Cell culture product quality attribute prediction using convolutional neural networks and Raman spectroscopy
© 2024 Wiley Periodicals LLC..
Advanced process control in the biopharmaceutical industry often lacks real-time measurements due to resource constraints. Raman spectroscopy and Partial Least Squares (PLS) models are often used to monitor bioprocess cultures in real-time. In spite of the ease of training, the accuracy of the PLS model is impacted if it is not used to predict quality attributes for the cell lines it is trained on. To address this issue, a deep convolutional neural network (CNN) is proposed for offline modeling of metabolites using Raman spectroscopy. By utilizing asymmetric least squares smoothing to adjust Raman spectra baselines, a generic training data set is created by amalgamating spectra from various cell lines and operating conditions. This data set, combined with their derivatives, forms a two-dimensional model input. The CNN model is developed and validated for predicting different quality variables against measurements from various continuous and fed-batch experimental runs. Validation results confirm that the deep CNN model is an accurate generic model of the process to predict real-time quality attributes, even in experimental runs not included in the training data. This model is robust and versatile, requiring no recalibration when deployed at different sites to monitor various cell lines and experimental runs.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:121 |
---|---|
Enthalten in: |
Biotechnology and bioengineering - 121(2024), 4 vom: 18. Apr., Seite 1231-1243 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Khodabandehlou, Hamid [VerfasserIn] |
---|
Links: |
---|
Themen: |
Biopharmaceutical manufacturing |
---|
Anmerkungen: |
Date Completed 01.04.2024 Date Revised 01.04.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1002/bit.28646 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM367745887 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM367745887 | ||
003 | DE-627 | ||
005 | 20240401232544.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240129s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1002/bit.28646 |2 doi | |
028 | 5 | 2 | |a pubmed24n1359.xml |
035 | |a (DE-627)NLM367745887 | ||
035 | |a (NLM)38284180 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Khodabandehlou, Hamid |e verfasserin |4 aut | |
245 | 1 | 0 | |a Cell culture product quality attribute prediction using convolutional neural networks and Raman spectroscopy |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 01.04.2024 | ||
500 | |a Date Revised 01.04.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2024 Wiley Periodicals LLC. | ||
520 | |a Advanced process control in the biopharmaceutical industry often lacks real-time measurements due to resource constraints. Raman spectroscopy and Partial Least Squares (PLS) models are often used to monitor bioprocess cultures in real-time. In spite of the ease of training, the accuracy of the PLS model is impacted if it is not used to predict quality attributes for the cell lines it is trained on. To address this issue, a deep convolutional neural network (CNN) is proposed for offline modeling of metabolites using Raman spectroscopy. By utilizing asymmetric least squares smoothing to adjust Raman spectra baselines, a generic training data set is created by amalgamating spectra from various cell lines and operating conditions. This data set, combined with their derivatives, forms a two-dimensional model input. The CNN model is developed and validated for predicting different quality variables against measurements from various continuous and fed-batch experimental runs. Validation results confirm that the deep CNN model is an accurate generic model of the process to predict real-time quality attributes, even in experimental runs not included in the training data. This model is robust and versatile, requiring no recalibration when deployed at different sites to monitor various cell lines and experimental runs | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Raman spectroscopy | |
650 | 4 | |a biopharmaceutical manufacturing | |
650 | 4 | |a bioprocess monitoring | |
650 | 4 | |a convolutional neural networks | |
650 | 4 | |a deep learning | |
650 | 4 | |a predictive modeling | |
700 | 1 | |a Rashedi, Mohammad |e verfasserin |4 aut | |
700 | 1 | |a Wang, Tony |e verfasserin |4 aut | |
700 | 1 | |a Tulsyan, Aditya |e verfasserin |4 aut | |
700 | 1 | |a Schorner, Gregg |e verfasserin |4 aut | |
700 | 1 | |a Garvin, Christopher |e verfasserin |4 aut | |
700 | 1 | |a Undey, Cenk |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Biotechnology and bioengineering |d 1976 |g 121(2024), 4 vom: 18. Apr., Seite 1231-1243 |w (DE-627)NLM000014702 |x 1097-0290 |7 nnns |
773 | 1 | 8 | |g volume:121 |g year:2024 |g number:4 |g day:18 |g month:04 |g pages:1231-1243 |
856 | 4 | 0 | |u http://dx.doi.org/10.1002/bit.28646 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 121 |j 2024 |e 4 |b 18 |c 04 |h 1231-1243 |