EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Explainable deep learning enhances robust and reliable real‐time monitoring of a chromatographic protein A capture step

Matthias Medl, Friedrich Leisch, Astrid Dürauer iD, Theresa Scharl iD

Biotechnology Journal · 2024-02 · 19 (2)

DOI: 10.1002/biot.202300554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biotechnology Journal, online erschienen am 22.02.2024. Verfasst von Matthias Medl und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Statistics, University of Natural Resources and Life Sciences, Vienna, Austria. Hauptthemen laut MEDLINE: Deep Learning, Biological Products. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The application of model‐based real‐time monitoring in biopharmaceutical production is a major step toward quality‐by‐design and the fundament for model predictive control. Data‐driven models have proven to be a viable option to model bioprocesses. In the high stakes setting of biopharmaceutical manufacturing it is essential to ensure high model accuracy, robustness, and reliability. That is only possible when (i) the data used for modeling is of high quality and sufficient size, (ii) state‐of‐the‐art modeling algorithms are employed, and (iii) the input‐output mapping of the model has been characterized. In this study, we evaluate the accuracy of multiple data‐driven models in predicting the monoclonal antibody (mAb) concentration, double stranded DNA concentration, host cell protein concentration, and high molecular weight impurity content during elution from a protein A chromatography capture step. The models achieved high‐quality predictions with a normalized root mean squared error of

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBiological ProductsStaphylococcal Protein AReproducibility of ResultsChromatographyAntibodies, Monoclonal

Stichwörter der Autor:innen

bioprocesschromatographyexplainableinterpretablemachine learning

Substanzen

Staphylococcal Protein AAntibodies, MonoclonalBiological Products

Autor:innen und Institutionen

  • Institute of Statistics, University of Natural Resources and Life Sciences, Vienna, Austria.
  • Institute of Bioprocess Science and Engineering, University of Natural Resources and Life Sciences, Vienna, Austria.

ORCID-Profile: Astrid Dürauer, Theresa Scharl

Zitieren

APA

Medl, M., Leisch, F., Dürauer, A., & Scharl, T. (2024). Explainable deep learning enhances robust and reliable real‐time monitoring of a chromatographic protein A capture step. Biotechnology Journal, 19(2). https://doi.org/10.1002/biot.202300554

Vancouver

Medl M, Leisch F, Dürauer A, Scharl T. Explainable deep learning enhances robust and reliable real‐time monitoring of a chromatographic protein A capture step. Biotechnology Journal. 2024;19(2). doi:10.1002/biot.202300554

BibTeX
@article{Medl2024,
  author = {Medl, Matthias and Leisch, Friedrich and Dürauer, Astrid and Scharl, Theresa},
  title = {Explainable deep learning enhances robust and reliable real‐time monitoring of a chromatographic protein A capture step},
  journal = {Biotechnology Journal},
  year = {2024},
  volume = {19},
  number = {2},
  doi = {10.1002/biot.202300554}
}
Kostenlos starten →