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

Modelling the structure and function of enzymes by machine learning.

M J Sternberg1, R A Lewis, R D King

  • 1Biomolecular Modelling Laboratory, Imperial Cancer Research Fund, London, UK.

Faraday Discussions
|January 1, 1992
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

Enhancement of protein modeling by human intervention in applying the automatic programs 3D-JIGSAW and 3D-PSSM.

Proteins·2002
Same author

Generating protein three-dimensional fold signatures using inductive logic programming.

Computers & chemistry·2002
Same author

PML bodies associate specifically with the MHC gene cluster in interphase nuclei.

Journal of cell science·2001
Same author

A structural census of metabolic networks for E. coli.

Journal of molecular biology·2001
Same author

Automated structure-based prediction of functional sites in proteins: applications to assessing the validity of inheriting protein function from homology in genome annotation and to protein docking.

Journal of molecular biology·2001
Same author

An approach to improving multiple alignments of protein sequences using predicted secondary structure.

Protein engineering·2001
Same journal

Ambient stability and surface adhesion of 2D polyaramid nanofilms.

Faraday discussions·2026
Same journal

Spiers Memorial Lecture: Spin-mediated promotion of magnetic metal catalysts.

Faraday discussions·2026
Same journal

Helium spin-echo as a surface-sensitive probe of vibrational energy dissipation.

Faraday discussions·2026
Same journal

Near-infrared vibrational second harmonic generation: a new nonlinear interfacial vibrational spectroscopy.

Faraday discussions·2026
Same journal

CO on a Rh/Fe<sub>3</sub>O<sub>4</sub> single-atom catalyst: high-resolution infrared spectroscopy and near-ambient-pressure scanning tunnelling microscopy.

Faraday discussions·2026
Same journal

Evolution of size-selected Pt cluster catalysts on prototypical oxide supports.

Faraday discussions·2026
See all related articles

The GOLEM machine learning program accurately predicts protein secondary structures and models drug activity. Its derived chemical rules offer insights into protein structures and enzyme-binding sites, outperforming traditional methods.

Area of Science:

  • Computational biology
  • Cheminformatics
  • Machine learning

Background:

  • Protein structure prediction is crucial for understanding function.
  • Quantitative structure-activity relationship (QSAR) modeling aids drug design.
  • Integrating chemical knowledge with machine learning can improve predictive accuracy.

Purpose of the Study:

  • To apply the GOLEM machine learning program to protein secondary structure prediction.
  • To utilize GOLEM for modeling quantitative structure-activity relationships in drug design.
  • To generate predictive rules based on chemical principles.

Main Methods:

  • GOLEM was applied to predict protein secondary structure for the alpha/alpha class.
  • GOLEM was used to model the activity of trimethoprim analogues binding to E. coli dihydrofolate reductase.

Related Experiment Videos

  • The system combined observational data with chemical background knowledge.

    • Main Results:

    • GOLEM achieved 81% accuracy in predicting protein secondary structure on an independent test set.
    • The derived rules identified specific residue patterns forming alpha-helices.
    • GOLEM provided a superior model for drug design compared to standard regression, aligning with crystallographic data.

    Conclusions:

    • GOLEM effectively predicts protein secondary structure and models drug-target interactions.
    • The generated stereochemical rules offer valuable insights into molecular recognition.
    • This approach enhances understanding in both structural biology and drug discovery.