Authors: H Tian C Liu X D Gao W B Yao
Publish Date: 2012/11/07
Volume: 29, Issue: 3, Pages: 505-513
Abstract
Granulocyte colonystimulating factor GCSF is a cytokine widely used in cancer patients receiving high doses of chemotherapeutic drugs to prevent the chemotherapyinduced suppression of white blood cells The production of recombinant GCSF should be increased to meet the increasing market demand This study aims to model and optimize the carbon source of autoinduction medium to enhance GCSF production using artificial neural networks coupled with genetic algorithm In this approach artificial neural networks served as bioprocess modeling tools and genetic algorithm GA was applied to optimize the established artificial neural network models Two artificial neural network models were constructed the backpropagation BP network and the radial basis function RBF network The root mean square error coefficient of determination and standard error of prediction of the BP model were 00375 0959 and 849 respectively whereas those of the RBF model were 00257 0980 and 582 respectively These values indicated that the RBF model possessed higher fitness and prediction accuracy than the BP model Under the optimized autoinduction medium the predicted maximum GCSF yield by the BPGA approach was 7166 whereas that by the RBFGA approach was 7517 These predicted values are in agreement with the experimental results with 724 and 76014 for the BPGA and RBFGA models respectively These results suggest that RBFGA is superior to BPGA The developed approach in this study may be helpful in modeling and optimizing other multivariable nonlinear and timevariant bioprocesses
Keywords: