EUVIMEDEUVIMED entdecken
Open Access

Self-supervised learning of T cell receptor sequences exposes core properties for T cell membership

Romi Goldner Kabeli iD, Sarit Zevin, Avital Abargel iD, Alona Zilberberg, Sol Efroni iD

Science Advances · 2024

DOI: 10.1126/sciadv.adk4670 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, 2024. Verfasst von Romi Goldner Kabeli und 4 weiteren Autor:innen. Beteiligte Einrichtung: The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel. Hauptthemen laut MEDLINE: Receptors, Antigen, T-Cell, T-Lymphocytes. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 107 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The T cell receptor (TCR) repertoire is an extraordinarily diverse collection of TCRs essential for maintaining the body’s homeostasis and response to threats. In this study, we compiled an extensive dataset of more than 4200 bulk TCR repertoire samples, encompassing 221,176,713 sequences, alongside 6,159,652 single-cell TCR sequences from over 400 samples. From this dataset, we then selected a representative subset of 5 million bulk sequences and 4.2 million single-cell sequences to train two specialized Transformer-based language models for bulk (CVC) and single-cell (scCVC) TCR repertoires, respectively. We show that these models successfully capture TCR core qualities, such as sharing, gene composition, and single-cell properties. These qualities are emergent in the encoded TCR latent space and enable classification into TCR-based qualities such as public sequences. These models demonstrate the potential of Transformer-based language models in TCR downstream applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Receptors, Antigen, T-CellT-LymphocytesHumansSupervised Machine LearningSingle-Cell AnalysisComputational Biology

Substanzen

Receptors, Antigen, T-Cell

Autor:innen und Institutionen

  • The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel.

ORCID-Profile: Romi Goldner Kabeli, Avital Abargel, Sol Efroni

Zitieren

APA

Goldner Kabeli, R., Zevin, S., Abargel, A., Zilberberg, A., & Efroni, S. (2024). Self-supervised learning of T cell receptor sequences exposes core properties for T cell membership. Science Advances. https://doi.org/10.1126/sciadv.adk4670

Vancouver

Goldner Kabeli R, Zevin S, Abargel A, Zilberberg A, Efroni S. Self-supervised learning of T cell receptor sequences exposes core properties for T cell membership. Science Advances. 2024. doi:10.1126/sciadv.adk4670

BibTeX
@article{GoldnerKabeli2024,
  author = {Goldner Kabeli, Romi and Zevin, Sarit and Abargel, Avital and Zilberberg, Alona and Efroni, Sol},
  title = {Self-supervised learning of T cell receptor sequences exposes core properties for T cell membership},
  journal = {Science Advances},
  year = {2024},
  doi = {10.1126/sciadv.adk4670}
}
Kostenlos starten →