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

Parameter estimation for scoring protein-ligand interactions using negative training data.

Tuan A Pham1, Ajay N Jain

  • 1Cancer Research Institute, Department of Biopharmaceutical Sciences, University of California, San Francisco, 2340 Sutter Street, San Francisco, California 94143-0128, USA.

Journal of Medicinal Chemistry
|September 29, 2006
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

CSCAN: Conformational Analysis of Macrocyclic Peptides through NMR Chemical Shifts.

Journal of chemical information and modeling·2026
Same author

Structure-based pose prediction: Non-cognate docking extended to macrocyclic ligands.

Journal of computer-aided molecular design·2024
Same author

From UK-2A to florylpicoxamid: Active learning to identify a mimic of a macrocyclic natural product.

Journal of computer-aided molecular design·2024
Same author

Correction: Complex peptide macrocycle optimization: combining NMR restraints with conformational analysis to guide structure-based and ligand-based design.

Journal of computer-aided molecular design·2024
Same author

Complex peptide macrocycle optimization: combining NMR restraints with conformational analysis to guide structure-based and ligand-based design.

Journal of computer-aided molecular design·2023
Same author

Unmasking the True Identity of Rapamycin's Minor Conformer.

Journal of natural products·2023
Same journal

Library Docking for Cannabinoid-2 Receptor Ligands.

Journal of medicinal chemistry·2026
Same journal

Charting New Territory: Systematic Evaluation of the Drug Potential of <i>N</i>-Trifluoromethyl Amides, Ureas & Carbamates.

Journal of medicinal chemistry·2026
Same journal

Red-Light-Triggered <i>In Vitro</i> and <i>In Vivo</i> Photocatalytic Cancer Therapy with Polypyridyl Os(II) Photocatalysts.

Journal of medicinal chemistry·2026
Same journal

Novel Selenium-Containing Small Molecule PD-L1 Inhibitors: Design, Synthesis, and Evaluation of the Antitumor Activity.

Journal of medicinal chemistry·2026
Same journal

HsClpP-Engaging Selective Mitochondrial Pan-PDK Degraders for Cancer Therapy.

Journal of medicinal chemistry·2026
Same journal

Rational Development of Activatable Prodrugs of the GSTP1 Inhibitor NBDHEX: Turn-On NIR Fluorogenic Drug Delivery with Selective Anticancer Activity.

Journal of medicinal chemistry·2026
See all related articles

This study introduces a generalized method for protein-ligand docking using negative training data to improve scoring function accuracy. The enhanced Surflex-Dock model significantly improves the enrichment of true ligands in virtual screening.

Area of Science:

  • Computational chemistry
  • Structural biology
  • Drug discovery

Background:

  • Surflex-Dock uses an empirical scoring function for protein-ligand interaction ranking.
  • The original function was trained solely on positive binding data, limiting its ability to penalize unfavorable interactions.
  • An ad hoc method was used to prevent protein-ligand interpenetration.

Purpose of the Study:

  • To develop a generalized method for incorporating negative training data into the Surflex-Dock scoring function.
  • To rigorously estimate all scoring function parameters.
  • To evaluate the impact of the new parametrization on docking accuracy and virtual screening utility.

Main Methods:

  • Incorporation of synthetically generated negative training data into the Surflex-Dock scoring function.

Related Experiment Videos

  • Rigorous estimation of scoring function parameters using both positive and negative data.
  • Evaluation of geometric docking accuracy.
  • Testing of virtual screening utility across 29 diverse protein-ligand systems.

    • Main Results:

    • Geometric docking accuracy remained excellent after incorporating negative data.
    • The enhanced Surflex-Dock demonstrated improved performance in virtual screening utility.
    • Maximal enrichment of true ligands over nonligands exceeded 20-fold in over 80% of tested cases.
    • Enrichment greater than 100-fold was achieved in over 50% of cases.

    Conclusions:

    • The generalized method for incorporating negative training data significantly enhances the Surflex-Dock scoring function.
    • The improved scoring function leads to more effective virtual screening for drug discovery.
    • This approach provides a more robust and accurate method for predicting protein-ligand interactions.