Cargando…

DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction

MOTIVATION: Computationally predicting major histocompatibility complex class I (MHC-I) peptide binding affinity is an important problem in immunological bioinformatics, which is also crucial for the identification of neoantigens for personalized therapeutic cancer vaccines. Recent cutting-edge deep...

Descripción completa

Detalles Bibliográficos
Autores principales: Qu, Wei, You, Ronghui, Mamitsuka, Hiroshi, Zhu, Shanfeng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10516514/
https://www.ncbi.nlm.nih.gov/pubmed/37669154
http://dx.doi.org/10.1093/bioinformatics/btad551
_version_ 1785109142747217920
author Qu, Wei
You, Ronghui
Mamitsuka, Hiroshi
Zhu, Shanfeng
author_facet Qu, Wei
You, Ronghui
Mamitsuka, Hiroshi
Zhu, Shanfeng
author_sort Qu, Wei
collection PubMed
description MOTIVATION: Computationally predicting major histocompatibility complex class I (MHC-I) peptide binding affinity is an important problem in immunological bioinformatics, which is also crucial for the identification of neoantigens for personalized therapeutic cancer vaccines. Recent cutting-edge deep learning-based methods for this problem cannot achieve satisfactory performance, especially for non-9-mer peptides. This is because such methods generate the input by simply concatenating the two given sequences: a peptide and (the pseudo sequence of) an MHC class I molecule, which cannot precisely capture the anchor positions of the MHC binding motif for the peptides with variable lengths. We thus developed an anchor position-aware and high-performance deep model, DeepMHCI, with a position-wise gated layer and a residual binding interaction convolution layer. This allows the model to control the information flow in peptides to be aware of anchor positions and model the interactions between peptides and the MHC pseudo (binding) sequence directly with multiple convolutional kernels. RESULTS: The performance of DeepMHCI has been thoroughly validated by extensive experiments on four benchmark datasets under various settings, such as 5-fold cross-validation, validation with the independent testing set, external HPV vaccine identification, and external CD8+ epitope identification. Experimental results with visualization of binding motifs demonstrate that DeepMHCI outperformed all competing methods, especially on non-9-mer peptides binding prediction. AVAILABILITY AND IMPLEMENTATION: DeepMHCI is publicly available at https://github.com/ZhuLab-Fudan/DeepMHCI.
format Online
Article
Text
id pubmed-10516514
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-105165142023-09-23 DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction Qu, Wei You, Ronghui Mamitsuka, Hiroshi Zhu, Shanfeng Bioinformatics Original Paper MOTIVATION: Computationally predicting major histocompatibility complex class I (MHC-I) peptide binding affinity is an important problem in immunological bioinformatics, which is also crucial for the identification of neoantigens for personalized therapeutic cancer vaccines. Recent cutting-edge deep learning-based methods for this problem cannot achieve satisfactory performance, especially for non-9-mer peptides. This is because such methods generate the input by simply concatenating the two given sequences: a peptide and (the pseudo sequence of) an MHC class I molecule, which cannot precisely capture the anchor positions of the MHC binding motif for the peptides with variable lengths. We thus developed an anchor position-aware and high-performance deep model, DeepMHCI, with a position-wise gated layer and a residual binding interaction convolution layer. This allows the model to control the information flow in peptides to be aware of anchor positions and model the interactions between peptides and the MHC pseudo (binding) sequence directly with multiple convolutional kernels. RESULTS: The performance of DeepMHCI has been thoroughly validated by extensive experiments on four benchmark datasets under various settings, such as 5-fold cross-validation, validation with the independent testing set, external HPV vaccine identification, and external CD8+ epitope identification. Experimental results with visualization of binding motifs demonstrate that DeepMHCI outperformed all competing methods, especially on non-9-mer peptides binding prediction. AVAILABILITY AND IMPLEMENTATION: DeepMHCI is publicly available at https://github.com/ZhuLab-Fudan/DeepMHCI. Oxford University Press 2023-09-05 /pmc/articles/PMC10516514/ /pubmed/37669154 http://dx.doi.org/10.1093/bioinformatics/btad551 Text en © The Author(s) 2023. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Paper
Qu, Wei
You, Ronghui
Mamitsuka, Hiroshi
Zhu, Shanfeng
DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction
title DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction
title_full DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction
title_fullStr DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction
title_full_unstemmed DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction
title_short DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction
title_sort deepmhci: an anchor position-aware deep interaction model for accurate mhc-i peptide binding affinity prediction
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10516514/
https://www.ncbi.nlm.nih.gov/pubmed/37669154
http://dx.doi.org/10.1093/bioinformatics/btad551
work_keys_str_mv AT quwei deepmhciananchorpositionawaredeepinteractionmodelforaccuratemhcipeptidebindingaffinityprediction
AT youronghui deepmhciananchorpositionawaredeepinteractionmodelforaccuratemhcipeptidebindingaffinityprediction
AT mamitsukahiroshi deepmhciananchorpositionawaredeepinteractionmodelforaccuratemhcipeptidebindingaffinityprediction
AT zhushanfeng deepmhciananchorpositionawaredeepinteractionmodelforaccuratemhcipeptidebindingaffinityprediction