Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide design

Summary: Predicting the binding of peptides to human leukocyte antigen (HLA) alleles is critical for identifying epitopes initiating immune responses in vaccine development and immunotherapies. Despite the progress in predicting binding peptides of 1% HLA class-I alleles with in silico prediction to...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinyuan Zhu, Jiadong Lu, Xinting Hu, Tengchuan Jin, Shan Lu, Fuli Feng
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Cell Reports
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2211124725005340
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183634201346048
author Xinyuan Zhu
Jiadong Lu
Xinting Hu
Tengchuan Jin
Shan Lu
Fuli Feng
author_facet Xinyuan Zhu
Jiadong Lu
Xinting Hu
Tengchuan Jin
Shan Lu
Fuli Feng
author_sort Xinyuan Zhu
collection DOAJ
description Summary: Predicting the binding of peptides to human leukocyte antigen (HLA) alleles is critical for identifying epitopes initiating immune responses in vaccine development and immunotherapies. Despite the progress in predicting binding peptides of 1% HLA class-I alleles with in silico prediction tools, it remains challenging to predict binding peptides for alleles lacking epitopes. To achieve the binding prediction on those zero-shot alleles, we developed a hierarchical progressive learning (HPL) framework that progressively learns sequence patterns of specific peptide-HLA complexes. HPL models improve the prediction performance for zero-shot HLA class-I alleles by 60.8% (1,414.0% for non-classical ones). We further developed an automated peptide mutation search program, which automatically identifies binding peptides for any target HLA class-I allele and mutates weak-binding or non-binding peptides to enhance binding affinity under the guidance of HPL models. Our program generated high-affinity binding candidates of any target allele with limited mutations in more than 38.1% of testing cases.
format Article
id doaj-art-770cc9803dfb44fd937f9dc775bc4b1f
institution OA Journals
issn 2211-1247
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Cell Reports
spelling doaj-art-770cc9803dfb44fd937f9dc775bc4b1f2025-08-20T02:17:19ZengElsevierCell Reports2211-12472025-06-0144611576310.1016/j.celrep.2025.115763Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide designXinyuan Zhu0Jiadong Lu1Xinting Hu2Tengchuan Jin3Shan Lu4Fuli Feng5School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, ChinaSchool of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, Anhui, ChinaSchool of Computer Science and Engineering, Nanyang Technological University, Singapore, SingaporeDivision of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, ChinaDepartment of Cellular and Molecular Medicine, University of California, San Diego, San Diego, CA, USA; Corresponding authorSchool of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, Anhui, China; Corresponding authorSummary: Predicting the binding of peptides to human leukocyte antigen (HLA) alleles is critical for identifying epitopes initiating immune responses in vaccine development and immunotherapies. Despite the progress in predicting binding peptides of 1% HLA class-I alleles with in silico prediction tools, it remains challenging to predict binding peptides for alleles lacking epitopes. To achieve the binding prediction on those zero-shot alleles, we developed a hierarchical progressive learning (HPL) framework that progressively learns sequence patterns of specific peptide-HLA complexes. HPL models improve the prediction performance for zero-shot HLA class-I alleles by 60.8% (1,414.0% for non-classical ones). We further developed an automated peptide mutation search program, which automatically identifies binding peptides for any target HLA class-I allele and mutates weak-binding or non-binding peptides to enhance binding affinity under the guidance of HPL models. Our program generated high-affinity binding candidates of any target allele with limited mutations in more than 38.1% of testing cases.http://www.sciencedirect.com/science/article/pii/S2211124725005340CP: Immunology
spellingShingle Xinyuan Zhu
Jiadong Lu
Xinting Hu
Tengchuan Jin
Shan Lu
Fuli Feng
Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide design
Cell Reports
CP: Immunology
title Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide design
title_full Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide design
title_fullStr Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide design
title_full_unstemmed Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide design
title_short Hierarchical progressive learning for zero-shot peptide-HLA binding prediction and automated antigenic peptide design
title_sort hierarchical progressive learning for zero shot peptide hla binding prediction and automated antigenic peptide design
topic CP: Immunology
url http://www.sciencedirect.com/science/article/pii/S2211124725005340
work_keys_str_mv AT xinyuanzhu hierarchicalprogressivelearningforzeroshotpeptidehlabindingpredictionandautomatedantigenicpeptidedesign
AT jiadonglu hierarchicalprogressivelearningforzeroshotpeptidehlabindingpredictionandautomatedantigenicpeptidedesign
AT xintinghu hierarchicalprogressivelearningforzeroshotpeptidehlabindingpredictionandautomatedantigenicpeptidedesign
AT tengchuanjin hierarchicalprogressivelearningforzeroshotpeptidehlabindingpredictionandautomatedantigenicpeptidedesign
AT shanlu hierarchicalprogressivelearningforzeroshotpeptidehlabindingpredictionandautomatedantigenicpeptidedesign
AT fulifeng hierarchicalprogressivelearningforzeroshotpeptidehlabindingpredictionandautomatedantigenicpeptidedesign