OPLS® for efficient identification of batch to batch process variation

Orthogonal Partial Least Squares (OPLS®), a more recent and less well-known modeling method for multivariate regression, has distinct benefits over traditional PLS modeling for some applications. Kaiser Optical Systems, Inc., a leading manufacturer of Raman spectroscopy equipment, embeds SIMCA®-Q software - part of the Umetrics® Suite of Data Analytics Solutions - in its Kaiser RamanRxn SystemsTM Analyzers. Sartorius used Kaiser Raman spectra data collected from in-line monitoring of batch cell culture processes to compare the results of regression analysis using OPLS versus PLS modeling.

Kaiser Optical Systems, Inc., a leading manufacturer of Raman spectroscopy equipment, embeds SIMCA®-Q software - part of the Umetrics® Suite of
Data Analytics Solutions - in its Kaiser RamanRxn SystemsTM Analyzers. Sartorius used Kaiser Raman spectra data collected from in-line monitoring of batch cell culture processes to compare the results of regression analysis using OPLS versus PLS modeling.

The case showed that OPLS allowed for clearer pattern identification in the dataset, improving the ability to distinguish between within and between batch variability. 

Fill out the form to download the full Case Story.