Related Experiment Video
Updated: May 28, 2026
07:37
An Integrated Raman Spectroscopy and Mass Spectrometry Platform to Study Single-Cell Drug Uptake, Metabolism, and Effects
Published on: January 9, 2020
Spectroscopy-Based Cell Culture Predictive Monitoring
Ahmed Kanfoud1, Pascal Gerkens2, Marie Bastin1
1DNAlytics, 1 Rue Jean Monnet, B-1348 Ottignies-Louvain-la-Neuve, Belgium.
Biotech (Basel (Switzerland))
|May 27, 2026
Summary
This study introduces a novel method for real-time cell culture monitoring using spectral data and machine learning. The technique anticipates future spectra, enabling predictive monitoring and reducing laboratory testing needs.
Area of Science:
- Biotechnology
- Analytical Chemistry
- Machine Learning
Background:
- Cell culture monitoring is crucial in biomanufacturing.
- Current methods require significant hands-on time and laboratory testing.
- Real-time monitoring is desirable for process optimization.
Purpose of the Study:
- To develop a method for anticipating future spectra in cell cultures.
- To enable predictive cell culture monitoring using machine learning.
- To reduce the need for extensive laboratory testing and manual intervention.
Main Methods:
- Spectral monitoring combined with chemometrics and machine learning.
- Extrapolation of spectra in a reduced-dimensionality space.
- Retroprojection of extrapolated spectra into the original space.
Main Results:
- Anticipated spectra enabled predictive cell culture monitoring up to several dozen hours.
- The method achieved satisfactory quality in predictions.
- Reduced need for hands-on time and laboratory testing was demonstrated.
Conclusions:
- The proposed method allows for near real-time, predictive cell culture monitoring.
- Anticipation of future spectra enhances biomanufacturing operations.
- This technology can lead to reduced operational costs and improved efficiency.
