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

MOUSE-III: learning rules of conformational analysis from X-ray data

W P Walters1, D P Dolata

  • 1Department of Chemistry, University of Arizona, Tucson 85721.

Journal of Molecular Graphics
|June 1, 1994
PubMed
Summary

MOUSE-III is a novel learning program that extracts conformational analysis rules from crystallographic data. It achieves over 95% accuracy in assigning molecular conformations, significantly compressing data through abstraction.

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

Kinase chemogenomics: targeting the human kinome for target validation and drug discovery.

Mini reviews in medicinal chemistry·2004
Same author

Consensus scoring: A method for obtaining improved hit rates from docking databases of three-dimensional structures into proteins.

Journal of medicinal chemistry·1999
Same author

Recognizing molecules with drug-like properties.

Current opinion in chemical biology·1999
Same author

The use of VRML in chemical education.

Journal of molecular graphics & modelling·1998
Same author

Can we learn to distinguish between "drug-like" and "nondrug-like" molecules?

Journal of medicinal chemistry·1998
Same author

Computational studies of sialyllactones: methods and uses.

Glycoconjugate journal·1997

Area of Science:

  • Computational chemistry
  • Machine learning in structural biology
  • Crystallographic data analysis

Background:

  • Conformational analysis is crucial for understanding molecular behavior.
  • Extracting meaningful rules from raw crystallographic data is challenging.
  • Existing methods may lack efficiency in rule generalization.

Purpose of the Study:

  • To introduce MOUSE-III, a learning program for automated conformational analysis rule discovery.
  • To demonstrate the program's ability to learn and generalize rules from crystallographic data.
  • To assess the accuracy and data compression capabilities of the learned rules.

Main Methods:

  • MOUSE-III processes raw crystallographic data to identify molecular features.
  • The program classifies data into conformational classes.

Related Experiment Videos

  • It learns rules linking molecular features to specific conformational classes.

    • Main Results:

    • Learned rules achieve over 95% accuracy in assigning conformations to unseen ring systems.
    • The program demonstrates significant data compression, up to 99%, via abstraction and generalization.
    • A detailed algorithm and learned rule example are presented.

    Conclusions:

    • MOUSE-III effectively automates the discovery of conformational analysis rules.
    • The learned rules are accurate, generalizable, and highly compressive.
    • The study highlights the potential of machine learning for structural data interpretation.