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

Predicting Molecular Geometry02:27

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries
Molecular Models02:00

Molecular Models

Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
Protein Folding01:22

Protein Folding

Overview
Protein Folding01:25

Protein Folding

Proteins are chains of amino acids linked together by peptide bonds. Upon synthesis, a protein folds into a three-dimensional conformation, critical to its biological function. Interactions between its constituent amino acids guide protein folding, and hence the protein structure is primarily dependent on its amino acid sequence.
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
Protein Folding01:22

Protein Folding

Overview
X-ray Crystallography02:18

X-ray Crystallography

The size of the unit cell and the arrangement of atoms in a crystal may be determined from measurements of the diffraction of X-rays by the crystal, termed X-ray crystallography.
Diffraction
Diffraction is the change in the direction of travel experienced by an electromagnetic wave when it encounters a physical barrier whose dimensions are comparable to those of the wavelength of the light. X-rays are electromagnetic radiation with wavelengths about as long as the distance between neighboring...

You might also read

Related Articles

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

Sort by
Same authorSame journal

A ligandable PNT domain establishes ERG as a directly targetable oncogenic driver in prostate cancer.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Structural rewiring of IL-7R dimerization by an oncogenic transmembrane mutation can be reversed by rational design.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Electric dipole moment drives the dynamics of the TNFR1 complex I signalosome.

Nature·2026
Same author

CD8<sup>+</sup> T cell loss induces autoinflammation in inborn errors of cell death.

Nature communications·2026
Same author

Repression of RIPK1 kinase by INPP5D inhibits expression of diverse proinflammatory mediators and late-onset Alzheimer's disease risk factors.

Immunity·2026
Same author

A comprehensive proteome structural analysis suggests undiscovered functional domains in ocean archaea.

Protein science : a publication of the Protein Society·2025

Related Experiment Video

Updated: Jun 11, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Void-X: A generative void-filling model for predicting atomic packing in proteins.

Jing Yang1,2, Junying Yuan1,3, James J Chou1,2

  • 1Interdisciplinary Research Center on Biology and Chemistry, Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences, Shanghai 201203, China.

Proceedings of the National Academy of Sciences of the United States of America
|June 9, 2026
PubMed
Summary
This summary is machine-generated.

We developed Void-X, a novel AI model for protein design. This bottom-up approach generates atom clusters to precisely design protein interactions at the atomic level.

Keywords:
AIdiscrete diffusion modelprotein design

More Related Videos

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Combining X-Ray Crystallography with Small Angle X-Ray Scattering to Model Unstructured Regions of Nsa1 from S. Cerevisiae
09:15

Combining X-Ray Crystallography with Small Angle X-Ray Scattering to Model Unstructured Regions of Nsa1 from S. Cerevisiae

Published on: January 10, 2018

Related Experiment Videos

Last Updated: Jun 11, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Combining X-Ray Crystallography with Small Angle X-Ray Scattering to Model Unstructured Regions of Nsa1 from S. Cerevisiae
09:15

Combining X-Ray Crystallography with Small Angle X-Ray Scattering to Model Unstructured Regions of Nsa1 from S. Cerevisiae

Published on: January 10, 2018

Area of Science:

  • Computational Biology
  • Artificial Intelligence
  • Protein Engineering

Background:

  • Generative AI, including transformer and diffusion models, has advanced de novo protein design.
  • Current top-down AI methods generate overall protein shapes for specific interactions.
  • These methods face limitations due to the scarcity of available protein complex structures.

Purpose of the Study:

  • To propose a novel bottom-up AI approach for protein-protein interaction design.
  • To develop a masked discrete diffusion model, Void-X, for atomic-level interaction prediction.
  • To generate atom clusters for optimal packing against specified protein regions.

Main Methods:

  • Trained a masked discrete diffusion model (Void-X) utilizing a diffusion transformer.
  • Utilized 8.7 million spherical atom clusters from the Protein Data Bank for training.
  • Employed a masked autoencoding strategy where ~70% of atoms served as context and ~30% were masked.

Main Results:

  • Void-X achieved 78.3% accuracy for intrachain and 68.2% accuracy for interchain clusters.
  • Information entropy was identified as a reliable predictor of Void-X's accuracy.
  • The model demonstrates capability in de novo generation of molecular interactions at the atomic level.

Conclusions:

  • Void-X offers a complementary bottom-up strategy to existing top-down protein design methods.
  • The model enables precise, atomic-level design of protein-protein interactions.
  • This approach has the potential to significantly impact future protein engineering efforts.