EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A modular protein language modelling approach to immunogenicity prediction

Hugh O'Brien iD, Max Salm, Laura T Morton, Maciej Szukszto, Felix O'Farrell, Charlotte Boulton, Laurence King, Supreet Kaur Bola iD, Pablo D Becker, Andrew Craig, Morten Nielsen, Yardena Samuels und 4 weitere

PLOS Computational Biology · 11.11.2024 · 20 (11) · e1012511

DOI: 10.1371/journal.pcbi.1012511 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 11.11.2024. Verfasst von Hugh O'Brien und 15 weiteren Autor:innen. Beteiligte Einrichtung: Achilles Therapeutics UK Ltd, United Kingdom. Hauptthemen laut MEDLINE: Computational Biology. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union's Horizon 2020, Horizon 2020 Framework Programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neoantigen immunogenicity prediction is a highly challenging problem in the development of personalised medicines. Low reactivity rates in called neoantigens result in a difficult prediction scenario with limited training datasets. Here we describe ImmugenX, a modular protein language modelling approach to immunogenicity prediction for CD8+ reactive epitopes. ImmugenX comprises of a pMHC encoding module trained on three pMHC prediction tasks, an optional TCR encoding module and a set of context specific immunogenicity prediction head modules. Compared with state-of-the-art models for each task, ImmugenX’s encoding module performs comparably or better on pMHC binding affinity, eluted ligand prediction and stability tasks. ImmugenX outperforms all compared models on pMHC immunogenicity prediction (Area under the receiver operating characteristic curve = 0.619, average precision: 0.514), with a 7% increase in average precision compared to the next best model. ImmugenX shows further improved performance on immunogenicity prediction with the integration of TCR context information. ImmugenX performance is further analysed for interpretability, which locates areas of weakness found across existing immunogenicity models and highlight possible biases in public datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyHumansCD8-Positive T-LymphocytesReceptors, Antigen, T-CellModels, Molecular

Substanzen

Receptors, Antigen, T-Cell

Autor:innen und Institutionen

  • Achilles Therapeutics UK Ltd, United Kingdom.
  • Research Department of Haematology, UCL Cancer Institute, University College London, London, United Kingdom.
  • Technical University of Denmark, Lyngby, Denmark.
  • Weizmann Institute of Science, Rehovot, Israel.
  • The Francis Crick Institute, London, United Kingdom.
  • Department of Developmental Biology and Cancer, Great Ormond Street Institute of Child Health, UCL.

ORCID-Profile: Hugh O'Brien, Supreet Kaur Bola, Sergio A Quezada

Förderung

  • European Union's Horizon 2020
  • Horizon 2020 Framework Programme

Zitieren

APA

O'Brien, H., Salm, M., Morton, L. T., Szukszto, M., O'Farrell, F., Boulton, C., King, L., Bola, S. K., Becker, P. D., Craig, A., Nielsen, M., Samuels, Y., Swanton, C., Mansour, M. R., Hadrup, S. R., & Quezada, S. A. (2024). A modular protein language modelling approach to immunogenicity prediction. PLOS Computational Biology, 20(11), e1012511. https://doi.org/10.1371/journal.pcbi.1012511

Vancouver

O'Brien H, Salm M, Morton LT, Szukszto M, O'Farrell F, Boulton C, et al. A modular protein language modelling approach to immunogenicity prediction. PLOS Computational Biology. 2024;20(11):e1012511. doi:10.1371/journal.pcbi.1012511

BibTeX
@article{OBrien2024,
  author = {O'Brien, Hugh and Salm, Max and Morton, Laura T and Szukszto, Maciej and O'Farrell, Felix and Boulton, Charlotte and King, Laurence and Bola, Supreet Kaur and Becker, Pablo D and Craig, Andrew and Nielsen, Morten and Samuels, Yardena and Swanton, Charles and Mansour, Marc R and Hadrup, Sine Reker and Quezada, Sergio A},
  title = {A modular protein language modelling approach to immunogenicity prediction},
  journal = {PLOS Computational Biology},
  year = {2024},
  volume = {20},
  number = {11},
  pages = {e1012511},
  doi = {10.1371/journal.pcbi.1012511}
}
Kostenlos starten →