EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Large scale paired antibody language models

Henry Kenlay, Frédéric A Dreyer iD, Aleksandr Kovaltsuk, Dom Miketa, Douglas Pires iD, Charlotte M Deane

PLOS Computational Biology · 06.12.2024 · 20 (12) · e1012646

DOI: 10.1371/journal.pcbi.1012646 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 06.12.2024. Verfasst von Henry Kenlay und 5 weiteren Autor:innen. Beteiligte Einrichtung: Exscientia, Oxford Science Park, Oxford, United Kingdom. Hauptthemen laut MEDLINE: Antibodies, Computational Biology. Die Arbeit wurde bisher 74-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Antibodies are proteins produced by the immune system that can identify and neutralise a wide variety of antigens with high specificity and affinity, and constitute the most successful class of biotherapeutics. With the advent of next-generation sequencing, billions of antibody sequences have been collected in recent years, though their application in the design of better therapeutics has been constrained by the sheer volume and complexity of the data. To address this challenge, we present IgBert and IgT5, the best performing antibody-specific language models developed to date which can consistently handle both paired and unpaired variable region sequences as input. These models are trained comprehensively using the more than two billion unpaired sequences and two million paired sequences of light and heavy chains present in the Observed Antibody Space dataset. We show that our models outperform existing antibody and protein language models on a diverse range of design and regression tasks relevant to antibody engineering. This advancement marks a significant leap forward in leveraging machine learning, large scale data sets and high-performance computing for enhancing antibody design for therapeutic development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AntibodiesComputational BiologyHumansMachine LearningHigh-Throughput Nucleotide SequencingAlgorithms

Substanzen

Antibodies

Autor:innen und Institutionen

  • Exscientia, Oxford Science Park, Oxford, United Kingdom.
  • Department of Statistics, University of Oxford, Oxford, United Kingdom.

ORCID-Profile: Frédéric A Dreyer, Douglas Pires

Zitieren

APA

Kenlay, H., Dreyer, F. A., Kovaltsuk, A., Miketa, D., Pires, D., & Deane, C. M. (2024). Large scale paired antibody language models. PLOS Computational Biology, 20(12), e1012646. https://doi.org/10.1371/journal.pcbi.1012646

Vancouver

Kenlay H, Dreyer FA, Kovaltsuk A, Miketa D, Pires D, Deane CM. Large scale paired antibody language models. PLOS Computational Biology. 2024;20(12):e1012646. doi:10.1371/journal.pcbi.1012646

BibTeX
@article{Kenlay2024,
  author = {Kenlay, Henry and Dreyer, Frédéric A and Kovaltsuk, Aleksandr and Miketa, Dom and Pires, Douglas and Deane, Charlotte M},
  title = {Large scale paired antibody language models},
  journal = {PLOS Computational Biology},
  year = {2024},
  volume = {20},
  number = {12},
  pages = {e1012646},
  doi = {10.1371/journal.pcbi.1012646}
}
Kostenlos starten →