Decision Tree‐PLS (DT‐PLS) algorithm for the development of process: Specific local prediction models

• Published in: Biotechnology progress Vol. 35; no. 4; pp. e2818 - n/a
• Main Authors: Narayanan, Harini, Sokolov, Michael, Butté, Alessandro, Morbidelli, Massimo
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.07.2019; Wiley Subscription Services, Inc
• Subjects: Algorithms; Bioreactors; Cell culture; cell culture process; Decision analysis; Decision trees; local predictive models; Localization; Mathematical models; partial least squares regression; Prediction models; Process variables; QbD; Regression analysis; Statistical analysis; local predictive models; QbD; partial least squares regression; cell culture process; decision trees
• ISSN: 8756-7938; 1520-6033; 1520-6033
• DOI: 10.1002/btpr.2818

This work presents a novel multivariate statistical algorithm, Decision Tree‐PLS (DT‐PLS), to improve the prediction and understanding of dynamic processes based on local partial least square regression (PLSR) models for characteristic process groups defined based on Decision Tree (DT) analysis. The DT‐PLS algorithm is successfully applied to two different cell culture data sets, one obtained from bioreactors of 3.5 L lab scale and the other obtained from the 15 ml ambr microbioreactor system. Substantial improvement in the predictive capabilities of the model can be achieved based on the localization compared to the classical PLSR approach, which is implemented in the commercially available packages. Additionally, the differences in the model parameters of the local models suggest that the governing process variables vary for the different process regimes indicating the different states of the cell under different process conditions.