Artificial neural network-genetic algorithm based optimization for the immobilization of cellulase on the smart polymer Eudragit L-100

Abstract

Cellulase was covalently immobilized on a smart polymer, Eudragit L-100 by carbodiimide coupling. Using data of central composite design, response surface methodology (RSM) and artificial neural network (ANN) were developed to investigate the effect of pH, carbodiimide concentration, and coupling time on the activity yield of immobilized cellulase. Results showed simulation and prediction accuracy of ANN was apparently higher compared to RSM. The maximum activity yield obtained from RSM was 57.56% at pH 5.54, carbodiimide concentration 0.32%, and coupling time 3.03 h, where the experimental value was 60.87 ± 4.79%. Using ANN as fitness function, a maximum activity yield of 69.83% was searched by genetic algorithm at pH 5.07, carbodiimide concentration 0.36%, and coupling time 4.10 h, where the experimental value was 66.75 ± 5.21%. ANN gave a 9.7% increase of activity yield over RSM. After reusing immobilized cellulase for 5 cycles, the remaining productivity was over 50%.