Colloidal interaction and connectionist modelling of protein osmotic pressure and the effect of physicochemical properties

Abstract

A proper knowledge of the osmotic pressure and thermodynamic behaviour of protein solutions is vital for designing an efficient protein separation process. It is also of great importance to develop a rapid and inexpensive technique to accurately estimate the protein osmotic pressure. A connectionist model to estimate the osmotic pressure of bovine serum albumin (BSA) in terms of pH, ionic strength and BSA concentration is proposed in this paper. Osmotic pressure of BSA is also modelled through the application of a colloidal interaction approach. Molecular interaction forces such as electrostatic, London-van der Waals and hydration along with entropy pressure are considered in the colloidal model to predict the BSA osmotic pressure. The advantages and disadvantages of both modelling approaches are discussed, and a hybrid modelling scheme is proposed for further investigations.

Connectionist Model to Estimate Performance of Steam-Assisted Gravity Drainage in Fractured and Unfractured Petroleum Reservoirs: Enhanced Oil Recovery Implications

“…Statistical parameters including the mean squared error (MSE), minimum absolute percentage error (MIPE), maximum absolute percentage error (MAPE), and coefficient of determination (R 2 ) were employed to check the closeness of the predicted SAGD performance parameters to the real outputs. 76,77 The ANN−BP and ANN−PSO predictions for CSOR compared to the measured values are plotted in Figures 6 and 7, respectively, as 11 and 13). We also compared the outputs obtained from smart models (i.e., conventional ANN and ANN− PSO) to the data predicted using the correlations based on statistical parameters (i.e., MSE, MIPE, MAPE, and R 2 ) as listed in Table 4.…”

“…To systematically examine the precision of the connectionist modeling introduced in this work, we employed statistical analysis and a graphical measure method. Statistical parameters including the mean squared error (MSE), minimum absolute percentage error (MIPE), maximum absolute percentage error (MAPE), and coefficient of determination ( R 2 ) were employed to check the closeness of the predicted SAGD performance parameters to the real outputs. , The ANN–BP and ANN–PSO predictions for CSOR compared to the measured values are plotted in Figures and , respectively, as scatter plots for the training and testing stages. The same methodology was applied for the RF parameter in the SAGD process, as shown in Figures and for the ANN–BP and ANN–PSO systems, respectively.…”

A New Perspective to Tribocharging: Could Tribocharging Lead to the Development of a Non-Destructive Approach for Process Monitoring and Quality Control of Powders?

“…Therefore, an effective network architecture requires high expertise in identifying proper hyperparameters for the network, such as the number of hidden layers, the number of neurons in each layer, and a knowledgeable background in the corresponding field [ 35 ]. Hence, this topic has been the subject of enormous research in recent years [ 36 , 37 ]. The computation of particle–wall collision numbers for different combinations of input parameters through CFD analysis is extremely time-intensive, taking hours if not days to run every simulation.…”

Utilization of support vector machine to calculate gas compressibility factor

“…Further information about ANN can be found in the recent literature [36][37][38][39][40][41][42][43][44][45][46][47].…”