Comparative Assessment of the Artificial Neural Network and Response Surface Modelling Efficiencies for Biohydrogen Production on Sugar Cane Molasses

This study comparatively evaluates the modelling efficiency of the Response Surface Methodology (RSM) and the Artificial Neural Network (ANN). Twenty-nine biohydrogen fermentation batches were carried out to generate the experimental data. The input parameters consisted of a concentration of molasses (50–150 g/l), pH (4–8), temperature (35–40 °C) and inoculum concentration (10–50 %). The obtained data were used to develop the RSM and ANN models. The ANN model was a committee of networks with a topology of 4-(6-10)-1 structured on multilayer perceptrons. RSM and ANN models gave R ² values of 0.75 and 0.91, respectively, with predicted optimum conditions of 150 g/l, 8 and 35 °C for molasses, pH and temperature, respectively, with differences in inoculum concentrations (10.11 and 15 %) for RSM and ANN, respectively. Upon validation, 15.12 and 119.08 % prediction errors on hydrogen volume were found for ANN and RSM, respectively. These findings suggest that ANN has greater accuracy in modelling the relationships between the considered process inputs for fermentative biohydrogen production and thus, is more reliable to navigate the optimization space.     

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.     

Application of artificial neural network coupling particle swarm optimization algorithm to biocatalytic production of GABA

The biotransformation of L-sodium glutamate (L-MSG) to gamma-aminobutyric acid (GABA) catalyzed by the cells of Lactobacillus brevis with higher glutamate decarboxylase activity was investigated. The results showed that pH, temperature, and FeSO(4) x 7H(2)O concentration had significantly positive effect on GABA yield. The individual and interactive effects of pH, temperature, and FeSO(4) x 7H(2)O concentration were further optimized in terms of GABA yield. In the present work, an artificial neural network (ANN) and response surface methodology (RSM) models were developed, which incorporated pH, temperature, and FeSO(4) x 7H(2)O concentration as input variables, and GABA yield as output variable. The optimized ANN topology included four neurons in the hidden layer and the best network architecture was 3-4-1. The trained ANN gave total root-mean square error (sigma) equal to 1.84 for GABA yield while the RSM gave sigma equal to 2.63. The results demonstrated a slightly higher prediction accuracy of ANN compared to RSM. The modeled maximum GABA yield was identified by applying particle swarm optimization algorithm to the ANN model developed. The modeled maximum GABA yield reached 91 mM under the following optimal conditions: 25 mL Na(2)HPO(4)-citric acid buffer (100 mM, pH 4.23), 120 mM L-MSG, 0.83 g/L FeSO(4) x 7H(2)O, 10 microM PLP, the resting cells obtained from a 60-h culture broth, 2.68 g dry cell weight (DCW)/L, and without agitation at 40 degrees C for 5 h. The previous high value of GABA yield that was observed was 81.8 mM. The optimized conditions allowed GABA yield to be increased from 81.8 to 90.57 mM after verification experiments test.     

Biodegradation of 4-chlorophenol by <Emphasis Type="Italic">Arthrobacter chlorophenolicus A6</Emphasis>: effect of culture conditions and degradation kinetics

Among known microbial species, Arthrobacter chlorophenolicus A6 has shown very good potential to treat phenolic wastewaters. In this study, the levels of various culture conditions, namely initial pH, agitation (rpm), temperature (°C), and inoculum age (h) were optimized to enhance 4-chlorophenol (4-CP) biodegradation and the culture specific growth rate. For optimization, central composite design of experiments followed by response surface methodology (RSM) was applied. Results showed that among the four independent variables, i.e., pH, agitation (rpm), temperature (°C), and inoculum age (h) investigated in this study, interaction effect between agitation and inoculum age as well as that between agitation and temperature were significant on both 4-CP biodegradation efficiency and culture specific growth rate. Also, at the RSM optimized settings of 7.5 pH, 207 rpm, 29.6°C and 39.5 h inoculum age, 100% biodegradation of 4-CP at a high initial concentration of 300 mg l⁻¹ was achieved within a short span of 18.5 h of culture. The enhancement in the 4-CP biodegradation efficiency was found to be 23% higher than that obtained at the unoptimized settings of the culture conditions. Results of batch growth kinetics of A. chlorophenolicus A6 for various 4-CP initial concentrations revealed that the culture followed substrate inhibition kinetics. Biokinetic constants involved in the process were estimated by fitting the experimental data to several models available from the literature.     

Optimization of alkaline protease production by <Emphasis Type="Italic">Aspergillus clavatus</Emphasis> ES1 in <Emphasis Type="Italic">Mirabilis jalapa</Emphasis> tuber powder using statistical experimental design

Medium composition and culture conditions for the bleaching stable alkaline protease production by Aspergillus clavatus ES1 were optimized. Two statistical methods were used. Plackett-Burman design was applied to find the key ingredients and conditions for the best yield. Response surface methodology (RSM) including full factorial design was used to determine the optimal concentrations and conditions. Results indicated that Mirabilis jalapa tubers powder (MJTP), culture temperature, and initial medium pH had significant effects on the production. Under the proposed optimized conditions, the protease experimental yield (770.66 U/ml) closely matched the yield predicted by the statistical model (749.94 U/ml) with R (2)=0.98. The optimum operating conditions obtained from the RSM were MJTP concentration of 10 g/l, pH 8.0, and temperature of 30 degrees C, Sardinella heads and viscera flour (SHVF) and other salts were used at low level. The medium optimization contributed an about 14.0-fold higher yield than that of the unoptimized medium (starch 5 g/l, yeast extract 2 g/l, temperature 30 degrees C, and pH 6.0; 56 U/ml). More interestingly, the optimization was carried out with the by-product sources, which may result in cost-effective production of alkaline protease by the strain.     

Response surface methodological analysis on biohydrogen production by enriched anaerobic cultures

The individual and interactive effects of pH, temperature and substrate concentration on the biohydrogen production from sucrose by mixed anaerobic cultures were investigated in this study. A central composite design and response surface methodology (RSM) were employed in planning the experiments, in order to determine the optimum conditions for biohydrogen production. Experimental results show that pH, temperature and substrate concentration all had a significant influence on specific hydrogen production potential (P_s) and the maximum hydrogen production rate (R_max) individually. Temperature and sucrose concentration, pH and temperature were interdependent or there was a significant interaction on P_s and R_max. Substrate concentration and pH were slightly interdependent, or their interactive effect on P_s and R_max was not significant. A maximum P_s of 252 mL H₂/g sucrose was estimated under the optimum conditions of pH 5.5, temperature 34.8 °C and sucrose concentration of 24.8 g/L, while a maximum R_max of 1511 mL H₂/h was calculated under the optimum conditions of pH 5.5, temperature 35.5 °C and sucrose concentration of 25.4 g/L. The experiment results show that the RSM with the central composite design was useful for optimizing the biohydrogen-producing process.     

Screening,selection and development of Bacillus subtilis apr-IBL04 for hyper production of macromolecule alkaline protease

Bacillus subtilis microbe is commonly found in soil and produces proteases on nitrogen and carbon-containing sources and increases the fertility rate by degrading nitrogenous organic materials. The present study was aimed to develop hyper producing mutant strain of B. subtilis for the production of proteases, to improve the process variables by the response surface methodology (RSM) under central composite design (CCD) and the production of protease by the particular mutant strain in a liquid state fermentation media. The mutation of the strain was carried out using ethidium bromide. Pure B. subtilis strain was collected and screened for hyper-production of protease. The production of protease by mutant B. subtilis strain was optimized by varying temperature, inoculum size, pH and incubation time under liquid state fermentation. The CCD model were found to be reliable with r² of 0.999. The maximum enzyme activity of B. subtilis IBL-04 mutant with 3 mL/100 mL inoculum size, 72 h fermentation time, pH 8, and 45 °C temperature was developed with enzyme activity 631.09 U/mL, indicates 1–7-fold increase in enzyme activity than the parent strain having 82.32 U/mL activity. These characteristics render its potential use in industries for pharmaceutical and dairy formulation.     

Statistical optimization of the phytoremediation of arsenic by Ludwigia octovalvis- in a pilot reed bed using response surface methodology (RSM) versus an artificial neural network (ANN)

In this study, the removal of arsenic (As) by plant, Ludwigia octovalvis, in a pilot reed bed was optimized. A Box-Behnken design was employed including a comparative analysis of both Response Surface Methodology (RSM) and an Artificial Neural Network (ANN) for the prediction of maximum arsenic removal. The predicted optimum condition using the desirability function of both models was 39 mg kg^?1 for the arsenic concentration in soil, an elapsed time of 42 days (the sampling day) and an aeration rate of 0.22 L/min, with the predicted values of arsenic removal by RSM and ANN being 72.6% and 71.4%, respectively. The validation of the predicted optimum point showed an actual arsenic removal of 70.6%. This was achieved with the deviation between the validation value and the predicted values being within 3.49% (RSM) and 1.87% (ANN). The performance evaluation of the RSM and ANN models showed that ANN performs better than RSM with a higher R² (0.97) close to 1.0 and very small Average Absolute Deviation (AAD) (0.02) and Root Mean Square Error (RMSE) (0.004) values close to zero. Both models were appropriate for the optimization of arsenic removal with ANN demonstrating significantly higher predictive and fitting ability than RSM.     

Efficiency of neural network-based combinatorial model predicting optimal culture conditions for maximum biomass yields in hairy root cultures

Key message

ANN-based combinatorial model is proposed and its efficiency is assessed for the prediction of optimal culture conditions to achieve maximum productivity in a bioprocess in terms of high biomass.

Abstract

A neural network approach is utilized in combination with Hidden Markov concept to assess the optimal values of different environmental factors that result in maximum biomass productivity of cultured tissues after definite culture duration. Five hidden Markov models (HMMs) were derived for five test culture conditions, i.e. pH of liquid growth medium, volume of medium per culture vessel, sucrose concentration (%w/v) in growth medium, nitrate concentration (g/l) in the medium and finally the density of initial inoculum (g fresh weight) per culture vessel and their corresponding fresh weight biomass. The artificial neural network (ANN) model was represented as the function of these five Markov models, and the overall simulation of fresh weight biomass was done with this combinatorial ANN–HMM. The empirical results of Rauwolfia serpentina hairy roots were taken as model and compared with simulated results obtained from pure ANN and ANN–HMMs. The stochastic testing and Cronbach’s α-value of pure and combinatorial model revealed more internal consistency and skewed character (0.4635) in histogram of ANN–HMM compared to pure ANN (0.3804). The simulated results for optimal conditions of maximum fresh weight production obtained from ANN–HMM and ANN model closely resemble the experimentally optimized culture conditions based on which highest fresh weight was obtained. However, only 2.99 % deviation from the experimental values could be observed in the values obtained from combinatorial model when compared to the pure ANN model (5.44 %). This comparison showed 45 % better potential of combinatorial model for the prediction of optimal culture conditions for the best growth of hairy root cultures.     

Production and recovery of an alkaline exo-polygalacturonase from Bacillus subtilis RCK under solid-state fermentation using statistical approach

The empirical models developed through two independent RSM (RSM-I, 2(3); RSM-II, 2(5)) in terms of effective operational factors of inoculum age, inoculum volume, wheat bran-to-moisture ratio (RSM-I) and contact time, extraction temperature, agitation, fermented bran-to-solvent ratio and SDS (RSM-II) were found adequate to describe the optimization of exo-polygalacturonase from Bacillus subtilis RCK under solid-state fermentation (SSF) conditions. Through the analysis of RSM-I, wheat bran-to-moisture ratio and inoculum volume were found to be the most significant factors and an increment in both had a positive effect in enhancing enzyme yield, while in RSM-II all the factors significantly affected enzyme recovery except fermented bran-to-solvent ratio, which had the least impact within the ranges investigated in enhancing enzyme recovery. Based on contour plots and variance analysis, optimum operational conditions for maximum exo-polygalacturonase yield were achieved when 1.5% (v/w) of 24h old (OD(600 nm) approximately 2.7+/-0.2) B. subtilis RCK cells were inoculated on moistened wheat bran (1:7 solid substrate-to-moisture ratio) and enzyme was harvested by addition of solvent (1:6 fermented bran-to-solvent ratio) under shaking conditions (200 rpm) in presence of SDS (0.25% w/v) for 15 min at 35 degrees C. An over all 3.4 fold (1.7-fold RSM-I; 2.0 fold RSM-II) increase in enzyme production was attained because of optimization by RSM.     

Real encoded genetic algorithm and response surface methodology to optimize production of an indolizidine alkaloid, swainsonine, from Metarhizium anisopliae

Response surface methodology (RSM) and artificial neural network-real encoded genetic algorithm (ANN-REGA) were employed to develop a process for fermentative swainsonine production from Metarhizium anisopliae (ARSEF 1724). The effect of finally screened process variables viz. inoculum size, oatmeal extract, glucose, and CaCl₂ were investigated through central composite design and were further utilized for training sets in ANN with training and test R values of 0.99 and 0.94, respectively. ANN-REGA was finally employed to simulate the predictive swainsonine production with best evolved media composition. ANN-REGA predicted a more precise fermentation model with 103 % (shake flask) increase in alkaloid production compared to 75.62 % (shake flask) obtained with RSM model upon validation.     

Artificial Intelligence versus Statistical Modeling and Optimization of Cholesterol Oxidase Production by using Streptomyces Sp.

Cholesterol oxidase (COD) is a bi-functional FAD-containing oxidoreductase which catalyzes the oxidation of cholesterol into 4-cholesten-3-one. The wider biological functions and clinical applications of COD have urged the screening, isolation and characterization of newer microbes from diverse habitats as a source of COD and optimization and over-production of COD for various uses. The practicability of statistical/ artificial intelligence techniques, such as response surface methodology (RSM), artificial neural network (ANN) and genetic algorithm (GA) have been tested to optimize the medium composition for the production of COD from novel strain Streptomyces sp. NCIM 5500. All experiments were performed according to the five factor central composite design (CCD) and the generated data was analysed using RSM and ANN. GA was employed to optimize the models generated by RSM and ANN. Based upon the predicted COD concentration, the model developed with ANN was found to be superior to the model developed with RSM. The RSM-GA approach predicted maximum of 6.283 U/mL COD production, whereas the ANN-GA approach predicted a maximum of 9.93 U/mL COD concentration. The optimum concentrations of the medium variables predicted through ANN-GA approach were: 1.431 g/50 mL soybean, 1.389 g/50 mL maltose, 0.029 g/50 mL MgSO₄, 0.45 g/50 mL NaCl and 2.235 ml/50 mL glycerol. The experimental COD concentration was concurrent with the GA predicted yield and led to 9.75 U/mL COD production, which was nearly two times higher than the yield (4.2 U/mL) obtained with the un-optimized medium. This is the very first time we are reporting the statistical versus artificial intelligence based modeling and optimization of COD production by Streptomyces sp. NCIM 5500.     

甲烷利用菌培养条件的优化及其初步应用

利用统计学实验设计（RSM）对能够利用甲烷的假单胞菌菌株ME16主要培养条件进行了优化。以液体无机盐和甲烷气体作为培养基分别进行了温度、接种量、甲烷含量和培养pH对细菌生长影响的研究,并在此基础上,利用响应面法分析优化了ME16菌株的主要培养条件,得到最佳培养条件为：温度29.4℃,接种量1.8%,甲烷含量25%。采用优化培养条件进行培养,细菌生物量增大0.8倍,达到稳定期的培养时间缩短了50h。该菌株初步应用于甲烷气体的脱除,脱除率达65.7 %,表明该菌株能良好的脱除空气中甲烷。     

Optimization of fermentation medium for triterpenoid production from <Emphasis Type="Italic">Antrodia camphorata</Emphasis> ATCC 200183 using artificial intelligence-based techniques

In this study, alteration in morphology of submergedly cultured Antrodia camphorata ATCC 200183 including arthroconidia, mycelia, external and internal structures of pellets was investigated. Two optimization models namely response surface methodology (RSM) and artificial neural network (ANN) were built to optimize the inoculum size and medium components for intracellular triterpenoid production from A. camphorata. Root mean squares error, R ², and standard error of prediction given by ANN model were 0.31%, 0.99%, and 0.63%, respectively, while RSM model gave 1.02%, 0.98%, and 2.08%, which indicated that fitness and prediction accuracy of ANN model was higher when compared to RSM model. Furthermore, using genetic algorithm (GA), the input space of ANN model was optimized, and maximum triterpenoid production of 62.84 mg l⁻¹ was obtained at the GA-optimized concentrations of arthroconidia (1.78 × 10⁵ ml⁻¹) and medium components (glucose, 25.25 g l⁻¹; peptone, 4.48 g l⁻¹; and soybean flour, 2.74 g l⁻¹). The triterpenoid production experimentally obtained using the ANN–GA designed medium was 64.79 ± 2.32 mg l⁻¹ which was in agreement with the predicted value. The same optimization process may be used to optimize many environmental and genetic factors such as temperature and agitation that can also affect the triterpenoid production from A. camphorata and to improve the production of bioactive metabolites from potent medicinal fungi by changing the fermentation parameters.     

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.     

Production of an extracellular alkaline metalloprotease from a newly isolated, moderately halophile, Salinivibrio sp. strain AF-2004

An extracellular protease was produced under stress conditions of high temperature and high salinity by a newly isolated moderate halophile, Salinivibrio sp. strain AF-2004 in a basal medium containing peptone, beef extract, glucose and NaCl. A modification of Kunitz method was used for protease assay. The isolate was capable of producing protease in the presence of sodium chloride, sodium sulfate, sodium nitrate, sodium nitrite, potassium chloride, sodium acetate and sodium citrate. The maximum protease was secreted in the presence of 7.5 to 10% (w/v) sodium sulfate or 3% (w/v) sodium acetate (4.6 U ml⁻¹). Various carbon sources including glucose, lactose, casein and peptone were capable of inducing enzyme production. The optimum pH, temperature and aeration for enzyme production were 9.0, 32 °C and 220 rpm, respectively. The enzyme production corresponded with growth and reached a maximum level during the mid-stationary phase. Maximum protease activity was exhibited in the medium containing 1% (w/v) NaCl at 60 °C, with 18% and 41% activity reductions at temperature 50 and 70 °C, respectively. The optimum pH for enzyme activity was 8.5, with 86% and 75% residual activities at pH 10 and 6, respectively. The activity of enzyme was inhibited by EDTA. These results suggest that the protease secreted by Salinivibrio sp. strain AF-2004 is industrially important from the perspectives of its activity at a broad pH ranges (5.0–10.0), its moderate thermoactivity in addition to its high tolerance to a wide range of salt concentration (0–10% NaCl).     

Optimization and modeling studies on the production of a new fibrinolytic protease using <Emphasis Type="Italic">Streptomyces radiopugnans</Emphasis>_VITSD8

Background

The current study demonstrated the possibility of statistical design tools combination with computational tools for optimization of fermentation conditions for enhanced fibrinolytic protease production.

Methods

The effects of using different carbon and nitrogen sources for protease production by Streptomyces radiopugnans_VITSD8 were examined by a full factorial design method. The incubation time, temperature, pH of the medium, and RPM were assessed by the predictable one factor at a time (OFAT) method. Optimization was carried out using starch and oat meal as carbon source, nitrogen source as peptic and malt extract using Fractional Factorial Design (FFD). The analysis was further continued for medium volume, temperature, initial medium pH, inoculum concentration, high determination co-efficient as (R’-0.965), and lower determination co-efficient of variation (CV-8.19%), which defines a reliable and accurate experimental value.

Results

Analysis of variance by the fixed slope effect by temperature and starch; temperature and L-aspargine, temperature and oat meal, temperature and peptic extracts, temperature and pH, temperature and duration of incubation were more vital for protease production at an interactive level. Response surface plots revealed that temperature, starch, and peptic extracts affix critical concerning in temperature. Programming estimated a 28% increase in protease production. Incubation temperature and medium volume portrayed extreme impact among all factor. Starch, peptic and temperature play an important regulatory role in protease production. Optimium temperature for protease production was 33°C. The ratio of carbon and nitrogen sources and pH were the major regulatory factors in protease production by Streptomyces radiopugnans_VITSD8. It demonstrated a 4% noteworthy change in condition.

Conclusion

Among all the selected parameters, temperature was the most intuitive factor, demonstrating a notable connection with the type of media and pH, while inoculum fixation had a direct impact on protein production.

     

Artificial neural network and response surface methodology: a comparative analysis for optimizing rice straw pretreatment and saccharification

Abstract

The present study demonstrates a comparative analysis between the artificial neural network (ANN) and response surface methodology (RSM) as optimization tools for pretreatment and enzymatic hydrolysis of lignocellulosic rice straw. The efficacy for both the processes, that is, pretreatment and enzymatic hydrolysis was evaluated using correlation coefficient (R²) & mean squared error (MSE). The values of R² obtained by ANN after training, validation, and testing were 1, 0.9005, and 0.997 for pretreatment and 0.962, 0.923, and 0.9941 for enzymatic saccharification, respectively. On the other hand, the R² values obtained with RSM were 0.9965 for cellulose recovery and 0.9994 for saccharification efficiency. Thus, ANN and RSM together successfully identify the substantial process conditions for rice straw pretreatment and enzymatic saccharification. The percentage of error for ANN and RSM were 0.009 and 0.01 for cellulose recovery and for 0.004 and 0.005 for saccharification efficiency, respectively, which showed the authority of ANN in exemplifying the non-linear behavior of the system.     

Influence of inoculum activity on the bio-methanization of a kitchen waste under different waste/inoculum ratios

The use of a granular inoculum prevented acidification during the anaerobic batch biodegradation of a kitchen waste for waste/inoculum ratios in the range of 0.5–2.3 g VS/g VS, when the alkalinity/COD ratio was 37 mg NaHCO₃/g COD. In similar experiments but using a suspended sludge with a significantly lower activity, the methane production rates and the biodegradability were significantly lower and the pH decreased below 5.5 at the waste/inoculum ratio of 2.3 g VS/g VS. When the added alkalinity was decreased to 2 mg NaHCO₃/g COD, the ratio waste/inoculum was clearly more important than the inoculum activity, since, irrespective of the sludge used, acidification occurred at waste/inoculum ratios higher than 0.5 g VS/g VS. The advantage of using granular sludge was further investigated in order to define reasonable condition of waste/inoculum ratio and added alkalinity that could be applied in practice. For a waste/inoculum ratio of 1.35, there were no significant differences between the results obtained for the biodegradability and maximum methane production rate (MMPR), when the alkalinity decreased from 44 to 22 mg NaHCO₃/g COD.     

Physical factors affecting the production of organic solvent-tolerant protease by Pseudomonas aeruginosa strain K

The physical factors affecting the production of an organic solvent-tolerant protease from Pseudomonas aeruginosa strain K was investigated. Growth and protease production were detected from 37 to 45 degrees C with 37 degrees C being the optimum temperature for P. aeruginosa. Maximum enzyme activity was achieved at static conditions with 4.0% (v/v) inoculum. Shifting the culture from stationary to shaking condition decreased the protease production (6.0-10.0% v/v). Extracellular organic solvent-tolerant protease was detected over a broad pH range from 6.0 to 9.0. However, the highest yield of protease was observed at pH 7.0. Neutral media increased the protease production compared to acidic or alkaline media.