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

Molecular similarity searching using atom environments, information-based feature selection, and a naïve Bayesian

Andreas Bender1, Hamse Y Mussa, Robert C Glen

  • 1Unilever Centre for Molecular Science Informatics, Chemistry Department, University of Cambridge, Cambridge CB2 1EW, UK. ab454@cam.ac.uk

Journal of Chemical Information and Computer Sciences
|January 27, 2004
PubMed
Summary

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

SOPA and SIMPA: normalized single-sample integrated multiomics pathway analysis of tumor heterogeneity in solid cancers.

Briefings in bioinformatics·2026
Same author

Post-discharge "continuum of care" clinical pathway (CP) for persons with severe neuro-disabilities - qualitative research to model needs-based community healthcare, capture the real-life care situation, and assess the appropriateness of the CP's concept with input from community- and hospital-based healthcare professionals.

Frontiers in neurology·2026
Same author

Reduction techniques for survival analysis.

Lifetime data analysis·2026
Same author

The Course of Rehabilitation of Ventilated and Tracheally Cannulated Patients in Neurological-Neurosurgical Early Rehabilitation.

Deutsches Arzteblatt international·2026
Same author

Interpretations of Menstrual Blood Appearance and Diagnostic Potential Among Social Media Users: Cross-Sectional Mixed Methods Social Media Listening Study.

Journal of medical Internet research·2026
Same author

Rethinking the role of synergy calculations in the next century of drug combination discovery.

Med (New York, N.Y.)·2026

A new method represents molecules using atom environments and information gain for feature selection, improving drug discovery similarity searching. This approach outperforms existing techniques in retrieving active molecules.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning in drug discovery

Background:

  • Similarity searching is crucial for identifying novel drug candidates.
  • Existing methods using 2D and 3D descriptors have limitations in accuracy and efficiency.
  • Effective molecular representation is key to successful similarity searching.

Purpose of the Study:

  • To introduce a novel, efficient, and accurate technique for molecular similarity searching.
  • To leverage atom environments and information gain for enhanced feature selection in chemical data.
  • To validate the new method's performance against established retrieval algorithms.

Main Methods:

  • Molecules are represented using atom environments.
  • Information gain is applied for feature selection from these environments.

Related Experiment Videos

  • A naive Bayesian classifier is utilized for compound classification.
  • The method is evaluated using five datasets of active molecules from the MDDR database.

    • Main Results:

    • The novel technique successfully retrieved active molecules across five test sets.
    • The algorithm demonstrated superior performance compared to existing 2D and 3D descriptor-based methods.
    • The approach provided insights into the structural features critical for molecular binding.

    Conclusions:

    • The atom environment and information gain-based method offers a powerful new approach for molecular similarity searching.
    • This technique enhances the identification of potential drug candidates by outperforming current methods.
    • The findings highlight the importance of specific structural components in molecular interactions.