual screening of chemical databases using validated QSAR models.

    • Main Results:

    • Current QSAR methodologies can yield validated models for accurate property prediction of unseen molecules.
    • The presented workflow successfully identified computationally relevant hits.
    • Subsequent experimental investigations confirmed the identified computational hits, validating the QSAR approach.

    Conclusions:

    • Modern QSAR modeling is evolving into a predictive approach focused on target property forecasting.
    • Rigorous validation and defined applicability domains are crucial for reliable QSAR predictions.
    • Validated QSAR models are effective tools for virtual screening and the discovery of novel bioactive compounds.