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

Training similarity measures for specific activities: application to reduced graphs.

Kristian Birchall1, Valerie J Gillet, Gavin Harper

  • 1Department of Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, United Kingdom.

Journal of Chemical Information and Modeling
|March 28, 2006
PubMed
Summary

This study introduces a genetic algorithm (GA) to optimize chemical structure similarity searching. The GA-derived weights for graph edit distance operations significantly improve recall in activity-based searches and virtual screening.

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

PyMolGen: Database-Driven Molecular Generation of Drug-Like Compounds.

Journal of chemical information and modeling·2026
Same author

Automated Molecular Design in BRADSHAW, Applied to the Optimization of ERAP1 Inhibitors.

Journal of medicinal chemistry·2026
Same author

Query Matters: How Selection Strategies Influence Active Learning in Drug Discovery.

Journal of chemical information and modeling·2026
Same author

Explicit Applicability Domain Calculations Can Help Determine When Uncertainty Estimates Are Less Reliable.

ACS omega·2026
Same author

Spotlight on Sjögren's: a patient perspective on burden of illness and unmet needs - results from a real-world survey.

RMD open·2026
Same author

Design and Synthesis of Pyrazoline Inhibitors of SARS-CoV‑2 NSP14.

ACS medicinal chemistry letters·2025

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Drug discovery

Background:

  • Reduced graph representations are effective for chemical similarity searching, complementing existing methods.
  • Edit distance quantifies graph similarity based on transformation operations, allowing for weighted operations.

Purpose of the Study:

  • To develop a genetic algorithm (GA) for training weights of edit distance operations in reduced chemical graphs.
  • To derive activity-class specific and generalized weights for improved similarity searching and virtual screening.

Main Methods:

  • Utilized a genetic algorithm (GA) to train weights for graph edit distance operations.
  • Applied the GA to activity classes from the MDDR database for specific and generalized weight derivation.
  • Evaluated performance using recall experiments.

Related Experiment Videos

Main Results:

  • GA-derived activity-class specific weights substantially improved recall compared to intuitive weights.
  • GA-derived generalized weights also showed significant improvement for broader virtual screening applications.
  • Optimized weights provide valuable structure-activity relationship insights.

Conclusions:

  • Genetic algorithm-based weight optimization enhances the performance of reduced graph edit distance for chemical similarity searching.
  • Activity-specific and generalized weights derived by GA offer significant advantages in drug discovery and virtual screening.
  • This approach provides a powerful tool for analyzing structure-activity relationships and guiding molecular design.