Search

The use of agro-industrial waste as substrate to produce enzymes has been widely studied in order to adjust the high productions of these biocatalysts with a reduction of the final cost in an ecologically correct process in the industry. This is the first work to use peach-palm (Bactris gasipaes Kunth.) waste for the production of carboxymethylcellulases (CMCase) by the Trichoderma stromaticum AM7 under solid-state fermentation (SSF) using the artificial neural network and genetic algorithm (ANN-GA) to optimize the cellulase production. ANN-AG was used to determine the optimal influence of nitrogen source concentration (2.46%), time (12 days), and temperature (26 °C) on the cellulase production with 98% of efficiency for algorithm prediction of endoglucanase activity. The predicted and experimental values of the CMCase activity in U/g of dry initial substrate (gds) were 122.9 and 120.0, respectively. After all optimization processes, the variation of these parameters allowed a final increase of 31.58-fold when compared to the initial fermentation. Moreover, the treatment of peach-palm waste with T. stromaticum AM7 endoglucanase had an effect on the degradation of the fibers analyzed by scanning electron microscopy and the saccharification of the waste by releasing reducing sugar (807.80 mg/g) for 8 h of incubation. These results are very promising to waste valorization and the biotechnological and industrial applications of cellulase of the T. stromaticum AM7 to food processes and biofuel production.

Simplex-centroid design along with artificial neural network coupled with genetic algorithm (ANN-GA) was applied to maximize exoglucanase production by Penicillium roqueforti ATCC 10110 under solid-state fermentation (SSF), using a blend of agroindustrial wastes as substrate. The first statistical treatment determined the ideal contents of green coconut shell, corn cob, and sugarcane bagasse in the substrate, which were 0.44, 2.06, and 2.50 g, respectively. The optimum conditions by the ANN-GA were obtained as follows: 24 h, 21 °C, and 8.1 and 81.0% for the time, temperature, pH, and moisture, respectively. Moreover, the predicted and the experimental values of exoglucanase activity were 267.94 and 268.58 IU/g, respectively. The optimization process increased the enzyme activity by up to 1263% compared with the preliminary analysis using individual substrates, demonstrating the high efficiency of the algorithms on predicting and optimizing enzyme production. Biochemical characterization demonstrated good thermostability, basic pH stability, halotolerance, and increased enzyme activity in the presence of metal ions (Co2+, Ca2+, Mg2+, and Fe2), solvents (ethanol and dichloromethane), and organic compounds (EDTA, Triton-X, and lactose,). These results indicate the algorithm efficiency for enzyme production purposes.

In the present work, an artificial neural network hybridized with a genetic algorithm (ANN-GA) has been applied to optimize Penicillium roqueforti ATCC 10110 lipase production in solid-state fermentation (SSF). For such a purpose, a feed-forward ANN with polynomial configuration 3-49-1 (i.e. 3 neurons in the input layer, 49 neurons in the hidden layer and 1 neuron in the output layer) was used to computationally model the experiment and a GA was used to optimize lipase production through the ANN model. The input variables optimized by the ANN-GA were fermentation time (1 day), incubation temperature (31.2 °C) and percentage moisture content (78%). Validation was performed by considering the optimal and central point conditions, thus obtaining a lipase activity value of 48.00 U g−1, which is three times greater than by using other methodologies. Furthermore, the ANN model was obtained using 28 essays (small dataset) with interpolation and generalization capability based on a significant and precise data choice and justified by mean square error and determination coefficient values. A total of 5.0 × 107 artificial tests were simulated from the small dataset of 28 experiments.