Design of experiments and artificial neural network linked genetic algorithm for modeling and optimization of L-asparaginase production by <Emphasis Type="Italic">Aspergillus terreus</Emphasis> MTCC 1782

The sequential optimization strategy for design of an experimental and artificial neural network (ANN) linked genetic algorithm (GA) were applied to evaluate and optimize media component for L-asparaginase production by Aspergillus terreus MTCC 1782 in submerged fermentation. The significant media components identified by Plackett-Burman design (PBD) were fitted into a second order polynomial model (R² = 0.910) and optimized for maximum L-asparaginase production using a five-level central composite design (CCD). A nonlinear model describing the effect of variables on L-asparaginase production was developed (R² = 0.995) and optimized by a back propagation NN linked GA. Ground nut oil cake (GNOC) flour 3.99% (w/v), sodium nitrate (NaNO₃) 1.04%, L-asparagine 1.84%, and sucrose 0.64% were found to be the optimum concentration with a maximum predicted L-asparaginase activity of 36.64 IU/mL using a back propagation NN linked GA. The experimental activity of 36.97 IU/mL obtained using the optimum concentration of media components is close to the predicted L-asparaginase activity of the ANN linked GA.     

Artificial intelligence based optimization of exocellular glucansucrase production from Leuconostoc dextranicum NRRL B-1146

Two different artificial intelligence techniques namely artificial neural network (ANN) and genetic algorithm (GA) were integrated for optimizing fermentation medium for the production of glucansucrase. The experimental data reported in a previous study were used to build the neural network. The ANN was trained using the back propagation algorithm. The ANN predicted values showed good agreement with the experimentally reported ones from a response surface based experiment. The concentrations of three medium components: viz Tween 80, sucrose and K(2)HPO(4) served as inputs to the neural network model and the enzyme activity as the output of the model. A model was generated with a coefficient of correlation (R(2)) of 1.0 for the training set and 0.90 for the test data. A genetic algorithm was used to optimize the input space of the neural network model to find the optimum settings for maximum enzyme activity. This artificial neural network supported genetic algorithm predicted a maximum glucansucrase activity of 6.92U/ml at medium composition of 0.54% (v/v) Tween 80, 5.98% (w/v) sucrose and 1.01% (w/v) K(2)HPO(4). ANN-GA predicted model gave a 6.0% increase of enzyme activity over the regression based prediction for optimized enzyme activity. The maximum enzyme activity experimentally obtained using the ANN-GA designed medium was 6.75+/-0.09U/ml which was in good agreement with the predicted value.     

Enhanced antibiotic production by Streptomyces sindenensis using artificial neural networks coupled with genetic algorithm and Nelder-Mead downhill simplex

Antibiotic production with Streptomyces sindenensis MTCC 8122 was optimized under submerged fermentation conditions by artificial neural network (ANN) coupled with genetic algorithm (GA) and Nelder-Mead downhill simplex (NMDS). Feed forward back-propagation ANN was trained to establish the mathematical relationship among the medium components and length of incubation period for achieving maximum antibiotic yield. The optimization strategy involved growing the culture with varying concentrations of various medium components for different incubation periods. Under non-optimized condition, antibiotic production was found to be 95 microgram/ml, which nearly doubled (176 microgram/ml) with the ANN-GA optimization. ANN-NMDS optimization was found to be more efficacious, and maximum antibiotic production (197 microgram/ml) was obtained by cultivating the cells with (g/l) fructose 2.7602, MgSO4 1.2369, (NH4)2PO4 0.2742, DL-threonine 3.069%, and soyabean meal 1.952%, for 9.8531 days of incubation, which was roughly 12% higher than the yield obtained by ANN coupled with GA under the same conditions.     

Optimization of L-asparaginase production from novel Enterobacter sp., by submerged fermentation using response surface methodology

The culture conditions and nutritional rations influencing the production of extra cellular antileukemic enzyme by novel Enterobacter aerogenes KCTC2190/MTCC111 were optimized in shake-flask culture. Process variables like pH, temperature, incubation time, carbon and nitrogen sources, inducer concentration, and inoculum size were taken into account. In the present study, finest enzyme activity achieved by traditional one variable at a time method was 7.6 IU/mL which was a 2.6-fold increase compared to the initial value. Further, the L-asparaginase production was optimized using response surface methodology, and validated experimental result at optimized process variables gave 18.35 IU/mL of L-asparaginase activity, which is 2.4-times higher than the traditional optimization approach. The study explored the E. aerogenes MTCC111 as a potent and potential bacterial source for high yield of antileukemic drug.     

Studies on pH and thermal stability of novel purified L-asparaginase from Pectobacterium carotojorum MTCC 1428

Glutaminase free L-asparaginase is known to be an excellent anticancer agent. In the present study, the combined effect of pH and temperature on the performance of purified novel L-asparaginase from Pectobacterium carotovorum MTCC 1428 was studied under assay conditions using response surface methodology (RSM). Deactivation studies and thermodynamic parameters of this therapeutically important enzyme were also investigated. The optimum pH and temperature of the purified L-asparaginase were found to be 8.49 and 39.3 degrees C, respectively. The minimum deactivation rate constant (k(d)) and maximum half life (t1/2) were found to be 0.041 min(-1) and 16.9 h, respectively at pH of 8.6 and 40 degreesC. Thermodynamic parameters (deltaG, deltaH, deltaS, and activation energies) were also evaluated for purified L-asparaginase. The probable mechanism of deactivation of purified L-asparaginase was explained to an extent on the basis of deactivation studies and thermodynamic parameters.     

Production of L-asparaginase by filamentous fungi

L-asparaginase production was investigated in the filamentous fungi Aspergillus tamarii and Aspergillus terreus. The fungi were cultivated in medium containing different nitrogen sources. A. terreus showed the highest L-asparaginase (activity) production level (58 U/L) when cultivated in a 2% proline medium. Both fungi presented the lowest level of L-asparaginase production in the presence of glutamine and urea as nitrogen sources. These results suggest that L-asparaginase production by of filamentous fungi is under nitrogen regulation.     

Media optimization for biosurfactant production by <Emphasis Type="Italic">Rhodococcus erythropolis</Emphasis> MTCC 2794: artificial intelligence versus a statistical approach

This paper entails a comprehensive study on production of a biosurfactant from Rhodococcus erythropolis MTCC 2794. Two optimization techniques—(1) artificial neural network (ANN) coupled with genetic algorithm (GA) and (2) response surface methodology (RSM)—were used for media optimization in order to enhance the biosurfactant yield by Rhodococcus erythropolis MTCC 2794. ANN and RSM models were developed, incorporating the quantity of four medium components (sucrose, yeast extract, meat peptone, and toluene) as independent input variables and biosurfactant yield [calculated in terms of percent emulsification index (% EI₂₄)] as output variable. ANN-GA and RSM were compared for their predictive and generalization ability using a separate data set of 16 experiments, for which the average quadratic errors were ~3 and ~6%, respectively. ANN-GA was found to be more accurate and consistent in predicting optimized conditions and maximum yield than RSM. For the ANN-GA model, the values of correlation coefficient and average quadratic error were ~0.99 and ~3%, respectively. It was also shown that ANN-based models could be used accurately for sensitivity analysis. ANN-GA-optimized media gave about a 3.5-fold enhancement in biosurfactant yield.     

Lipase from solvent tolerant Pseudomonas aeruginosa strain: production optimization by response surface methodology and application

Solvent tolerant Pseudomonas aeruginosa strain PseA has been studied for lipase activity. This strain has earlier been reported to be secreting alkaline and solvent stable protease. It produced an extra cellular lipase with suitable properties for detergent applications viz. (i) alkaline in nature, (ii) stability and compatibility towards bleach oxidants, surfactants and detergent formulations and (iii) resistant to proteolysis. Since the culture supernatant contains both protease and lipase which are together required in detergent formulations, enzymes from P. aeruginosa seem ideal for use as detergent additive. P. aeruginosa lipase exhibited remarkable stability in wide range of organic solvents at 25% (v/v) concentration. This property can be useful for solvent bioremediation and biotransformations in non-aqueous media. Media optimization for cost effective production of lipase was carried out by response surface methodology which led to 5.58-fold increase in lipase production (4580 IU/ml) over un-optimized media.     

Optimization of culture conditions for the production of Pleuromutilin from Pleurotus Mutilus using a hybrid method based on central composite design, neural network, and particle swarm optimization

This study aims at optimizing the culture conditions (agitation speed, temperature and pH) of the Pleuromutilin production by Pleurotus mutilus. A hybrid methodology including a central composite design (CCD), an artificial neural network (ANN), and a particle swarm optimization algorithm (PSO) was used. Specifically, the CCD and ANN were used for conducting experiments and modeling the non-linear process, respectively. The PSO was used for two purposes: Replacing the standard back propagation in training the ANN (PSONN) and optimizing the process. In comparison to the response surface methodology (RSM) and to the Bayesian regularization neural network (BRNN), PSONN model has shown the highest modeling ability. Under this hybrid approach (PSONN-PSO), the optimum levels of culture conditions were: 242 rpm agitation speed; temperature 26.88 and pH 6.06. A production of 10,074 ± 500 ??g/g, which was in very good agreement with the prediction (10,149 ??g/g), was observed in verification experiment. The hybrid PSONN-PSO gave a yield of 27.5% greater than that obtained by the hybrid BRNN-PSO. This work shows that the combination of PSONN with the generic PSO algorithm has a good predictability and a good accuracy for bio-process optimization. This hybrid approach is sufficiently general and thus can be helpful for modeling and optimization of other industrial bio-processes.     

Maximizing production of Penicillium cyclopium partial acylglycerol lipase

Penicillium cyclopium partial acylglycerol lipase production was maximized in shaken batch culture. The effect of inoculum size and substrate concentration on the lipase activity released in the culture medium was visualized using a surface response methodology based on a Doehlert experimental design. The main advantage of this approach is the low number of experiments required to construct a predictive model of the experimental domain. Substrate percentage (corn steep, w/v) ranged from 0.1% to 1.9% and inoculum from 100 spores/ml to 3,200 spores/ml. We determined that an optimal set of experimental conditions for high lipase production was 1.0% substrate and 3,200 spores/ml, with initial pH 5.0, temperature 25 degrees C and shaking speed 120 rpm. Between the conditions giving the minimum and the maximum lipase production, we observed a three-fold increase in both the predicted and the measured values.     

Use of response surface methodology to optimize culture medium for production of lipase with Candida sp. 99-125

Response surface methodology (RSM) was employed to optimize culture medium for production of lipase with Candida sp. 99-125. In the first step, a Plackett–Burmen design was used to evaluate the effects of different components in the culture medium. Soybean oil, soybean powder and K₂HPO₄ have significant influences on the lipase production. The concentrations of three factors were optimized subsequently using central composite designs and response surface analysis. The optimized condition allowed the production of lipase to be increased from 5000 to 6230 IU/ml in shake flask system. The lipase fermentation in 5 l fermenter reached 9600 IU/ml.     

Optimization of production and reaction conditions of polygalacturonase from Byssochlamys fulva

In the present study, the optimization of production and reaction conditions of polygalacturonase produced by a fungus Byssochlamys fulva MTCC 505 was achieved. The production of polygalacturonase with a considerable activity of 1.28 IU/ml was found when the culture was shaken at 30°C for 5 days in 100 ml of medium containing (w/v) 10 g/l pectin, 2 g/l NaNO?, 1 g/l KH?PO?, 0.5 g/l KCl, 0.5 g/l MgSO?. 7H?O, 0.001 g/l FeSO?. 7H?O, 0.001 g/l CaCl?. The best carbon and nitrogen source for this enzyme were pectin (1%) and Ca(NO?)? (0.1%), respectively. The enzyme gave maximum activity at incubation time of 72 h, temperature of 30°C and pH 4.5. During the optimization of reaction conditions, the enzyme showed maximum activity in sodium citrate buffer (50 mM) of pH 5.5 at 50°C reaction temperature for 15 minutes of incubation. The enzyme showed greater affinity for polygalacturonic acid as substrate (0.5%). Km and Vmax values were 0.15 mg/ml and 4.58 μmol/ml/min. The effect of various phenolics, thiols, protein inhibitors and metal ions on the enzyme activity was investigated. The enzyme was quite stable at 4°C and 30°C. At 40°C the half life of the enzyme was 6 h and at 60°C it was 2 h.     

Optimization of fibrinolytic enzyme production by Bacillus subtilis DC-2 in aqueous two-phase system (poly-ethylene glycol 4000 and sodium sulfate)

The central composite rotable design (CCRD) was used to determine optimal conditions for fibrinolytic enzyme production by Bacillus subtilis DC-2 in poly-ethylene glycol 4000 (PEG 4000) and sodium sulfate (Na(2)SO(4)) aqueous two-phase system (ATPS). PEG 4000 and Na(2)SO(4) concentration, fermentation time and temperature, and pH were selected as variables to evaluate the fibrinolytic activity in PEG phase. Using response surface methodology (RSM), a second-order polynomial equation was obtained by multiple regression analysis. The predicted maximal fibrinolytic activity in PEG phase was 1241.02 IU/ml with 9.05% PEG 4000 concentration, 5.06% Na(2)SO(4) concentration, 118.77 h fermentation time, 37.57 degrees C fermentation temperature and pH 6.52. The validity of the response model was verified by a good agreement between predicted and experimental results. The fibrinolytic activity obtained from experimental results in PEG phase (1223.61 IU/ml) was higher than that produced in homogeneous fermentation (1165.58 IU/ml).     

Studies on pH and thermal stability of novel purified L-asparaginase from <Emphasis Type="Italic">Pectobacterium carotovorum</Emphasis> MTCC 1428

Glutaminase free L-asparaginase is known to be an excellent anticancer agent. In the present study, the combined effect of pH and temperature on the performance of purified novel L-asparaginase from Pectobacterium carotovorum MTCC 1428 was studied under assay conditions using response surface methodology (RSM). Deactivation studies and thermodynamic parameters of this therapeutically important enzyme were also investigated. The optimum pH and temperature of the purified L-asparaginase were found to be 8.49 and 39.3°C, respectively. The minimum deactivation rate constant (k _d ) and maximum half life (t _1/2) were found to be 0.041 min⁻¹ and 16.9 h, respectively at pH of 8.6 and 40°C. Thermodynamic parameters (ΔG, ΔH, ΔS, and activation energies) were also evaluated for purified L-asparaginase. The probable mechanism of deactivation of purified L-asparaginase was explained to an extent on the basis of deactivation studies and thermodynamic parameters.     

基于人工神经网络-遗传算法的樟芝发酵培养基优化

采用优化模型对药用丝状真菌樟芝的复杂发酵过程进行建模,并获得最优发酵培养基组成.对樟芝发酵过程中的形态变化过程进行了观察,并分别采用人工神经网络(ANN)和响应面法(RSM)对樟芝发酵过程进行建模,同时采用遗传算法(GA)优化了发酵培养基组成.结果表明,ANN模型比RSM模型具有更好的实验数据拟合能力和预测能力,GA计算得到樟芝生物量理论最大值为6.2 g/L,并获得发酵最佳接种量及培养基组成:孢子浓度1.76× 105个/mL,葡萄糖29.1 g/L,蛋白胨9.4 g/L,黄豆粉2.8 g/L.在最佳培养条件下,樟芝生物量为(6.1±0.2)g/L.基于ANN-GA的优化方法可用于优化其他丝状真菌的复杂发酵过程,从而获得生物量或活性代谢产物.     

Optimization of actinomycin V production by Streptomyces triostinicus using artificial neural network and genetic algorithm

Artificial neural network (ANN) and genetic algorithm (GA) were applied to optimize the medium components for the production of actinomycinV from a newly isolated strain of Streptomyces triostinicus which is not reported to produce this class of antibiotics. Experiments were conducted using the central composite design (CCD), and the data generated was used to build an artificial neural network model. The concentrations of five medium components (MgSO₄, NaCl, glucose, soybean meal and CaCO₃) served as inputs to the neural network model, and the antibiotic yield served as outputs of the model. Using the genetic algorithm, the input space of the neural network model was optimized to find out the optimum values for maximum antibiotic yield. Maximum antibiotic yield of 452.0 mg l⁻¹ was obtained at the GA-optimized concentrations of medium components (MgSO₄ 3.657; NaCl 1.9012; glucose 8.836; soybean meal 20.1976 and CaCO₃ 13.0842 gl⁻¹). The antibiotic yield obtained by the ANN/GA was 36.7% higher than the yield obtained with the response surface methodology (RSM).     

Optimization of culture parameters for extracellular protease production from a newly isolated Pseudomonas sp. using response surface and artificial neural network models

Radial basis function (RBF) artificial neural network (ANN) and response surface methodology (RSM) were used to build a predictive model of the combined effects of independent variables (pH, temperature, inoculum volume) for extracellular protease production from a newly isolated Pseudomonas sp. The optimum operating conditions obtained from the quadratic form of the RSM and ANN models were pH 7.6, temperature 38 °C, and inoculum volume of 1.5 with 58.5 U/ml of predicted protease activity within 24 h of incubation. The normalized percentage mean squared error obtained from ANN and RSM models were 0.05 and 0.1%, respectively. The results demonstrated an higher prediction accuracy of ANN compared to RSM. This superiority of ANN over other multi factorial approaches could make this estimation technique a very helpful tool for fermentation monitoring and control.     

Culture conditions optimization of hyaluronic acid production by Streptococcus zooepidemicus based on radial basis function neural network and quantum-behaved particle swarm optimization algorithm

This study aimed to optimize the culture conditions (agitation speed, aeration rate and stirrer number) of hyaluronic acid production by Streptococcus zooepidemicus. Two optimization algorithms were used for comparison: response surface methodology (RSM) and radial basis function neural network coupling quantum-behaved particle swarm optimization algorithm (RBF-QPSO). In RBF-QPSO approach, RBF is employed to model the microbial HA production and QPSO algorithm is used to find the optimal culture conditions with the established RBF estimator as the objective function. The predicted maximum HA yield by RSM and RBF-QPSO was 5.27 and 5.62 g/l, respectively, while a maximum HA yield of 5.21 and 5.58 g/l was achieved in the validation experiments under the optimal culture conditions obtained by RSM and RBF-QPSO, respectively. It was indicated that both models provided similar quality predictions for the above three independent variables in terms of HA yield, but RBF model gives a slightly better fit to the measured data compared to RSM model. This work shows that the combination of RBF neural network with QPSO algorithm has good predictability and accuracy for bioprocess optimization and may be helpful to the other industrial bioprocesses optimization to improve productivity.     

Response surface methodology for lovastatin production by Aspergillus terreus GD13 strain

A wild type Aspergillus terreus GD13 strain, chosen after extensive screening, was optimized for lovastatin production using statistical Box-Behnken design of experiments. The interactive effect of four process parameters, i.e. lactose and soybean meal, inoculum size (spore concentration) and age of the spore culture, on the production of lovastatin was evaluated employing response surface methodology (RSM). The model highlighted the positive effect of soybean meal concentration and inoculum level for achieving maximal level of lovastatin (1342 mg/l). The optimal fermentation conditions improved the lovastatin titre by 7.0-folds when compared to the titres obtained under unoptimized conditions.     

Culture condition improvement for whole-cell lipase production in submerged fermentation by Rhizopus chinensis using statistical method

Rhizopus chinensis CCTCC M201021 was a versatile strain capable of producing whole-cell lipase with synthetic activity in submerged fermentation. In order to improve the production of whole-cell lipase and study the culture conditions systematically, the combination of taguchi method and response surface methodology was performed. Taguchi method was used for the initial optimization, and eight factors viz., maltose, olive oil, peptone, K2HPO4, agitation, inoculum size, fermentation volume and pH were selected for this study. The whole-cell lipase activity yield was two times higher than the control experiment under initial optimal conditions, and four significant factors (inoculum, olive oil, fermentation volume and peptone) were selected to test the effect on the lipase production using response surface methodology. The optimal fermentation parameters for enhanced whole-cell lipase yield were found to be: inoculum 4.25 x 10(8) spores/L, olive oil 2.367% (w/v), fermentation volume 18 mL/250 mL flask, peptone 4.06% (w/v). Subsequent experimental trails confirmed the validity of the model. These optimal culture conditions in the shake flask led to a lipase yield of 13875 U/L, which 120% increased compare with the non-optimized conditions.