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

Protein-protein Interfaces02:04

Protein-protein Interfaces

14.8K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
14.8K
Protein-Protein Interfaces02:04

Protein-Protein Interfaces

4.5K
No description available
4.5K
The Equilibrium Binding Constant and Binding Strength02:18

The Equilibrium Binding Constant and Binding Strength

15.1K
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:
15.1K
The Equilibrium Binding Constant and Binding Strength02:18

The Equilibrium Binding Constant and Binding Strength

10.1K
No description available
10.1K
Conserved Binding Sites01:49

Conserved Binding Sites

5.2K
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...
5.2K
Conserved Binding Sites01:49

Conserved Binding Sites

2.0K
No description available
2.0K

You might also read

Related Articles

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

Sort by
Same author

Reparameterizing a Lipid Force Field Using Small-Angle X-ray Scattering to Improve Predictions of Multicomponent Membranes under Organic Solvent Stress.

The journal of physical chemistry. B·2026
Same author

Allosteric prediction via convolutional neural networks and protein structural and dynamical features.

Biophysical journal·2025
Same author

TCR-H: explainable machine learning prediction of T-cell receptor epitope binding on unseen datasets.

Frontiers in immunology·2024
Same author

MHC-Fine: Fine-tuned AlphaFold for precise MHC-peptide complex prediction.

Biophysical journal·2024
Same author

Generative β-hairpin design using a residue-based physicochemical property landscape.

Biophysical journal·2024
Same author

MHC-Fine: Fine-tuned AlphaFold for Precise MHC-Peptide Complex Prediction.

bioRxiv : the preprint server for biology·2023

Related Experiment Video

Updated: Feb 9, 2026

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

958

Using physical potentials and learned models to distinguish native binding interfaces from de novo designed

Omar N A Demerdash1, Julie C Mitchell

  • 1Medical Scientist Training Program, University of Wisconsin-Madison, Madison, Wisconsin; Biophysics Program, University of Wisconsin-Madison, Madison, Wisconsin.

Proteins
|June 14, 2013
PubMed
Summary

We developed a computational model to predict protein binding. This model accurately identifies designed proteins capable of binding, improving protein design and understanding biological interactions.

Keywords:
machine learningprotein bindingprotein complexprotein designstacking interactions

More Related Videos

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

17.6K
Bridging the Bio-Electronic Interface with Biofabrication
16:38

Bridging the Bio-Electronic Interface with Biofabrication

Published on: June 6, 2012

17.3K

Related Experiment Videos

Last Updated: Feb 9, 2026

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

958
Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules
10:58

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

17.6K
Bridging the Bio-Electronic Interface with Biofabrication
16:38

Bridging the Bio-Electronic Interface with Biofabrication

Published on: June 6, 2012

17.3K

Area of Science:

  • Computational Biology
  • Structural Biology
  • Biophysics

Background:

  • Protein-protein interactions are crucial for biological processes.
  • Computational and recombinant protein techniques enable rational protein design.
  • Predicting binding affinity of designed proteins is essential for experimental validation.

Purpose of the Study:

  • To develop and validate a computational model for predicting protein-protein binding.
  • To assess the performance of different machine learning kernels for binding prediction.
  • To identify key features contributing to accurate binding prediction in designed proteins.

Main Methods:

  • Developed a learned classification model combining energetic and non-energetic features.
  • Utilized specialized potentials for aromatic interactions, hydrogen bonds, electrostatics, shape, and desolvation.
  • Trained and validated support-vector machine (SVM) models, comparing various kernels, including Gaussian.

Main Results:

  • The Gaussian kernel SVM model achieved 79-86% accuracy on independent test data for both high-resolution complexes and designed nonbinders.
  • Multiple physical potentials, particularly for dielectric-dependent electrostatics and hydrogen bonding, significantly enhanced predictive accuracy.
  • Combined information from multiple physical potentials proved more valuable than any single energetics model.

Conclusions:

  • The developed computational model effectively predicts protein-protein binding for designed proteins.
  • The integration of diverse physical potentials is key to improving prediction accuracy.
  • Further analysis revealed unique prediction patterns for designed interfaces compared to other data types.