OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction

The key roles of Major Histocompatibility Complex (MHC) Class I and II molecules in the immune system are well established. This study aims to develop a novel machine learning framework for predicting antigen peptide presentation by MHC Class I and II molecules. By integrating large-scale mass spect...

Full description

Saved in:
Bibliographic Details
Main Authors: Fangfang Jian, Haihua Cai, Qushuo Chen, Xiaoyong Pan, Weiwei Feng, Ye Yuan
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in Immunology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fimmu.2025.1550252/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850044342874406912
author Fangfang Jian
Haihua Cai
Qushuo Chen
Xiaoyong Pan
Weiwei Feng
Ye Yuan
Ye Yuan
author_facet Fangfang Jian
Haihua Cai
Qushuo Chen
Xiaoyong Pan
Weiwei Feng
Ye Yuan
Ye Yuan
author_sort Fangfang Jian
collection DOAJ
description The key roles of Major Histocompatibility Complex (MHC) Class I and II molecules in the immune system are well established. This study aims to develop a novel machine learning framework for predicting antigen peptide presentation by MHC Class I and II molecules. By integrating large-scale mass spectrometry data and other relevant data types, we present a prediction model OnmiMHC based on deep learning. We rigorously assessed its performance using an independent test set, OnmiMHC achieves a PR-AUC score of 0.854 and a TOP20%-PPV of 0.934 in the MHC-I task, which outperforms existing methods. Likewise, in the domain of MHC-II prediction, our model OnmiMHC exhibits a PR-AUC score of 0.606 and a TOP20%-PPV of 0.690, outperforming other baseline methods. These results demonstrate the superiority of our model OnmiMHC in accurately predicting peptide-MHC binding affinities across both MHC-I and MHC-II molecules. With its superior accuracy and predictive capability, our model not only excels in general predictive tasks but also achieves significant results in the prediction of neoantigens for specific cancer types. Particularly for Uterine Corpus Endometrial Carcinoma (UCEC), our model has successfully predicted neoantigens with a high binding probability to common human alleles. This discovery is of great significance for the development of personalized tumor vaccines targeting UCEC.
format Article
id doaj-art-acd2eb230ea346e79c206477ee6366a9
institution DOAJ
issn 1664-3224
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Immunology
spelling doaj-art-acd2eb230ea346e79c206477ee6366a92025-08-20T02:54:59ZengFrontiers Media S.A.Frontiers in Immunology1664-32242025-02-011610.3389/fimmu.2025.15502521550252OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding predictionFangfang Jian0Haihua Cai1Qushuo Chen2Xiaoyong Pan3Weiwei Feng4Ye Yuan5Ye Yuan6Department of Obstetrics and Gynecology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDigitalGene, Ltd, Shanghai, ChinaDigitalGene, Ltd, Shanghai, ChinaInstitute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, and Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, ChinaDepartment of Obstetrics and Gynecology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaKey Laboratory of Biopharmaceutical Preparation and Delivery, Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Biochemical Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing, ChinaThe key roles of Major Histocompatibility Complex (MHC) Class I and II molecules in the immune system are well established. This study aims to develop a novel machine learning framework for predicting antigen peptide presentation by MHC Class I and II molecules. By integrating large-scale mass spectrometry data and other relevant data types, we present a prediction model OnmiMHC based on deep learning. We rigorously assessed its performance using an independent test set, OnmiMHC achieves a PR-AUC score of 0.854 and a TOP20%-PPV of 0.934 in the MHC-I task, which outperforms existing methods. Likewise, in the domain of MHC-II prediction, our model OnmiMHC exhibits a PR-AUC score of 0.606 and a TOP20%-PPV of 0.690, outperforming other baseline methods. These results demonstrate the superiority of our model OnmiMHC in accurately predicting peptide-MHC binding affinities across both MHC-I and MHC-II molecules. With its superior accuracy and predictive capability, our model not only excels in general predictive tasks but also achieves significant results in the prediction of neoantigens for specific cancer types. Particularly for Uterine Corpus Endometrial Carcinoma (UCEC), our model has successfully predicted neoantigens with a high binding probability to common human alleles. This discovery is of great significance for the development of personalized tumor vaccines targeting UCEC.https://www.frontiersin.org/articles/10.3389/fimmu.2025.1550252/fullpeptide-MHC bindingMHC I and IIdeep learninguterine corpus endometrial carcinomaneoantigen
spellingShingle Fangfang Jian
Haihua Cai
Qushuo Chen
Xiaoyong Pan
Weiwei Feng
Ye Yuan
Ye Yuan
OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction
Frontiers in Immunology
peptide-MHC binding
MHC I and II
deep learning
uterine corpus endometrial carcinoma
neoantigen
title OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction
title_full OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction
title_fullStr OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction
title_full_unstemmed OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction
title_short OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction
title_sort onmimhc a machine learning solution for ucec tumor vaccine development through enhanced peptide mhc binding prediction
topic peptide-MHC binding
MHC I and II
deep learning
uterine corpus endometrial carcinoma
neoantigen
url https://www.frontiersin.org/articles/10.3389/fimmu.2025.1550252/full
work_keys_str_mv AT fangfangjian onmimhcamachinelearningsolutionforucectumorvaccinedevelopmentthroughenhancedpeptidemhcbindingprediction
AT haihuacai onmimhcamachinelearningsolutionforucectumorvaccinedevelopmentthroughenhancedpeptidemhcbindingprediction
AT qushuochen onmimhcamachinelearningsolutionforucectumorvaccinedevelopmentthroughenhancedpeptidemhcbindingprediction
AT xiaoyongpan onmimhcamachinelearningsolutionforucectumorvaccinedevelopmentthroughenhancedpeptidemhcbindingprediction
AT weiweifeng onmimhcamachinelearningsolutionforucectumorvaccinedevelopmentthroughenhancedpeptidemhcbindingprediction
AT yeyuan onmimhcamachinelearningsolutionforucectumorvaccinedevelopmentthroughenhancedpeptidemhcbindingprediction
AT yeyuan onmimhcamachinelearningsolutionforucectumorvaccinedevelopmentthroughenhancedpeptidemhcbindingprediction