ESMpHLA : Evolutionary Scale Model‐Based Deep Learning Prediction of HLA Class I Binding Peptides
HLA · 2025
DOI: 10.1111/tan.70263 ↗Kurz gefasst
Fachartikel in der Zeitschrift HLA, 2025. Verfasst von Xiaorui Cheng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Biorheological Science and Technology (Ministry of Education), College of Bioengineering, Chongqing University, Chongqing, China. Hauptthemen laut MEDLINE: Deep Learning, Peptides, Histocompatibility Antigens Class I, HLA-A Antigens. Die Arbeit nennt 25 Literaturangaben. Gefördert von: Key Projects of Technological Innovation and Application Development of Chongqing, Graduate Scientific Research and Innovation Foundation of Chongqing, Graduate School, Chongqing University.
Abstract (Originalsprache)
The recognition of endogenous peptides by HLA class I plays a crucial role in CD8+ T cell immune responses and human adaptive cell immune. Thus, the prediction of HLA class I‐peptide binding affinities is always the core issue for the research of immune recognition and vaccine development. In this study, an evolutionary scale model (ESM) combined with parallel CNN blocks and a cross attention mechanism was used to construct a novel ESMpHLA model for predicting HLA class I binding peptides. Based on the 91,560 binding peptides of 41 HLA‐A alleles, 56,731 of 50 HLA‐B alleles and 2444 of 10 HLA‐C alleles, the ESMpHLA model was successfully established and achieved satisfying prediction performances with the overall accuracy and AUC values of 0.874 and 0.938 for the test dataset. The results indicate that the ESMpHLA model performs well in dealing with different HLA class I 2‐field alleles as well as the peptides with different lengths. Then, the generalisation ability of the ESMpHLA model was validated by an independent test dataset compiled from recent IEDB weekly benchmark datasets. The results showed that the ESMpHLA model achieved the highest ROC‐AUC and PR‐AUC values when compared with the latest BVMHC, CapsNet‐MHC, STMHCpan and BVLSTM models. In addition, two ensemble models were also established by integrating the above 5 deep learning models using soft‐voting and hard‐voting strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Key Laboratory of Biorheological Science and Technology (Ministry of Education), College of Bioengineering, Chongqing University, Chongqing, China.
- College of Bioengineering, Chongqing University, Chongqing, China.
ORCID-Profile: Hu Mei, Pingqing Wang
Förderung
- Key Projects of Technological Innovation and Application Development of Chongqing
- Graduate Scientific Research and Innovation Foundation of Chongqing
- Graduate School, Chongqing University
Zitieren
APA
Cheng, X., Mei, H., Chen, P., Wu, H., Liu, R., Lei, Y., & Wang, P. (2025). ESMpHLA : Evolutionary Scale Model‐Based Deep Learning Prediction of HLA Class I Binding Peptides. HLA. https://doi.org/10.1111/tan.70263
Vancouver
Cheng X, Mei H, Chen P, Wu H, Liu R, Lei Y, et al. ESMpHLA : Evolutionary Scale Model‐Based Deep Learning Prediction of HLA Class I Binding Peptides. HLA. 2025. doi:10.1111/tan.70263
BibTeX
@article{Cheng2025,
author = {Cheng, Xiaorui and Mei, Hu and Chen, Pengji and Wu, Haixia and Liu, Rui and Lei, Yuanyuan and Wang, Pingqing},
title = {ESMpHLA : Evolutionary Scale Model‐Based Deep Learning Prediction of HLA Class I Binding Peptides},
journal = {HLA},
year = {2025},
doi = {10.1111/tan.70263}
}
EUVIMED