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

A general approach for developing system-specific functions to score protein-ligand docked complexes using support

Ata Amini1, Paul J Shrimpton, Stephen H Muggleton

  • 1Structural Bioinformatics Group, Centre for Bioinformatics, Division of Molecular Biosciences, Imperial College London, London SW7 2AY, United Kingdom.

Proteins
|October 3, 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

Computational Resources for Molecular Biology 2026.

Journal of molecular biology·2026
Same author

3DSeqCheck: A Web-based Tool for Verifying Sequence Consistency Between a 3D Structure File and the Corresponding UniProt Entry.

Journal of molecular biology·2026
Same author

The aging of the AlphaFold database.

Nature structural & molecular biology·2025
Same author

Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models.

Machine learning·2025
Same author

Computational Resources for Molecular Biology 2025.

Journal of molecular biology·2025
Same author

Phyre2.2: A Community Resource for Template-based Protein Structure Prediction.

Journal of molecular biology·2025
Same journal

Engineered HSP90-MP65 Bivalent Fusion Antigen: A Novel Vaccine Candidate Against Invasive Candidiasis.

Proteins·2026
Same journal

Physics-Based Energy Functions for Computational Protein Design.

Proteins·2026
Same journal

Impact of Stabilizing Osmolytes on the Conformational Dynamics of Human and Rat Islet Amyloid Polypeptides.

Proteins·2026
Same journal

Stabilization of Bone Morphogenetic Protein-2 at Physiological pH: Contrasting Roles of CHAPS and Arginine in Aggregation Inhibition.

Proteins·2026
Same journal

Structural Insights Into the Function of Leishmania major Adenylosuccinate Lyase.

Proteins·2026
Same journal

Generalizing the Gaussian Network Model: Spanning-Tree Thermodynamics Shows Entropy-Driven KRAS Activation.

Proteins·2026
See all related articles

A new method using support vector inductive logic programming (SVILP) can create accurate scoring functions for predicting protein-ligand binding affinities. This approach offers comparable performance to existing methods and aids in hypothesis generation for drug design.

Area of Science:

  • Computational chemistry
  • Bioinformatics
  • Machine learning in drug discovery

Background:

  • Accurate ranking of binding affinities in protein-ligand docking is crucial for drug discovery but remains challenging.
  • Existing scoring functions are often system-specific and lack transferability.
  • Lead optimization requires reliable methods for predicting ligand binding efficacy.

Purpose of the Study:

  • To develop a novel system-specific scoring function for predicting protein-ligand binding affinities using support vector inductive logic programming (SVILP).
  • To evaluate the performance of SVILP on protein-ligand complexes and compare it with state-of-the-art methods.
  • To explore the potential of SVILP for hypothesis generation in drug design.

Main Methods:

  • Utilized inductive logic programming (ILP) to learn qualitative, logic-based rules from data.

Related Experiment Videos

  • Integrated ILP with support vector machine regression to create quantitative rules (SVILP).
  • Applied SVILP to datasets of protein-ligand complexes for binding affinity prediction.

    • Main Results:

    • SVILP demonstrated comparable performance to state-of-the-art methods on five protein-ligand systems based on cross-validated correlation coefficients.
    • A McNemar test indicated SVILP was significantly better than CoMFA and CoMSIA on one occasion.
    • The method allows for graphical display and understanding of learned rules, facilitating hypothesis generation.

    Conclusions:

    • SVILP provides a robust approach for developing system-specific scoring functions in computational drug discovery.
    • The method is effective for predicting binding affinities of protein-ligand complexes and can be extended to protein-protein interactions.
    • The interpretability of SVILP rules supports hypothesis-driven ligand design and optimization.