Continuous glucose feedback control using Raman spectroscopy and deep learning models for biopharmaceutical processes
Biotechnology Progress · 2025-07 · 41 (4)
DOI: 10.1002/btpr.70020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biotechnology Progress, online erschienen am 02.04.2025. Verfasst von Mohammad Rashedi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Operations Transformation and Digital Strategy, Amgen Inc., Thousand Oaks, California, USA. Hauptthemen laut MEDLINE: Spectrum Analysis, Raman, Deep Learning, Glucose. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 28 Literaturangaben.
Abstract (Originalsprache)
This study explores the implementation of continuous glucose control strategies in high‐consumption, high‐complexity cell culture processes using Raman spectroscopy and advanced deep learning models, including convolutional neural networks and variational autoencoder just‐in‐time learning. By leveraging deep learning‐derived process monitoring, the study enhances glucose measurement accuracy and stability, enabling precise control across different glucose set points. This approach allows for a systematic evaluation of glycosylation effects and other critical quality attributes, addressing the impact of glucose variability on product consistency. Continuous glucose control is compared against traditional bolus feeding, demonstrating improved set‐point maintenance, reduced high mannose (HM) levels, and enhanced overall titer productivity. To extend these benefits to manufacturing environments where Raman spectroscopy may not be feasible, a continuous glucose calculator (CGC) is developed as a scalable alternative. Experimental validation across multiple cell lines confirmed that both Raman‐based and CGC‐driven strategies minimized glucose fluctuations, reduced undesirable byproducts, and optimized process yields. These findings highlight the potential of continuous glucose control, combined with deep learning models, to improve bioprocess efficiency and product quality while addressing the challenges of dynamic, high‐consumption bioreactor systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Operations Transformation and Digital Strategy, Amgen Inc., Thousand Oaks, California, USA.
- Process Development, Amgen Inc., West Greenwich, Rhode Island, USA.
- Operations Transformation and Digital Strategy, Amgen Inc., West Greenwich, Rhode Island, USA.
ORCID-Profile: Mohammad Rashedi
Zitieren
APA
Rashedi, M., Demers, M., Khodabandehlou, H., Wang, T., Garvin, C., & Rianna, S. (2025). Continuous glucose feedback control using Raman spectroscopy and deep learning models for biopharmaceutical processes. Biotechnology Progress, 41(4). https://doi.org/10.1002/btpr.70020
Vancouver
Rashedi M, Demers M, Khodabandehlou H, Wang T, Garvin C, Rianna S. Continuous glucose feedback control using Raman spectroscopy and deep learning models for biopharmaceutical processes. Biotechnology Progress. 2025;41(4). doi:10.1002/btpr.70020
BibTeX
@article{Rashedi2025,
author = {Rashedi, Mohammad and Demers, Matthew and Khodabandehlou, Hamid and Wang, Tony and Garvin, Christopher and Rianna, Steve},
title = {Continuous glucose feedback control using Raman spectroscopy and deep learning models for biopharmaceutical processes},
journal = {Biotechnology Progress},
year = {2025},
volume = {41},
number = {4},
doi = {10.1002/btpr.70020}
}
EUVIMED