Hindawi Publishing Corporation BioMed Research International Volume 2014, Article ID 361732, 8 pages http://dx.doi.org/10.1155/2014/361732 Research Article Role of Feed Forward Neural Networks Coupled with Genetic Algorithm in Capitalizing of Intracellular Alpha-Galactosidase Production by Acinetobacter sp. Sirisha Edupuganti, 1 Ravichandra Potumarthi, 2 Thadikamala Sathish, 3 and Lakshmi Narasu Mangamoori 1 1 Centre for Biotechnology, Institute of Science and Technology, Jawaharlal Nehru Technological University Hyderabad, Andhra Pradesh (AP) 500 085, India 2 Department of Chemical Engineering, Monash University, Clayton, 3800, Australia 3 Bioengineering and Environmental Centre, Indian Institute of Chemical Technology, Hyderabad, Andhra Pradesh (AP) 500607, India Correspondence should be addressed to Lakshmi Narasu Mangamoori; mangamoori@gmail.com Received 28 February 2014; Accepted 14 July 2014 Academic Editor: Juliana Maria Leite Nobrega de Moura Bell Copyright © 2014 Sirisha Edupuganti et al. his is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Alpha-galactosidase production in submerged fermentation by Acinetobacter sp. was optimized using feed forward neural networks and genetic algorithm (FFNN-GA). Six diferent parameters, pH, temperature, agitation speed, carbon source (rainose), nitrogen source (tryptone), and K 2 HPO 4 , were chosen and used to construct 6-10-1 topology of feed forward neural network to study interactions between fermentation parameters and enzyme yield. he predicted values were further optimized by genetic algorithm (GA). he predictability of neural networks was further analysed by using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R 2 -value for training and testing data. Using hybrid neural networks and genetic algorithm, alpha-galactosidase production was improved from 7.5 U/mL to 10.2 U/mL. 1. Introduction Alpha-galactosidases (3.2.1.22) belong to the family of gly- cosyl hydrolases or glycosidases. hese enzymes catalyze the hydrolysis of terminal alpha 1–6 linked galactose residues from simple and complex oligosaccharides and polysaccha- rides [1]. hey are widely distributed in plants, animals, and microorganisms. Alpha-galactosidases ind potential applica- tions in food, pharmacological, and chemical industries. he enzyme has been used in food industry for enhancing the nutritional quality of legumes by degrading galactooligosac- charides that cause gas or latulence [2]. It is also used to improve crystallization of sugar by removing rainose from molasses in beet sugar industry [3] and in guar gum processing [4] and for enhancing bleaching of sotwood along with mannanase in paper and pulp industry [5] and in processing of animal feed [6]. In humans, mutations in gfA gene lead to Fabry’s disease, a rare X-linked recessive lysosomal storage disorder. Enzyme replacement therapy with -galactosidase is considered a potential treatment for Fabry’s patients [7]. In addition, the enzyme can also convert type “B” erythrocytes to type “O” erythrocytes [8] and is also used in xenotransplantation [9]. Microbial sources for alpha- galactosidase are being explored because of ease of cultivation and fermentation conditions. However, for cost-efective production, fermentation medium plays a vital role in the commercial production of enzymes. he nutritional require- ments of each microorganism are varied and are regulated by physiological, biochemical, and genetic makeup of the organ- ism [10]. herefore optimization of fermentation medium is considered a crucial step for cost-efective production of the desired product. Traditional methods use one at a time method of approach that is laborious and time-consuming and it does not relect interactions between diferent variables [11]. Experiments based on statistical methods are consid- ered to be more economical and efective than traditional