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

Conservation of Protein Domains02:26

Conservation of Protein Domains

3.1K
3.1K
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

You might also read

Related Articles

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

Sort by
Same author

Autonomous biomedical research with an artificial intelligence agent.

Science (New York, N.Y.)·2026
Same author

Enhanced Gait Variability Index in Neurological and Geriatric Rehabilitation: A Scoping Review.

NeuroRehabilitation·2026
Same author

Generalizable AI predicts immunotherapy outcomes across cancers and treatments.

Nature medicine·2026
Same author

OpenIO: An open framework for AI-native immunotherapy.

Cancer cell·2026
Same author

AS-IV attenuates nigral NLRP3 inflammasome in a Parkinson's disease mouse model via gut microbiota.

Communications biology·2026
Same author

Mo/NiCu Heterometallic Interfaces for the Selective Electrosynthesis of Nitrite from Ammonia.

ACS applied materials & interfaces·2026

Related Experiment Video

Updated: Jun 7, 2025

Patterning Bioactive Proteins or Peptides on Hydrogel Using Photochemistry for Biological Applications
09:19

Patterning Bioactive Proteins or Peptides on Hydrogel Using Photochemistry for Biological Applications

Published on: September 15, 2017

7.2K

FoldMark: Safeguarding Protein Structure Generative Models with Distributional and Evolutionary Watermarking.

Zaixi Zhang1, Ruofan Jin1, Kaidi Fu2

  • 1Princeton University, Princeton, NJ, USA.

Biorxiv : the Preprint Server for Biology
|November 18, 2024
PubMed
Summary

This study introduces FoldMark, a novel watermarking technique for generative AI models used in protein structure prediction and design. FoldMark embeds invisible copyright information into protein structures, ensuring authenticity and traceability while maintaining structural integrity.

More Related Videos

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
07:08

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

7.2K
Author Spotlight: Photo Switchable Protein Recruitment for Reversible Patterning in Artificial Cellular Systems
07:10

Author Spotlight: Photo Switchable Protein Recruitment for Reversible Patterning in Artificial Cellular Systems

Published on: February 23, 2024

1.1K

Related Experiment Videos

Last Updated: Jun 7, 2025

Patterning Bioactive Proteins or Peptides on Hydrogel Using Photochemistry for Biological Applications
09:19

Patterning Bioactive Proteins or Peptides on Hydrogel Using Photochemistry for Biological Applications

Published on: September 15, 2017

7.2K
Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
07:08

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

7.2K
Author Spotlight: Photo Switchable Protein Recruitment for Reversible Patterning in Artificial Cellular Systems
07:10

Author Spotlight: Photo Switchable Protein Recruitment for Reversible Patterning in Artificial Cellular Systems

Published on: February 23, 2024

1.1K

Area of Science:

  • Computational Biology
  • Artificial Intelligence
  • Biotechnology

Background:

  • Protein structure is fundamental to function, driving advancements in drug discovery and bioengineering.
  • Generative AI has significantly enhanced protein structure prediction and design capabilities.
  • Ethical concerns, including copyright and biosecurity, hinder the widespread adoption of protein generative models.

Purpose of the Study:

  • To investigate the feasibility of embedding watermarks into protein generative models and their outputs.
  • To develop a method for copyright authentication and tracking of AI-generated protein structures.
  • To address ethical challenges associated with protein generative AI.

Main Methods:

  • Proposed a two-stage watermarking strategy named FoldMark.
  • Pretrained watermark encoder and decoder to embed and recover user-specific information in protein structures.
  • Fine-tuned generative models using Low-Rank Adaptation (LoRA) with watermarks as a condition.

Main Results:

  • FoldMark demonstrated effectiveness across various protein structure prediction (ESMFold, MultiFlow) and design models (FrameDiff, FoldFlow).
  • The watermarking process had a negligible impact on the quality of the generated protein structures.
  • The proposed framework proved robust against post-processing and adaptive attacks.

Conclusions:

  • FoldMark offers a viable solution for copyright protection and traceability in protein generative AI.
  • The method successfully integrates watermarking without compromising the performance or quality of generative models.
  • This approach facilitates the responsible development and deployment of advanced protein design technologies.