Modeling of Medium Constituents for Optimized Production of Lipase From Niger Seed Oil Cake (Guizotia abyssinica) Using Artificial Neural Networks and Genetic Algorithms

A hybrid system of Artificial Neural Networks (ANN) and Genetic Algorithms (GA) was adopted to optimize the medium constituents to enhance the lipase production by Yarrowia lipolytica NCIM 3589 in solid state fermentation (SSF) using Niger seed oil cake as the substrate. Different microbial metabolism regulating fermentation variables (initial moisture content of the substrate, glucose, and urea) were studied to construct a ‘3–5–1’ topology of the ANN for identifying the nonlinear relationship between fermentation variables and the enzyme yield. ANN model was subsequently optimized using GA for obtaining maximum lipase production.  The usage of ANN–GA hybrid methodology resulted in a significant improvement (25 %) in the lipase yield when compared to preliminary investigations. MATLAB 7 was used for implementing the ANN–GA methodology and the corresponding program was included in the appendix.