Improved prediction of MHC-peptide binding using protein language models
Major histocompatibility complex Class I (MHC-I) molecules bind to peptides derived from intracellular antigens and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipu...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Bioinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbinf.2023.1207380/full |
| _version_ | 1797741443008167936 |
|---|---|
| author | Nasser Hashemi Boran Hao Mikhail Ignatov Mikhail Ignatov Ioannis Ch. Paschalidis Ioannis Ch. Paschalidis Ioannis Ch. Paschalidis Pirooz Vakili Sandor Vajda Sandor Vajda Sandor Vajda Dima Kozakov Dima Kozakov Dima Kozakov |
| author_facet | Nasser Hashemi Boran Hao Mikhail Ignatov Mikhail Ignatov Ioannis Ch. Paschalidis Ioannis Ch. Paschalidis Ioannis Ch. Paschalidis Pirooz Vakili Sandor Vajda Sandor Vajda Sandor Vajda Dima Kozakov Dima Kozakov Dima Kozakov |
| author_sort | Nasser Hashemi |
| collection | DOAJ |
| description | Major histocompatibility complex Class I (MHC-I) molecules bind to peptides derived from intracellular antigens and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipulation of the cellular immune system. Predicting whether a given peptide binds to an MHC molecule is an important step in the above process and has motivated the introduction of many computational approaches to address this problem. NetMHCPan, a pan-specific model for predicting binding of peptides to any MHC molecule, is one of the most widely used methods which focuses on solving this binary classification problem using shallow neural networks. The recent successful results of Deep Learning (DL) methods, especially Natural Language Processing (NLP-based) pretrained models in various applications, including protein structure determination, motivated us to explore their use in this problem. Specifically, we consider the application of deep learning models pretrained on large datasets of protein sequences to predict MHC Class I-peptide binding. Using the standard performance metrics in this area, and the same training and test sets, we show that our models outperform NetMHCpan4.1, currently considered as the-state-of-the-art. |
| first_indexed | 2024-03-12T14:26:47Z |
| format | Article |
| id | doaj.art-e4ac602f29ef4f8cb40a092b72c4058b |
| institution | Directory Open Access Journal |
| issn | 2673-7647 |
| language | English |
| last_indexed | 2024-03-12T14:26:47Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioinformatics |
| spelling | doaj.art-e4ac602f29ef4f8cb40a092b72c4058b2023-08-18T05:12:08ZengFrontiers Media S.A.Frontiers in Bioinformatics2673-76472023-08-01310.3389/fbinf.2023.12073801207380Improved prediction of MHC-peptide binding using protein language modelsNasser Hashemi0Boran Hao1Mikhail Ignatov2Mikhail Ignatov3Ioannis Ch. Paschalidis4Ioannis Ch. Paschalidis5Ioannis Ch. Paschalidis6Pirooz Vakili7Sandor Vajda8Sandor Vajda9Sandor Vajda10Dima Kozakov11Dima Kozakov12Dima Kozakov13Division of Systems Engineering, Boston University, Boston, MA, United StatesDepartment of Electrical and Computer Engineering, Boston University, Boston, MA, United StatesDepartment of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, United StatesLaufer Center for Physical and Quantitative Biology, Stony Brook University, Stony Brook, NY, United StatesDivision of Systems Engineering, Boston University, Boston, MA, United StatesDepartment of Electrical and Computer Engineering, Boston University, Boston, MA, United StatesDepartment of Biomedical Engineering, Boston University, Boston, MA, United StatesDivision of Systems Engineering, Boston University, Boston, MA, United StatesDivision of Systems Engineering, Boston University, Boston, MA, United StatesDepartment of Biomedical Engineering, Boston University, Boston, MA, United StatesDepartment of Chemistry, Boston University, Boston, MA, United StatesDepartment of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, United StatesLaufer Center for Physical and Quantitative Biology, Stony Brook University, Stony Brook, NY, United StatesDepartment of Biomedical Engineering, Boston University, Boston, MA, United StatesMajor histocompatibility complex Class I (MHC-I) molecules bind to peptides derived from intracellular antigens and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipulation of the cellular immune system. Predicting whether a given peptide binds to an MHC molecule is an important step in the above process and has motivated the introduction of many computational approaches to address this problem. NetMHCPan, a pan-specific model for predicting binding of peptides to any MHC molecule, is one of the most widely used methods which focuses on solving this binary classification problem using shallow neural networks. The recent successful results of Deep Learning (DL) methods, especially Natural Language Processing (NLP-based) pretrained models in various applications, including protein structure determination, motivated us to explore their use in this problem. Specifically, we consider the application of deep learning models pretrained on large datasets of protein sequences to predict MHC Class I-peptide binding. Using the standard performance metrics in this area, and the same training and test sets, we show that our models outperform NetMHCpan4.1, currently considered as the-state-of-the-art.https://www.frontiersin.org/articles/10.3389/fbinf.2023.1207380/fullMHC class Ideep learningtransformersnatural language processingcellular immune system |
| spellingShingle | Nasser Hashemi Boran Hao Mikhail Ignatov Mikhail Ignatov Ioannis Ch. Paschalidis Ioannis Ch. Paschalidis Ioannis Ch. Paschalidis Pirooz Vakili Sandor Vajda Sandor Vajda Sandor Vajda Dima Kozakov Dima Kozakov Dima Kozakov Improved prediction of MHC-peptide binding using protein language models Frontiers in Bioinformatics MHC class I deep learning transformers natural language processing cellular immune system |
| title | Improved prediction of MHC-peptide binding using protein language models |
| title_full | Improved prediction of MHC-peptide binding using protein language models |
| title_fullStr | Improved prediction of MHC-peptide binding using protein language models |
| title_full_unstemmed | Improved prediction of MHC-peptide binding using protein language models |
| title_short | Improved prediction of MHC-peptide binding using protein language models |
| title_sort | improved prediction of mhc peptide binding using protein language models |
| topic | MHC class I deep learning transformers natural language processing cellular immune system |
| url | https://www.frontiersin.org/articles/10.3389/fbinf.2023.1207380/full |
| work_keys_str_mv | AT nasserhashemi improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT boranhao improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT mikhailignatov improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT mikhailignatov improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT ioannischpaschalidis improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT ioannischpaschalidis improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT ioannischpaschalidis improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT piroozvakili improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT sandorvajda improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT sandorvajda improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT sandorvajda improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT dimakozakov improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT dimakozakov improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels AT dimakozakov improvedpredictionofmhcpeptidebindingusingproteinlanguagemodels |