Monitoring of complex industrial bioprocesses for metabolite concentrations using modern spectroscopies and machine learning: Application to gibberellic acid production

Two rapid vibrational spectroscopic approaches (diffuse reflectance–absorbance Fourier transform infrared [FT‐IR] and dispersive Raman spectroscopy), and one mass spectrometric method based on in vacuo Curie‐point pyrolysis (PyMS), were investigated in this study. A diverse range of unprocessed, ind...

Full description

Saved in:
Bibliographic Details
Published in:Biotechnology and bioengineering 2002-06, Vol.78 (5), p.527-538
Main Authors: McGovern, Aoife C., Broadhurst, David, Taylor, Janet, Kaderbhai, Naheed, Winson, Michael K., Small, David A., Rowland, Jem J., Kell, Douglas B., Goodacre, Royston
Format: Article
Language:English
Subjects:
Algorithms
Biological and medical sciences
Biotechnology
Cluster Analysis
dispersive Raman spectroscopy
evolutionary computing
Expert Systems
Feedback
Fourier transform infrared spectroscopy
Fundamental and applied biological sciences. Psychology
Gibberella - metabolism
Gibberellins - analysis
Linear Models
Mass Spectrometry - instrumentation
Mass Spectrometry - methods
Methods. Procedures. Technologies
Microbial engineering. Fermentation and microbial culture technology
Models, Biological
Multivariate Analysis
Others
pyrolysis mass spectrometry
Quality Control
Reproducibility of Results
Sensitivity and Specificity
Spectroscopy, Fourier Transform Infrared - instrumentation
Spectroscopy, Fourier Transform Infrared - methods
Spectrum Analysis - instrumentation
Spectrum Analysis - methods
Spectrum Analysis, Raman - instrumentation
Spectrum Analysis, Raman - methods
Various methods and equipments
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Two rapid vibrational spectroscopic approaches (diffuse reflectance–absorbance Fourier transform infrared [FT‐IR] and dispersive Raman spectroscopy), and one mass spectrometric method based on in vacuo Curie‐point pyrolysis (PyMS), were investigated in this study. A diverse range of unprocessed, industrial fed‐batch fermentation broths containing the fungus Gibberella fujikuroi producing the natural product gibberellic acid, were analyzed directly without a priori chromatographic separation. Partial least squares regression (PLSR) and artificial neural networks (ANNs) were applied to all of the information‐rich spectra obtained by each of the methods to obtain quantitative information on the gibberellic acid titer. These estimates were of good precision, and the typical root‐mean‐square error for predictions of concentrations in an independent test set was
ISSN:0006-3592
1097-0290
DOI:10.1002/bit.10226