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

Bayesian interpretation of a distance function for navigating high-dimensional descriptor spaces.

Martin Vogt1, Jeffrey W Godden, Jürgen Bajorath

  • 1Department of Life Science Informatics, B-IT, Rheinische Friedrich-Wilhelms-Universität, Dahlmannstrasse 2, D-53113 Bonn, Germany.

Journal of Chemical Information and Modeling
|January 24, 2007
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

Global Assessment of Substituents on the Basis of Analogue Series.

Journal of medicinal chemistry·2020
Same author

From Qualitative to Quantitative Analysis of Activity and Property Landscapes.

Journal of chemical information and modeling·2020
Same author

Systematic Data Analysis and Diagnostic Machine Learning Reveal Differences between Compounds with Single- and Multitarget Activity.

Molecular pharmaceutics·2020
Same author

Data set of activity cliffs with single-atom modification and associated X-ray structure information for medicinal and computational chemistry applications.

Data in brief·2020
Same author

DeepCOMO: from structure-activity relationship diagnostics to generative molecular design using the compound optimization monitor methodology.

Journal of computer-aided molecular design·2020
Same author

Inhibitor bias in luciferase-based luminescence assays.

Future science OA·2020
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

A new Bayesian distance function helps identify potential drug candidates by ranking molecules based on their similarity to known active compounds. This method efficiently focuses searches within "active subspaces" for drug discovery.

Area of Science:

  • Computational chemistry and cheminformatics.
  • Application of Bayesian statistics in molecular modeling.
  • Drug discovery and lead optimization.

Background:

  • Analyzing molecular similarity in high-dimensional spaces is crucial for drug discovery.
  • Existing similarity search tools can be computationally intensive.
  • Identifying
  • active subspaces
  • can improve search efficiency.

Purpose of the Study:

  • To develop a novel Bayesian distance function for molecular similarity analysis.
  • To focus computational searches on relevant
  • active subspaces
  • .

Main Methods:

  • Defined a Bayesian distance function to measure molecular similarity.

Related Experiment Videos

  • Ranked database compounds by their distance to the center of an active subspace.
  • Transformed distance calculations into a Bayesian
  • log-odds
  • estimate.

    • Main Results:

    • Minimizing distance to the active subspace center maximizes the likelihood of a compound being active.
    • The Bayesian function provides a ranking of molecules by decreasing similarity to templates.
    • The proposed method favorably compared to standard fingerprints in database searching.

    Conclusions:

    • The developed Bayesian distance function offers an effective approach for similarity searching in drug discovery.
    • This method enhances the efficiency of identifying potential drug candidates by focusing on
    • active subspaces
    • .