Optimization of medium constituents for Cephalosporin C production using response surface methodology and artificial neural networks


Abstract

Artificial neural networks (ANN) and response surface methodology (RSM) were used to build a model to describe the effects of four independent variables (moisture content, concentrations of glucose, ammonium nitrate and methionine) on the yield of cephalosporin C (CPC) from Acremonium chrysogenum under solid state fermentation. The respective uses of RSM and ANN were found to be effective in locating the optimum conditions within the range fixed from the preliminary runs. When compared with the predictions given by RSM, ANN was found to be superior in describing the fermentation process for the production of CPC. When a global optimization routine was employed to optimize the equation resulted from the neural networks, the optimum predicted antibiotic yield was found to be 29.4 mg/g which is 14.8 % higher than the optimum value obtained from preliminary runs, and 9.2 % higher than value obtained from Box-Behnken design of RSM. Keywords: Optimization, Cephalosporin C, Acremonium chrysogenum, Solid state fermentation, Artificial neural networks, Response surface methodology Received: 21 January 2009 / Received in revised form: 14 February 2009, Accepted: 23 February 2009, Published online: 25 February 2009



Download PDF