Cargando…

Binding peptide generation for MHC Class I proteins with deep reinforcement learning

MOTIVATION: MHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs fo...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Ziqi, Zhang, Baoyi, Guo, Hongyu, Emani, Prashant, Clancy, Trevor, Jiang, Chongming, Gerstein, Mark, Ning, Xia, Cheng, Chao, Min, Martin Renqiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9907221/
https://www.ncbi.nlm.nih.gov/pubmed/36692135
http://dx.doi.org/10.1093/bioinformatics/btad055
_version_ 1784884131818110976
author Chen, Ziqi
Zhang, Baoyi
Guo, Hongyu
Emani, Prashant
Clancy, Trevor
Jiang, Chongming
Gerstein, Mark
Ning, Xia
Cheng, Chao
Min, Martin Renqiang
author_facet Chen, Ziqi
Zhang, Baoyi
Guo, Hongyu
Emani, Prashant
Clancy, Trevor
Jiang, Chongming
Gerstein, Mark
Ning, Xia
Cheng, Chao
Min, Martin Renqiang
author_sort Chen, Ziqi
collection PubMed
description MOTIVATION: MHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs for MHC Class I proteins, in vitro experiments have been conducted to screen peptides with high binding affinities to hundreds of given MHC Class I proteins. However, considering tens of thousands of known MHC Class I proteins, conducting in vitro experiments for extensive MHC proteins is infeasible, and thus a more efficient and scalable way to characterize binding motifs is needed. RESULTS: We presented a de novo generation framework, coined PepPPO, to characterize binding motif for any given MHC Class I proteins via generating repertoires of peptides presented by them. PepPPO leverages a reinforcement learning agent with a mutation policy to mutate random input peptides into positive presented ones. Using PepPPO, we characterized binding motifs for around 10 000 known human MHC Class I proteins with and without experimental data. These computed motifs demonstrated high similarities with those derived from experimental data. In addition, we found that the motifs could be used for the rapid screening of neoantigens at a much lower time cost than previous deep-learning methods. AVAILABILITY AND IMPLEMENTATION: The software can be found in https://github.com/minrq/pMHC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
format Online
Article
Text
id pubmed-9907221
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-99072212023-02-09 Binding peptide generation for MHC Class I proteins with deep reinforcement learning Chen, Ziqi Zhang, Baoyi Guo, Hongyu Emani, Prashant Clancy, Trevor Jiang, Chongming Gerstein, Mark Ning, Xia Cheng, Chao Min, Martin Renqiang Bioinformatics Original Paper MOTIVATION: MHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs for MHC Class I proteins, in vitro experiments have been conducted to screen peptides with high binding affinities to hundreds of given MHC Class I proteins. However, considering tens of thousands of known MHC Class I proteins, conducting in vitro experiments for extensive MHC proteins is infeasible, and thus a more efficient and scalable way to characterize binding motifs is needed. RESULTS: We presented a de novo generation framework, coined PepPPO, to characterize binding motif for any given MHC Class I proteins via generating repertoires of peptides presented by them. PepPPO leverages a reinforcement learning agent with a mutation policy to mutate random input peptides into positive presented ones. Using PepPPO, we characterized binding motifs for around 10 000 known human MHC Class I proteins with and without experimental data. These computed motifs demonstrated high similarities with those derived from experimental data. In addition, we found that the motifs could be used for the rapid screening of neoantigens at a much lower time cost than previous deep-learning methods. AVAILABILITY AND IMPLEMENTATION: The software can be found in https://github.com/minrq/pMHC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. Oxford University Press 2023-01-24 /pmc/articles/PMC9907221/ /pubmed/36692135 http://dx.doi.org/10.1093/bioinformatics/btad055 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
Chen, Ziqi
Zhang, Baoyi
Guo, Hongyu
Emani, Prashant
Clancy, Trevor
Jiang, Chongming
Gerstein, Mark
Ning, Xia
Cheng, Chao
Min, Martin Renqiang
Binding peptide generation for MHC Class I proteins with deep reinforcement learning
title Binding peptide generation for MHC Class I proteins with deep reinforcement learning
title_full Binding peptide generation for MHC Class I proteins with deep reinforcement learning
title_fullStr Binding peptide generation for MHC Class I proteins with deep reinforcement learning
title_full_unstemmed Binding peptide generation for MHC Class I proteins with deep reinforcement learning
title_short Binding peptide generation for MHC Class I proteins with deep reinforcement learning
title_sort binding peptide generation for mhc class i proteins with deep reinforcement learning
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9907221/
https://www.ncbi.nlm.nih.gov/pubmed/36692135
http://dx.doi.org/10.1093/bioinformatics/btad055
work_keys_str_mv AT chenziqi bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT zhangbaoyi bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT guohongyu bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT emaniprashant bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT clancytrevor bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT jiangchongming bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT gersteinmark bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT ningxia bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT chengchao bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning
AT minmartinrenqiang bindingpeptidegenerationformhcclassiproteinswithdeepreinforcementlearning