EUVIMEDEUVIMED entdecken
Crossref

TinyHLAnet : A Light‐Weight 3D Structure‐Aware Architecture for Rapid and Explainable Identification of CD8 + T‐Cell Antigens

Naren Chandran Sakthivel, Sumanta Mukherjee, Nagasuma Chandra iD

HLA · 2025

DOI: 10.1111/tan.70410 ↗

Kurz gefasst

Fachartikel in der Zeitschrift HLA, 2025. Verfasst von Naren Chandran Sakthivel und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry, Indian Institute of Science, Bangalore, Karnataka, India. Hauptthemen laut MEDLINE: CD8-Positive T-Lymphocytes, Epitopes, T-Lymphocyte, Deep Learning, Peptides. Die Arbeit nennt 55 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

CD8+ T cell response is contingent on the surveillance and recognition of peptide antigens presented on HLA class I molecules. The highly polymorphic nature of the HLA loci combined with the vast cognate peptide space makes comprehensive experimental characterisation of the peptides presented by different individuals in different disease conditions intractable. Several computational methods for epitope prediction exist, but there is a necessity in the field for rapid, interpretable and personalised prediction of CD8+ T cell epitopes. We address this gap by developing a novel deep learning architecture, termed TinyHLAnet, that produces highly accurate and fast prediction of peptide‐HLA (class I) complex formation. This architecture is developed using constraints derived from domain knowledge of contact formation in peptide‐HLA (class I) complexes. Specifically, the estimation of binding affinity of the peptide‐HLA complex is decomposed into subproblems relating to estimating the interaction strength of each intermolecular residue pair in the complex, which in itself is factorised into three different components based on knowledge of residue pair interactions. This compartmentalisation allows for the production of a model that uses a fraction of the parameters used by existing gold standard methods at no loss of prediction accuracy but provides much greater throughput. The TinyHLAnet prediction engine serves as a framework for several applications, with two examples shown here: TinyHLAnet‐SCAN, for proteome‐wide scanning of epitopes, and TinyHLAnet‐ESCAPE, for prediction of likely immune escape mutants.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CD8-Positive T-LymphocytesEpitopes, T-LymphocyteDeep LearningPeptidesComputational BiologyHistocompatibility Antigens Class ISoftwareHumansProtein Binding

Substanzen

Epitopes, T-LymphocytePeptidesHistocompatibility Antigens Class I

Autor:innen und Institutionen

  • Department of Biochemistry, Indian Institute of Science, Bangalore, Karnataka, India.
  • IBM Research, Bangalore, Karnataka, India.
  • Department of Bioengineering, Indian Institute of Science, Bangalore, Karnataka, India.

ORCID-Profile: Nagasuma Chandra

Zitieren

APA

Sakthivel, N. C., Mukherjee, S., & Chandra, N. (2025). TinyHLAnet : A Light‐Weight 3D Structure‐Aware Architecture for Rapid and Explainable Identification of CD8 + T‐Cell Antigens. HLA. https://doi.org/10.1111/tan.70410

Vancouver

Sakthivel NC, Mukherjee S, Chandra N. TinyHLAnet : A Light‐Weight 3D Structure‐Aware Architecture for Rapid and Explainable Identification of CD8 + T‐Cell Antigens. HLA. 2025. doi:10.1111/tan.70410

BibTeX
@article{Sakthivel2025,
  author = {Sakthivel, Naren Chandran and Mukherjee, Sumanta and Chandra, Nagasuma},
  title = {TinyHLAnet : A Light‐Weight 3D Structure‐Aware Architecture for Rapid and Explainable Identification of CD8 + T‐Cell Antigens},
  journal = {HLA},
  year = {2025},
  doi = {10.1111/tan.70410}
}
Kostenlos starten →