Novel calibration design improves knowledge transfer across products for the characterization of pharmaceutical bioprocesses
Biotechnology Journal · 2024-07 · 19 (7)
DOI: 10.1002/biot.202400080 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biotechnology Journal, online erschienen am 12.07.2024. Verfasst von Laura M Helleckes und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Bio- and Geosciences, IBG-1: Biotechnology, Forschungszentrum Jülich GmbH, Jülich, Germany. Hauptthemen laut MEDLINE: Machine Learning. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: Deutscher Akademischer Austauschdienst.
Abstract (Originalsprache)
Modern machine learning has the potential to fundamentally change the way bioprocesses are developed. In particular, horizontal knowledge transfer methods, which seek to exploit data from historical processes to facilitate process development for a new product, provide an opportunity to rethink current workflows. In this work, we first assess the potential of two knowledge transfer approaches, meta learning and one‐hot encoding, in combination with Gaussian process (GP) models. We compare their performance with GPs trained only on data of the new process, that is, local models. Using simulated mammalian cell culture data, we observe that both knowledge transfer approaches exhibit test set errors that are approximately halved compared to those of the local models when two, four, or eight experiments of the new product are used for training. Subsequently, we address the question whether experiments for a new product could be designed more effectively by exploiting existing knowledge. In particular, we suggest to specifically design a few runs for the novel product to calibrate knowledge transfer models, a task that we coin calibration design . We propose a customized objective function to identify a set of calibration design runs, which exploits differences in the process evolution of historical products. In two simulated case studies, we observed that training with calibration designs yields similar test set errors compared to common design of experiments approaches. However, the former requires approximately four times fewer experiments. Overall, the results suggest that process development could be significantly streamlined when systematically carrying knowledge from one product to the next.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Bio- and Geosciences, IBG-1: Biotechnology, Forschungszentrum Jülich GmbH, Jülich, Germany.
- Institute of Biotechnology, RWTH Aachen University, Aachen, Germany.
- DataHow AG, Zurich, Switzerland.
- Department of Chemistry and Applied Biosciences, Institute for Chemical and Bioengineering, ETH Zurich, Zurich, Switzerland.
ORCID-Profile: Laura M Helleckes
Förderung
- Deutscher Akademischer Austauschdienst
Zitieren
APA
Helleckes, L. M., Wirnsperger, C., Polak, J., Guillén-Gosálbez, G., Butté, A., & von Stosch, M. (2024). Novel calibration design improves knowledge transfer across products for the characterization of pharmaceutical bioprocesses. Biotechnology Journal, 19(7). https://doi.org/10.1002/biot.202400080
Vancouver
Helleckes LM, Wirnsperger C, Polak J, Guillén-Gosálbez G, Butté A, von Stosch M. Novel calibration design improves knowledge transfer across products for the characterization of pharmaceutical bioprocesses. Biotechnology Journal. 2024;19(7). doi:10.1002/biot.202400080
BibTeX
@article{Helleckes2024,
author = {Helleckes, Laura M and Wirnsperger, Claus and Polak, Jakub and Guillén-Gosálbez, Gonzalo and Butté, Alessandro and von Stosch, Moritz},
title = {Novel calibration design improves knowledge transfer across products for the characterization of pharmaceutical bioprocesses},
journal = {Biotechnology Journal},
year = {2024},
volume = {19},
number = {7},
doi = {10.1002/biot.202400080}
}
EUVIMED