Artificial neural network (ANN)‐based prediction of depth filter loading capacity for filter sizing

Abstract

This article presents an application of artificial neural network (ANN) modelling towards prediction of depth filter loading capacity for clarification of a monoclonal antibody (mAb) product during commercial manufacturing. The effect of operating parameters on filter loading capacity was evaluated based on the analysis of change in the differential pressure (DP) as a function of time. The proposed ANN model uses inlet stream properties (feed turbidity, feed cell count, feed cell viability), flux, and time to predict the corresponding DP. The ANN contained a single output layer with ten neurons in hidden layer and employed a sigmoidal activation function. This network was trained with 174 training points, 37 validation points, and 37 test points. Further, a pressure cut-off of 1.1 bar was used for sizing the filter area required under each operating condition. The modelling results showed that there was excellent agreement between the predicted and experimental data with a regression coefficient (R ) of 0.98. The developed ANN model was used for performing variable depth filter sizing for different clarification lots. Monte-Carlo simulation was performed to estimate the cost savings by using different filter areas for different clarification lots rather than using the same filter area. A 10% saving in cost of goods was obtained for this operation. © 2016 American Institute of Chemical Engineers Biotechnol. Prog., 32:1436-1443, 2016.

Implementation of chemometrics, design of experiments, and neural network analysis for prior process knowledge assessment, failure modes and effect analysis, scale‐down model development, and process characterization for a chromatographic purification of Teriparatide

“…Another novel approach we have presented in this article is the application of neural network in establishing SDM by utilizing raw chromatography signal generated by AKTA systems in bio manufacturing. The applications of neural networks for membrane separations are extensively reviewed by Asgahri et al 18 with a recent application in Biologics 19 . Neural networks have already been applied for analytical chromatography 20–25 and in combination with mechanistic models in process chromatography 12,13 .…”

“…The applications of neural networks for membrane separations are extensively reviewed by Asgahri et al 18 with a recent application in Biologics. 19 Neural networks have already been applied for analytical chromatography [20][21][22][23][24][25] and in combination with mechanistic models in process chromatography. 12,13 Since NN can reproduce highly complex nonlinear behavior through its simple network architecture, it is suitable for evaluating complex relationships between a large number of input variables and outputs, especially in processes where the mechanism is not entirely understood.…”

A decade in review: use of data analytics within the biopharmaceutical sector

“…These algorithms allow for non-linear relationships to be modelled, which can be particularly useful for capturing non-linearities within biological systems. For example, NN were applied successfully to predict loading capacity of depth filtration filters based upon non-linear functional correlations between inputs and outputs [ 25 ]. SVM are also advantageous due to their strong ability to generalise properties on unseen data which has resulted in its application across biological areas [ 26 ].…”

A comprehensive experimental and artificial network investigation of the performance of an ultrafiltration titanium dioxide ceramic membrane: application in produced water treatment

“…Artificial Neural Network is the most popular method in artificial intelligence modelling due to increased capacity computers and the advancement in computational sciences. Artificial Neural Network is inspired by the human brain (Agarwal et al ., ). It mimics the behaviour of the actual neurons of the human brain by using what is called transfer functions.…”