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

Mutations01:39

Mutations

81.5K
Overview
81.5K
Covalently Linked Protein Regulators02:04

Covalently Linked Protein Regulators

6.8K
Proteins can undergo many types of post-translational modifications, often in response to changes in their environment. These modifications play an important role in the function and stability of these proteins. Covalently linked molecules include functional groups, such as methyl, acetyl, and phosphate groups, and also small proteins, such as ubiquitin. There are around 200 different types of covalent regulators that have been identified.
These groups modify specific amino acids in a protein....
6.8K
Mismatch Repair01:36

Mismatch Repair

40.0K
Overview
40.0K

You might also read

Related Articles

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

Sort by
Same author

Agnostic material classification using differential de Bruijn graphs of DNA imprints.

bioRxiv : the preprint server for biology·2026
Same author

Promera: a unified model for biomolecular structure prediction, filtering, and design.

bioRxiv : the preprint server for biology·2026
Same author

Overestimating zero-shot fitness prediction: Broad benchmarks mask local failures and practical limitations.

bioRxiv : the preprint server for biology·2026
Same author

Integrating Transcription Factors with Electrochemical Pendulum Bioanalysis for Hormone Detection.

Journal of the American Chemical Society·2026
Same author

A cross-vertebrate brain protein interaction map identifies conserved neural and non-neural complexes.

Cell reports·2026
Same author

A protein interactome for the last eukaryotic common ancestor illuminates the biochemical basis of modern genetic diseases.

Cell genomics·2026

Related Experiment Video

Updated: Jun 19, 2025

Implementation of In Vitro Drug Resistance Assays: Maximizing the Potential for Uncovering Clinically Relevant Resistance Mechanisms
08:46

Implementation of In Vitro Drug Resistance Assays: Maximizing the Potential for Uncovering Clinically Relevant Resistance Mechanisms

Published on: December 9, 2015

10.6K

Stability Oracle: a structure-based graph-transformer framework for identifying stabilizing mutations.

Daniel J Diaz1,2,3, Chengyue Gong4, Jeffrey Ouyang-Zhang4

  • 1UT Austin, Department of Computer Science, Austin, TX, 78712, USA. dannyjdiaz305@gmail.com.

Nature Communications
|July 23, 2024
PubMed
Summary
This summary is machine-generated.

Stability Oracle, a new structure-based graph-transformer framework, accurately identifies protein mutations that enhance stability. This computational tool accelerates biotechnologies by overcoming data limitations and improving protein engineering.

More Related Videos

A Deep-sequencing-assisted, Spontaneous Suppressor Screen in the Fission Yeast Schizosaccharomyces pombe
07:55

A Deep-sequencing-assisted, Spontaneous Suppressor Screen in the Fission Yeast Schizosaccharomyces pombe

Published on: March 7, 2019

8.0K
A New Toolkit for Evaluating Gene Functions using Conditional Cas9 Stabilization
08:20

A New Toolkit for Evaluating Gene Functions using Conditional Cas9 Stabilization

Published on: September 2, 2021

4.1K

Related Experiment Videos

Last Updated: Jun 19, 2025

Implementation of In Vitro Drug Resistance Assays: Maximizing the Potential for Uncovering Clinically Relevant Resistance Mechanisms
08:46

Implementation of In Vitro Drug Resistance Assays: Maximizing the Potential for Uncovering Clinically Relevant Resistance Mechanisms

Published on: December 9, 2015

10.6K
A Deep-sequencing-assisted, Spontaneous Suppressor Screen in the Fission Yeast Schizosaccharomyces pombe
07:55

A Deep-sequencing-assisted, Spontaneous Suppressor Screen in the Fission Yeast Schizosaccharomyces pombe

Published on: March 7, 2019

8.0K
A New Toolkit for Evaluating Gene Functions using Conditional Cas9 Stabilization
08:20

A New Toolkit for Evaluating Gene Functions using Conditional Cas9 Stabilization

Published on: September 2, 2021

4.1K

Area of Science:

  • Biotechnology
  • Protein Engineering
  • Computational Biology

Background:

  • Engineering stabilized proteins is crucial for industrial and pharmaceutical applications.
  • Existing methods face challenges with data scarcity, bias, generalization, and computation time.

Purpose of the Study:

  • To present Stability Oracle, a novel structure-based graph-transformer framework.
  • To achieve state-of-the-art (SOTA) performance in identifying thermodynamically stabilizing mutations.

Main Methods:

  • Developed a structure-based graph-transformer framework named Stability Oracle.
  • Introduced innovations: Thermodynamic Permutations for data augmentation, structural amino acid embeddings, and a protein structure-specific attention-bias mechanism.
  • Utilized training/test splits to mitigate data leakage and ensure robust model evaluation.

Main Results:

  • Stability Oracle achieves SOTA performance in identifying stabilizing mutations.
  • The framework outperforms sequence-based models like Prostata-IFML, despite being trained on significantly less data and having fewer parameters.
  • Demonstrated the effectiveness of structural amino acid embeddings and attention-bias mechanisms.

Conclusions:

  • Stability Oracle offers a powerful and efficient approach to protein stabilization.
  • The framework provides a viable path for fine-tuning structure-based transformers for various protein engineering tasks.
  • Accelerates the development of protein-based biotechnologies through accurate prediction of stabilizing mutations.