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

Identifying biologically active compound classes using phenotypic screening data and sampling statistics.

Justin Klekota1, Erik Brauner, Stuart L Schreiber

  • 1Howard Hughes Medical Institute, Harvard Institute of Chemistry and Cell Biology, Broad Institute of Harvard and MIT, Harvard University, 12 Oxford Street, Cambridge, Massachusetts 02138, USA. JDKlekota@aol.com

Journal of Chemical Information and Modeling
|November 29, 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

Discovery of molecular glues that bind FKBP12 and structurally distinct targets using DNA-encoded libraries.

Nature communications·2026
Same author

Author Correction: Diversity-oriented synthesis yields novel multistage antimalarial inhibitors.

Nature·2025
Same author

Publisher Correction: Mutant p53 protein accumulation is selectively targetable by proximity-inducing drugs.

Nature chemical biology·2025
Same author

Mutant p53 protein accumulation is selectively targetable by proximity-inducing drugs.

Nature chemical biology·2025
Same author

Highly specific intracellular ubiquitination of a small molecule.

Nature chemical biology·2025
Same author

Selectivity Profiling of Bromodomain PROTACs Using Chemical Inducers of Proximity DNA-Encoded Library Screening.

ACS chemical biology·2025
Same journal

PSDTA: An Approach to Drug-Target Binding Affinity Prediction by Integrating Physicochemical and Structural Information to Reduce Feature Redundancy.

Journal of chemical information and modeling·2026
Same journal

M-JEPA: Predictive Self-Supervised Learning for Molecular Graphs with Scaffold-Shift Evaluation on Tox21.

Journal of chemical information and modeling·2026
Same journal

Advancing Biochemical Molecule Registration, Representation and Search for New Drug Modalities.

Journal of chemical information and modeling·2026
Same journal

A Unified Molecular Graph and Protein Language Model Framework for Predicting Human Drug-Hormone Receptor Interactions with Structure-Aware Validation.

Journal of chemical information and modeling·2026
Same journal

Intricate Role of Cholesterol in Membrane Fusion.

Journal of chemical information and modeling·2026
Same journal

tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES.

Journal of chemical information and modeling·2026
See all related articles

This study introduces a novel class-scoring technique for phenotypic high-throughput screening assays. This method improves compound activity prediction by analyzing structural similarities, enhancing hit recovery and reducing false positives.

Area of Science:

  • Drug discovery and development
  • Computational chemistry
  • Bioinformatics

Background:

  • Phenotypic high-throughput screening (HTS) assays face challenges with limited resolution and measurement errors, impacting compound activity scoring.
  • Leveraging structural similarity among compounds can enhance hit-recovery rates in screening data.
  • Existing methods may miss weakly active or novel compound classes due to individual assay limitations.

Purpose of the Study:

  • To present a novel technique for predicting compound activity in phenotypic HTS by scoring entire structural classes.
  • To improve the reproducibility and efficiency of hit identification in HTS data.
  • To identify potentially novel active compound classes that might be overlooked by traditional methods.

Main Methods:

Related Experiment Videos

  • Development of a class-scoring technique utilizing clustering and sampling statistics.
  • Application of the technique to a set of phenotypic assays against a commercial compound library.
  • Comparison of class-scoring results with individual compound measurements from the assays.

    • Main Results:

    • Activity prediction scores generated by class scoring were more reproducible than individual assay measurements.
    • Class scoring demonstrated higher efficiency in recovering known active compounds with fewer false positives.
    • A high recovery rate of 87% for known biologically active compounds was achieved, indicating a low false-negative rate.
    • The technique identified potentially novel and weakly active compound classes missed by individual measurements.

    Conclusions:

    • The class-scoring technique offers a robust improvement over individual compound scoring in phenotypic HTS.
    • This method enhances the reliability and efficiency of drug discovery screening by reducing false positives and negatives.
    • Class scoring facilitates the discovery of novel bioactive compound classes, expanding the potential hit space.