EUVIMEDEUVIMED entdecken
Crossref

Meta learning addresses noisy and under-labeled data in machine learning-guided antibody engineering

Mason Minot, Sai T Reddy

Cell Systems · 2024-01 · 15 (1) · 4-18.e4

DOI: 10.1016/j.cels.2023.12.003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cell Systems, 2024-01. Verfasst von Mason Minot und 1 weiteren Autor:innen. Beteiligte Einrichtung: ETH Zurich, Department of Biosystems Science and Engineering, Basel 4056, Switzerland. Hauptthemen laut MEDLINE: Antibodies, Engineering. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Eidgenössische Technische Hochschule Zürich, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning-guided protein engineering is rapidly progressing; however, collecting high-quality, large datasets remains a bottleneck. Directed evolution and protein engineering studies often require extensive experimental processes to eliminate noise and label protein sequence-function data. Meta learning has proven effective in other fields in learning from noisy data via bi-level optimization given the availability of a small dataset with trusted labels. Here, we leverage meta learning approaches to overcome noisy and under-labeled data and expedite workflows in antibody engineering. We generate yeast display antibody mutagenesis libraries and screen them for target antigen binding followed by deep sequencing. We then create representative learning tasks, including learning from noisy training data, positive and unlabeled learning, and learning out of distribution properties. We demonstrate that meta learning has the potential to reduce experimental screening time and improve the robustness of machine learning models by training with noisy and under-labeled training data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AntibodiesEngineeringAmino Acid SequenceMachine LearningMutagenesis

Stichwörter der Autor:innen

antibody engineeringdeep sequencingmachine learningmeta learningprotein engineering

Substanzen

Antibodies

Autor:innen und Institutionen

  • ETH Zurich, Department of Biosystems Science and Engineering, Basel 4056, Switzerland.
  • ETH Zurich, Department of Biosystems Science and Engineering, Basel 4056, Switzerland. Electronic address: sai.reddy@ethz.ch.

Förderung

  • Eidgenössische Technische Hochschule Zürich
  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Zitieren

APA

Minot, M., & Reddy, S. T. (2024). Meta learning addresses noisy and under-labeled data in machine learning-guided antibody engineering. Cell Systems, 15(1), 4-18.e4. https://doi.org/10.1016/j.cels.2023.12.003

Vancouver

Minot M, Reddy ST. Meta learning addresses noisy and under-labeled data in machine learning-guided antibody engineering. Cell Systems. 2024;15(1):4-18.e4. doi:10.1016/j.cels.2023.12.003

BibTeX
@article{Minot2024,
  author = {Minot, Mason and Reddy, Sai T},
  title = {Meta learning addresses noisy and under-labeled data in machine learning-guided antibody engineering},
  journal = {Cell Systems},
  year = {2024},
  volume = {15},
  number = {1},
  pages = {4--18.e4},
  doi = {10.1016/j.cels.2023.12.003}
}
Kostenlos starten →