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 Concept Videos

Conserved Binding Sites01:49

Conserved Binding Sites

Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
The Equilibrium Binding Constant and Binding Strength02:18

The Equilibrium Binding Constant and Binding Strength

The equilibrium binding constant (Kb) quantifies the strength of a protein-ligand interaction. Kb can be calculated as follows when the reaction is at equilibrium:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Effect of pre- and postprandial administration of Maoto extract granules on the pharmacokinetics of ephedrine and pseudoephedrine in healthy adults.

Journal of natural medicines·2025
See all related articles

Related Experiment Video

Updated: May 14, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Dynamic stability-driven machine learning improves binding pose identification on human serum albumin.

Yasuyuki Kourogi1, Kenji Ogata2, Jin Tokunaga3

  • 1Second Department of Clinical Pharmacy, School of Pharmaceutical Sciences, Kyushu University of Medical Science, Nobeoka, Japan. kourogi@phoenix.ac.jp.

Journal of Computer-Aided Molecular Design
|May 12, 2026
PubMed
Summary

Machine learning combined with short molecular dynamics simulations accurately identifies drug binding poses on human serum albumin (HSA). This dynamic approach improves upon traditional docking methods for understanding drug-protein interactions and pharmacokinetics.

Keywords:
Binding pose identificationDynamic stability featuresHuman serum albuminMachine learningMolecular dockingMolecular dynamics

Related Experiment Videos

Last Updated: May 14, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Area of Science:

  • Computational Chemistry
  • Pharmacology
  • Biophysics

Background:

  • Accurate identification of ligand binding modes on human serum albumin (HSA) is crucial for understanding drug-protein interactions that affect pharmacokinetics.
  • Conventional molecular docking methods struggle to differentiate specific binding poses from nonspecific surface interactions on HSA due to its complex, multisite nature.

Purpose of the Study:

  • To develop a machine-learning framework that integrates dynamic stability information from molecular dynamics (MD) simulations to improve the identification of ligand binding poses on HSA.
  • To assess the efficacy of this framework in distinguishing correct binding modes from incorrect ones.

Main Methods:

  • A machine-learning framework was developed incorporating features derived from short MD simulations (5 ns) of HSA-ligand complexes.
  • Features included time-dependent interaction patterns like contact persistence, distance fluctuations, and interaction energy descriptors.
  • The framework was validated using Leave-One-PDB-Out cross-validation on 31 HSA-ligand crystal structures and external validation with a nateglinide-HSA complex.

Main Results:

  • The machine-learning models incorporating MD-derived features significantly outperformed docking score-only models in identifying correct binding poses (pose-level and site-level RMSD criteria).
  • The framework demonstrated utility in discriminating plausible binding modes within the HSA context, as shown by external validation.
  • Informative dynamic features were successfully extracted from short, 5 ns MD simulations, indicating early-stage dynamics are sufficient for improved pose discrimination.

Conclusions:

  • Short molecular dynamics simulations provide practically useful and interpretable features for machine-learning-based binding-pose identification on HSA.
  • The proposed framework offers a practical strategy to enhance binding mode analysis in pharmacokinetically relevant HSA studies.
  • Further validation is needed to establish broader applicability beyond HSA.