Machine learning application to predict binding affinity between peptide containing non-canonical amino acids and HLA-A0201
PLOS One · 2025
DOI: 10.1371/journal.pone.0314833 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Shan Jiang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry and Center for Structural Biology, Vanderbilt University, Nashville, Tennessee, United States of America. Hauptthemen laut MEDLINE: Machine Learning, Amino Acids, Peptides, HLA-A2 Antigen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDA NIH HHS, NHLBI NIH HHS, NIAID NIH HHS.
Abstract (Originalsprache)
Class Ι major histocompatibility complexes (MHC-Ι), encoded by the highly polymorphic HLA-A, HLA-B, and HLA-C genes in humans, are expressed on all nucleated cells. Both self and foreign proteins are processed to peptides of 8–10 amino acids, loaded into MHC-Ι, within the endoplasmic reticulum and then presented on the cell surface. Foreign peptides presented in this fashion activate CD8 + T cells and their immunogenicity correlates with their affinity for the MHC-Ι binding groove. Thus, predicting antigen binding affinity for MHC-Ι is a valuable tool for identifying potentially immunogenic antigens. While quite a few predictors for MHC-Ι binding exist, there are no currently available tools that can predict antigen/MHC-Ι binding affinity for antigens with explicitly labeled post-translational modifications or unusual/non-canonical amino acids (NCAAs). However, such modifications are increasingly recognized as critical mediators of peptide immunogenicity. In this work, we propose a machine learning application that quantifies the binding affinity of epitopes containing NCAAs to MHC-Ι and compares its performance with other commonly used regressors. Our model demonstrates robust performance, with 5-fold cross-validation yielding an R 2 value of 0.477 and a root-mean-square error (RMSE) of 0.735, indicating strong predictive capability for peptides with NCAAs. This work provides a valuable tool for the computational design and optimization of peptides incorporating NCAAs, potentially accelerating the development of novel peptide-based therapeutics with enhanced properties and efficacy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Chemistry and Center for Structural Biology, Vanderbilt University, Nashville, Tennessee, United States of America.
- Division of Clinical Pharmacology, Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.
- Institute for Drug Discovery, Institute for Computer Science, Wilhelm Ostwald Institute for Physical and Theoretical Chemistry, University Leipzig, Leipzig, Germany.
- Center for Scalable Data Analytics and Artificial Intelligence ScaDS.AI and School of Embedded Composite Artificial Intelligence SECAI, Dresden/Leipzig, Germany.
- Department of Pharmacology, Institute of Chemical Biology, Center for Applied Artificial Intelligence in Protein Dynamics, Vanderbilt University, Nashville, Tennessee, United States of America.
ORCID-Profile: Shan Jiang, Yunchao Liu, Jens Meiler
Förderung
- NIDA NIH HHS
- NHLBI NIH HHS
- NIAID NIH HHS
- NIH HHS
- NLM NIH HHS
- NIA NIH HHS
- NCI NIH HHS
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Jiang, S., Su, Z., Bloodworth, N., Liu, Y., Martina, C. E., Harrison, D. G., & Meiler, J. (2025). Machine learning application to predict binding affinity between peptide containing non-canonical amino acids and HLA-A0201. PLOS One. https://doi.org/10.1371/journal.pone.0314833
Vancouver
Jiang S, Su Z, Bloodworth N, Liu Y, Martina CE, Harrison DG, et al. Machine learning application to predict binding affinity between peptide containing non-canonical amino acids and HLA-A0201. PLOS One. 2025. doi:10.1371/journal.pone.0314833
BibTeX
@article{Jiang2025,
author = {Jiang, Shan and Su, Zhaoqian and Bloodworth, Nathaniel and Liu, Yunchao and Martina, Cristina E and Harrison, David G and Meiler, Jens},
title = {Machine learning application to predict binding affinity between peptide containing non-canonical amino acids and HLA-A0201},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0314833}
}
EUVIMED