Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Covalently Linked Protein Regulators

Covalently Linked Protein Regulators

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....

You might also read

Related Articles

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

Sort by

Same author

Identification of drug candidates against glioblastoma with machine learning and high-throughput screening of heterogeneous cellular models.

Digital discovery·2026

Same author

Multiobjective Design of Growth Media with Genome-Scale Metabolic Models and Bayesian Optimization.

Computational and structural biotechnology journal·2026

Same author

Accurate prediction of gene deletion phenotypes with Flux Cone Learning.

Nature communications·2025

Same author

Barking up the right tree: Immune checkpoint signatures of human and dog cancers.

PLoS computational biology·2025

Same author

Improving the generalization of protein expression models with mechanistic sequence information.

Nucleic acids research·2025

Same author

Knowledge graph embeddings in the biomedical domain: are they useful? A look at link prediction, rule learning, and downstream polypharmacy tasks.

Bioinformatics advances·2024

Search research articles

Related Experiment Video

Updated: May 21, 2025

Tuning Degradation to Achieve Specific and Efficient Protein Depletion

Tuning Degradation to Achieve Specific and Efficient Protein Depletion

Published on: July 20, 2019

Tuning ProteinMPNN to reduce protein visibility via MHC Class I through direct preference optimization.

Hans-Christof Gasser¹, Diego A Oyarzún^1,2, Javier Antonio Alfaro^1,3,4,5

¹School of Informatics, University of Edinburgh, Edinburgh, EH8 9AB, United Kingdom.

Protein Engineering, Design & Selection : PEDS

|March 18, 2025

Summary

We adapted ProteinMPNN for protein design, reducing immune system visibility by minimizing cytotoxic T lymphocyte (CTL) epitopes. This method preserves protein structure while enhancing safety for therapeutic applications.

Keywords:

MHC Class I ProteinMPNN direct preference optimization protein deimmunization protein design

More Related Videos

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

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

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

Published on: July 14, 2015

Related Experiment Videos

Last Updated: May 21, 2025

Tuning Degradation to Achieve Specific and Efficient Protein Depletion

Tuning Degradation to Achieve Specific and Efficient Protein Depletion

Published on: July 20, 2019

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

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

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

Published on: July 14, 2015

Area of Science:

Computational Biology
Immunology
Protein Engineering

Background:

ProteinMPNN is a key tool for designing amino acid sequences that fold into specific 3D protein structures.
Cytotoxic T lymphocytes (CTLs) recognize foreign proteins via the Major Histocompatibility Complex class I (MHC-I) pathway, triggering immune responses.
Reducing the visibility of designed proteins to CTLs is crucial for developing safe and effective protein-based therapeutics.

Purpose of the Study:

To modify ProteinMPNN for designing proteins with reduced immunogenicity.
To decrease the presentation of epitopes recognized by CTLs through the MHC-I pathway.
To maintain the structural integrity of designed proteins while minimizing immune recognition.

Main Methods:

Integration of Direct Preference Optimization (DPO), a technique from large language models, into the protein design workflow.
Utilizing MHC-I peptide presentation prediction algorithms to guide the design process.
Iterative refinement of protein sequences to minimize predicted MHC-I epitopes.

Main Results:

Successful generation of protein designs with significantly reduced MHC-I epitope presentation.
Demonstration that the DPO-integrated framework effectively lowers immune visibility.
Confirmation that the structural integrity of the designed proteins is maintained.

Conclusions:

The novel framework successfully reduces protein immunogenicity by minimizing MHC-I epitope presentation.
Direct Preference Optimization is an effective method for fine-tuning protein design towards reduced immune recognition.
This approach holds promise for creating safer protein therapeutics with lower risks of immune rejection.