EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Ziqi Chen, Baoyi Zhang, Hongyu Guo, Prashant Emani, Trevor Clancy, Chongming Jiang, Mark Gerstein, Xia Ning iD, Chao Cheng iD, Martin Renqiang Min

Bioinformatics · 03.02.2023 · 39 (2)

DOI: 10.1093/bioinformatics/btad055 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 24.01.2023. Verfasst von Ziqi Chen und 9 weiteren Autor:innen. Beteiligte Einrichtung: Machine Learning Department, NEC Labs America, Princeton, NJ 08540, USA. Hauptthemen laut MEDLINE: Peptides, Histocompatibility Antigens Class I. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PeptidesHistocompatibility Antigens Class IHumansProtein BindingSoftware

Substanzen

PeptidesHistocompatibility Antigens Class I

Autor:innen und Institutionen

  • Machine Learning Department, NEC Labs America, Princeton, NJ 08540, USA.
  • Computer Science and Engineering Department, The Ohio State University, Columbus, OH 43210, USA.
  • Chemical and Biomolecular Engineering Department, Rice University, Houston, TX 77005, USA.
  • Digital Technologies Research Centre, National Research Council Canada, Ottawa, ON K1A 0R6, Canada.
  • School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada.
  • School of Medicine, Yale University, New Haven, CT 06520, USA.

ORCID-Profile: Xia Ning, Chao Cheng

Förderung

  • National Science Foundation

Zitieren

APA

Chen, Z., Zhang, B., Guo, H., Emani, P., Clancy, T., Jiang, C., Gerstein, M., Ning, X., Cheng, C., & Min, M. R. (2023). Binding peptide generation for MHC Class I proteins with deep reinforcement learning. Bioinformatics, 39(2). https://doi.org/10.1093/bioinformatics/btad055

Vancouver

Chen Z, Zhang B, Guo H, Emani P, Clancy T, Jiang C, et al. Binding peptide generation for MHC Class I proteins with deep reinforcement learning. Bioinformatics. 2023;39(2). doi:10.1093/bioinformatics/btad055

BibTeX
@article{Chen2023,
  author = {Chen, Ziqi and Zhang, Baoyi and Guo, Hongyu and Emani, Prashant and Clancy, Trevor and Jiang, Chongming and Gerstein, Mark and Ning, Xia and Cheng, Chao and Min, Martin Renqiang},
  title = {Binding peptide generation for MHC Class I proteins with deep reinforcement learning},
  journal = {Bioinformatics},
  year = {2023},
  volume = {39},
  number = {2},
  doi = {10.1093/bioinformatics/btad055}
}
Kostenlos starten →