Estimation of adsorption isotherm and mass transfer parameters in protein chromatography using artificial neural networks

Abstract

Mechanistic modeling has been repeatedly successfully applied in process development and control of protein chromatography. For each combination of adsorbate and adsorbent, the mechanistic models have to be calibrated. Some of the model parameters, such as system characteristics, can be determined reliably by applying well-established experimental methods, whereas others cannot be measured directly. In common practice of protein chromatography modeling, these parameters are identified by applying time-consuming methods such as frontal analysis combined with gradient experiments, curve-fitting, or combined Yamamoto approach. For new components in the chromatographic system, these traditional calibration approaches require to be conducted repeatedly. In the presented work, a novel method for the calibration of mechanistic models based on artificial neural network (ANN) modeling was applied. An in silico screening of possible model parameter combinations was performed to generate learning material for the ANN model. Once the ANN model was trained to recognize chromatograms and to respond with the corresponding model parameter set, it was used to calibrate the mechanistic model from measured chromatograms. The ANN model's capability of parameter estimation was tested by predicting gradient elution chromatograms. The time-consuming model parameter estimation process itself could be reduced down to milliseconds. The functionality of the method was successfully demonstrated in a study with the calibration of the transport-dispersive model (TDM) and the stoichiometric displacement model (SDM) for a protein mixture.

Model‐Based Investigation on the Mass Transfer and Adsorption Mechanisms of Mono‐Pegylated Lysozyme in Ion‐Exchange Chromatography

“…The results are shown in Table . The axial dispersion was found to be similar to the literature data …”

“…For lysozyme, the mass transfer coefficient calculated according to with the internal mass transfer resistance was found to be consistent with the literature data . An approximately linear decrease of the film diffusion coefficient with increasing was determined as displayed in Figure a.…”

Cross‐scale quality assessment of a mechanistic cation exchange chromatography model

“…The transport dispersive model was selected as column model, due to multiple successful case studies for the simulation of ion exchange chromatography systems. [37][38][39][40][41] Equation (2 The Danckwerts' boundary conditions are given in Equations (4) and (5).…”

“…The transport dispersive model was selected as column model, due to multiple successful case studies for the simulation of ion exchange chromatography systems 37‐41 . Equation (2) describes the macroscopic transport of component i through the chromatography column.…”

“…The transport dispersive model was selected as column model, due to multiple successful case studies for the simulation of ion exchange chromatography systems. [37][38][39][40][41] Equation (2) describes the macroscopic transport of component i through the chromatography column. The change of the concentration c i (x, t) is a function of convective mass transport in the interstitial volume, peak broadening caused by axial dispersion D ax , and mass transfer from the interstitial volume into the pore phase of the particle with the radius r P .…”