Related Experiment Video
Updated: May 10, 2026
09:32
Immunopeptidomics: Isolation of Mouse and Human MHC Class I- and II-Associated Peptides for Mass Spectrometry Analysis
Published on: October 15, 2021
Exhaustive proteome mining for functional MHC-I ligands
Christian P Koch1, Anna M Perna, Sabrina Weissmüller
1Department of Chemistry and Applied Biosciences, Eidgenössische Technische Hochschule (ETH) , Wolfgang-Pauli-Str. 10, 8093 Zürich, Switzerland.
ACS Chemical Biology
|June 19, 2013
Summary
We developed a machine-learning method to find major histocompatibility complex class I (MHC-I) ligands. This approach aids in designing peptides for reverse vaccinology and understanding immune responses.
Area of Science:
- Immunology
- Computational Biology
- Bioinformatics
Background:
- Identifying Major Histocompatibility Complex class I (MHC-I) ligands is crucial for understanding T-cell mediated immunity.
- Current methods for identifying MHC-I ligands are often limited in scope and reliability.
Purpose of the Study:
- To develop and apply a novel machine-learning approach for comprehensive identification of MHC-I ligands.
- To computationally screen octapeptides and genome-derived proteomes for potential MHC-I binders.
- To explore the application of machine learning in rational peptide design for reverse vaccinology.
Main Methods:
- Developed a high-level machine-learning model to predict MHC-I binding octapeptides.
- Applied the model to analyze all possible octapeptides (20^8) and proteomes from Mus musculus, influenza A H3N8, and vesicular stomatitis virus (VSV).
- Validated predicted ligands by assessing direct MHC-I binding and stabilization on TAP-deficient RMA-S cells (murine H-2K(b)).
- Assessed the immunogenicity of computationally identified peptides in vivo.
Main Results:
- Successfully identified potent octapeptides with direct MHC-I binding and stabilization properties.
- VSV-derived peptides predicted by the model induced CD8(+) T-cell proliferation in mice post-infection.
- Demonstrated the model's capability to analyze large-scale proteomic data for MHC-I ligand discovery.
Conclusions:
- High-level machine-learning models offer efficient and reliable identification of MHC-I ligands.
- This approach enables rational design of peptides for immunological applications.
- The study presents a promising strategy for reverse vaccinology and vaccine development.
