EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

For antibody sequence generative modeling, mixture models may be all you need

Jonathan Parkinson iD, Wei Wang

Bioinformatics · 02.05.2024 · 40 (5)

DOI: 10.1093/bioinformatics/btae278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 23.04.2024. Verfasst von Jonathan Parkinson und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry and Biochemistry, University of California, San Diego, La Jolla, CA 92093-0359, United States. Hauptthemen laut MEDLINE: Antibodies. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Antibody therapeutic candidates must exhibit not only tight binding to their target but also good developability properties, especially low risk of immunogenicity. Results In this work, we fit a simple generative model, SAM, to sixty million human heavy and seventy million human light chains. We show that the probability of a sequence calculated by the model distinguishes human sequences from other species with the same or better accuracy on a variety of benchmark datasets containing >400 million sequences than any other model in the literature, outperforming large language models (LLMs) by large margins. SAM can humanize sequences, generate new sequences, and score sequences for humanness. It is both fast and fully interpretable. Our results highlight the importance of using simple models as baselines for protein engineering tasks. We additionally introduce a new tool for numbering antibody sequences which is orders of magnitude faster than existing tools in the literature. Availability and implementation All tools developed in this study are available at https://github.com/Wang-lab-UCSD/AntPack.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AntibodiesHumansSoftwareSequence Analysis, ProteinComputational BiologyImmunoglobulin Heavy ChainsImmunoglobulin Light ChainsAlgorithms

Substanzen

AntibodiesImmunoglobulin Heavy ChainsImmunoglobulin Light Chains

Autor:innen und Institutionen

  • Department of Chemistry and Biochemistry, University of California, San Diego, La Jolla, CA 92093-0359, United States.
  • MAP Bioscience, La Jolla, CA 92093, United States.
  • Department of Cellular and Molecular Medicine, University of California, San Diego, La Jolla, CA 92093-0359, United States.

ORCID-Profile: Jonathan Parkinson

Förderung

  • NIAID NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Parkinson, J., & Wang, W. (2024). For antibody sequence generative modeling, mixture models may be all you need. Bioinformatics, 40(5). https://doi.org/10.1093/bioinformatics/btae278

Vancouver

Parkinson J, Wang W. For antibody sequence generative modeling, mixture models may be all you need. Bioinformatics. 2024;40(5). doi:10.1093/bioinformatics/btae278

BibTeX
@article{Parkinson2024,
  author = {Parkinson, Jonathan and Wang, Wei},
  title = {For antibody sequence generative modeling, mixture models may be all you need},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {5},
  doi = {10.1093/bioinformatics/btae278}
}
Kostenlos starten →