Statistical and Artificial Neural Network Approaches to Modeling and Optimization of Fermentation Conditions for Production of a Surface/Bioactive Glyco-lipo-peptide

Statistical versus neural network-embedded swarm intelligence optimization of a metallo-neutral-protease production: activity kinetics and food industry applications

An integrated approach involving response surface methodology (RSM) and artificial neural network-ant-colony hybrid optimization (ANN-ACO) was adopted to develop a bioprocess medium to increase the yield of Bacillus cereus neutral protease under submerged fermentation conditions. The ANN-ACO model was comparatively superior (predicted r2 = 98.5%, mean squared error [MSE] = 0.0353) to RSM model (predicted r2 = 86.4%, MSE = 23.85) in predictive capability arising from its low performance error. The hybrid model recommended a medium containing (gL-1) molasses 45.00, urea 9.81, casein 25.45, Ca2+ 1.23, Zn2+ 0.021, Mn2+ 0.020, and 4.45% (vv-1) inoculum, for a 6.75-fold increase in protease activity from a baseline of 76.63 UmL-1. Yield was further increased in a 5-L bioreactor to a final volumetric productivity of 3.472 mg(Lh)-1. The 10.0-fold purified 46.6-kDa-enzyme had maximum activity at pH 6.5, 45-55 °C, with Km of 6.92 mM, Vmax of 769.23 µmolmL-1 min-1, kcat of 28.49 s-1, and kcat/Km of 4.117 × 103 M-1 s-1, at 45 °C, pH 6.5. The enzyme was stabilized by Ca2+, activated by Zn2+ but inhibited by EDTA suggesting that it was a metallo-protease. The biomolecule significantly clarified orange and pineapple juices indicating its food industry application.

Common operational issues and possible solutions for sustainable biosurfactant production from lignocellulosic feedstock

Surfactants are compounds with high surface activity and emulsifying property. These compounds find application in food, medical, pharmaceutical, and petroleum industries, as well as in agriculture, bioremediation, cleaning, cosmetics, and personal care product formulations. Due to their widespread use and environmental persistence, ensuring biodegradability and sustainability is necessary so as not to harm the environment. Biosurfactants, i.e., surfactants of plant or microbial origin produced from lignocellulosic feedstock, perform better than their petrochemically derived counterparts on the scale of net-carbon-negativity. Although many biosurfactants are commercially available, their high cost of production justifies their application only in expensive pharmaceuticals and cosmetics. Besides, the annual number of new biosurfactant compounds reported is less, compared to that of chemical surfactants. Multiple operational issues persist in the biosurfactant value chain. In this review, we have categorized some of these issues based on their relative position in the value chain - hurdles occurring during planning, upstream processes, production stage, and downstream processes - alongside plausible solutions. Moreover, we have presented the available paths forward for this industry in terms of process development and integrated pretreatment, combining conventional tried-and-tested strategies, such as reactor designing and statistical optimization with cutting-edge technologies including metabolic modeling and artificial intelligence. The development of techno-economically feasible biosurfactant production processes would be instrumental in the complete substitution of petrochemical surfactants, rather than mere supplementation.

Enhanced production of mycelium biomass and exopolysaccharides of Pleurotus ostreatus by integrating response surface methodology and artificial neural network

This study aimed to enhance the production of mycelium biomass and exopolysaccharides (EPS) of Pleurotus ostreatus in submerged fermentation. Response Surface Methodology (RSM)sought to optimize culture conditions, whereas Artificial Neural Network (ANN)aimed to predict the mycelium biomass and EPS. After optimization of RSM model conditions, the maximum biomass (36.45 g/L) and EPS (6.72 g/L) were obtained at the optimum temperature of 22.9 °C, pH 5.6, and agitation of 138.9 rpm. Further, the Genetic Algorithm (GA) was employed to optimize the cultivation conditions in order to maximize the mycelium biomass and EPS production. The ANN model with an optimized network structure gave the coefficient of determination (R2) value of 0.99 and the least mean squared error of 1.9 for the validation set. In the end, a graphical user interface was developed to predict mycelium biomass and EPS production.

Unlocking the potential of biosurfactants: Production, applications, market challenges, and opportunities for agro-industrial waste valorization

Biosurfactants are eco-friendly compounds with unique properties and promising potential as sustainable alternatives to chemical surfactants. The current review explores the multifaceted nature of biosurfactant production and applications, highlighting key fermentative parameters and microorganisms able to convert carbon-containing sources into biosurfactants. A spotlight is given on biosurfactants' obstacles in the global market, focusing on production costs and the challenges of large-scale synthesis. Innovative approaches to valorizing agro-industrial waste were discussed, documenting the utilization of lignocellulosic waste, food waste, oily waste, and agro-industrial wastewater in the segment. This strategy strongly contributes to large-scale, cost-effective, and environmentally friendly biosurfactant production, while the recent advances in waste valorization pave the way for a sustainable society.

Application of the novel manta-ray foraging algorithm to optimize acidic peptidase production in solid-state fermentation using binary agro-industrial waste

Peptidases, which constitute about 20% of the global enzyme market, have found applications in detergent, food and pharmaceutical industries, and could be produced on a large scale using low-cost agro-industrial waste. An acidophilic Bacillus cereus strain produced acidic peptidase on binary-agro-industrial waste comprising yam peels and fish processing waste at pH 4.5 with high catalytic activity. A five-variable central composite rotatable design of a response surface methodology was used to model bioprocess conditions for improved peptidase production in solid-state fermentation. Data generated was leveraged as the basis for applying the novel Manta-ray foraging optimization-linked feed-forward artificial neural network to predict bioprocess conditions optimally. Results obtained from the optimization experiments revealed a significant coefficient of determination of 0.9885 with low-performance error. The bioprocess predicted a peptidase activity of 1035.32 U/mL under optimized conditions set as 54.8 g/100 g yam peels, 23.85 g/100 g fish waste, 0.31 g/100 g CaCl2, 47.54% (v/w) moisture content, and pH 2. Peptidase activity was improved 5-fold, and was stable for 240 min between pH 2.5 and 3.5. Michaelis-Menten kinetics revealed a Km of 0.119 mM and a catalytic efficiency of 45462.19 mM-1 min-1. The bioprocess holds promise for sustainable enzyme-driven applications.

Strain improvement, artificial intelligence optimization, and sensitivity analysis of asparaginase-mediated acrylamide reduction in sweet potato chips

In recent times, L-asparaginase has emerged as a potential anti-carcinogen through hydrolysis of L-asparagine in the blood for anti-leukemic application, and in carbohydrate-based foods, for acrylamide reduction applications. In this study, Aspergillus sydowii strain UCCM 00124 produced an L-asparaginase with a baseline acrylamide reduction potential of 64.5% in sweet potato chips. Plasma mutagenesis at atmospheric pressure and room temperature (ARTP) was employed to improve L-asparaginase production while artificial neural network embedded with genetic algorithm (ANN-GA) and global sensitivity analysis were used to identify and optimize process conditions for improved acrylamide reduction in sweet potato chips. The ARTP mutagenesis generated a valine-deficient mutant, Val-Asp-S-180-L with 2.5-fold L-asparaginase improvement. The ANN-GA hybrid evolutionary intelligence significantly improved process efficiency to 98.18% under optimized conditions set as 118.6 °C, 726.37 g/L asparagine content, 9.92 µg/mL L-asparaginase, 4.54% NaCl, and soaking time of 15 h without significant changes in sensory properties. The sensitivity index revealed initial asparagine content as the most sensitive parameter to the bioprocess. The enzyme demonstrated significant thermo-stability with Arrhenius deactivation rate constant, Kd, of 0.00562 min-1 and half-life, t1/2, of 123.35 min at 338 K. These conditions are recommended for sustainable healthier, and safer sweet potato chips processing in the food industry.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13197-023-05757-5.

Biosurfactants: Secondary Metabolites Involved in the Process of Bioremediation and Biofilm Removal

The search for environmentally friendly methods to remove persistent substances such as organic pollutants and sessile communities such as biofilms that severely affect the environment and human health resulted in biosurfactant discovery. Owing to their low level of toxicity and high biodegradability, biosurfactants are increasingly preferred to be used for removal of pollutants from nature. These amphipathic molecules can be synthesized inexpensively, employing cheap substrates such as agricultural and industrial wastes. Recent progress has been made in identifying various biosurfactants that can be used to remove organic pollutants and harmful microbial aggregates, as well as novel microbial strains that produce these surface-active molecules to survive in a hydrocarbon-rich environment. This review focuses on the identification and understanding the role of biosurfactants and the microorganisms involved in the removal of biofilms and remediation of xenobiotics and various types of hydrocarbons such as crude oil, aromatic hydrocarbons, n-alkanes, aliphatic hydrocarbons, asphaltenes, naphthenes, and other petroleum products. This property of biosurfactant is very important as biofilms are of great concern due to their impact on the environment, public health, and industries worldwide. This work also includes several advanced molecular methods that can be used to enhance the production of biosurfactants by the microorganisms studied.

Prediction of surfactin fermentation with Bacillus subtilis DSM10 by response surface methodology optimized artificial neural network

Biosurfactants produced by Bacillus species are an emerging group of surface-active molecules. They have excellent surface tension reducer and high emulsifier properties. Generally, the biosurfactant fermentation leads to a low product concentration. Therefore, our goal was to investigate Bacillus subtilis DSM10 production and improve the biosurfactant content in the broth by media optimization via response surface methodology. The optimal combinations of the investigated factors were determined as the following: pH = 9, glucose = 20 g/L, and NH₄ NO₃  = 2 g/L. Under the optimized conditions, the formed surfactin strain reduced surface tension in the broth by 48% (from 72 to 37 mN/m) and the isolated product by 63% (from 72 to 27 mN/m). An artificial neural network was built based on the results of response surface methodology to predict the product quality and the harvesting time of broth. Thus, finally, the model can predict the final cell and product amount, and even their time course, with around 90% reliability.

Production, characterization and techno-economic evaluation of Aspergillus fusant L-asparaginase

Protoplast fusion is one of the most reliable methods of introducing desirable traits into industrially-promising fungal strains. It harnesses the entire genomic repertoire of fusing microorganisms by routing the natural barrier and genetic incompatibility between them. In the present study, the axenic culture of a thermo-halotolerant strain of Aspergillus candidus (Asp-C) produced an anti-leukemic L-asparaginase (L-ASNase) while a xylan-degrading strain of Aspergillus sydowii (Asp-S) produced the acrylamide-reduction type. Protoplast fusion of the wild strains generated Fusant-06 with improved anti-leukemic and acrylamide reduction potentials. Submerged fed-batch fermentation was preferred to batch and continuous modes on the basis of impressive techno-economics. Fusant-06 L-ASNase was purified by PEG/Na⁺ citrate aqueous two-phase system (ATPS) to 146.21-fold and global sensitivity analysis report revealed polymer molecular weight and citrate concentration as major determinants of yield and purification factor, respectively. The enzyme was characterized by molecular weight, amino acid profile, activity and stability to chemical agents. Michaelis-Menten kinetics, evaluated under optimum conditions gave K_m, V_max, K_cat, and K_cat/K_m as 6.67 × 10^-5 M, 1666.67 µmolmin^-1 mg^-1 protein, 3.88 × 10⁴ min^-1 and 5.81 × 10⁸ M^-1.min^-1 respectively. In-vitro cytotoxicity of HL-60 cell lines by Fusant-06 L-ASNase improved significantly from their respective wild strains. Stability of Fusant-06 L-ASNase over a wide range of pH, temperature and NaCl concentration, coupled with its micromolar K_m value, confers commercial and therapeutic value on the product. Free-radical scavenging and acrylamide reduction activities were intermediate and the conferred thermo-halo-stability could be exploited for sustainable clinical and food industry applications.

Interspecific protoplast fusion of atmospheric and room-temperature plasma mutants of Aspergillus generates an L-asparaginase hyper-producing hybrid with techno-economic benefits

The axenic culture of Aspergillus candidus (Asp-C) produced an anti-leukemic L-asparaginase while Aspergillus sydowii (Asp-S) produced the acrylamide-reduction type. Upon mutagenesis by atmospheric and room-temperature plasma (ARTP), their individual L-asparaginase activities improved 2.3-folds in each of Ile^-Thr^-Asp-C-180-K and Val^-Asp-S-180-E stable mutants. Protoplast fusion of selected stable mutants generated fusant-09 with improved anti-leukemic activity, acrylamide reduction, higher temperature optimum and superior kinetic parameters. Submerged (SmF) and solid-state fermentation (SSF) types were compared; likewise batch, fed-batch and continuous fermentation modes; and fed-batch submerged fermentation was selected on the basis of impressive techno-economics. Fusant L-asparaginase was purified by PEG/Na⁺ citrate aqueous two-phase system and molecular exclusion chromatography to 69.96 and 146.21-fold, respectively, and characterized by molecular weight, specificity, activity and stability to chemical and physical agents. Michaelis-Menten kinetics, evaluated under optimum conditions gave K_m, V_max, K_cat, and K_cat/K_m as 1.667 × 10^-3 M, 1666.67 µmol min^-1 mg^-1 protein, 645.99 s^-1 and 3.88 × 10⁵ M^-1 s^-1 respectively. In-vitro cytotoxicity of HL-60 cell lines by fusant-09 L-asparaginase improved 3.00 and 18.71-folds from mutants Ile^-Thr^-Asp-C-180-K and Val^-Asp-S-180-E, and from 5.73 and 32.55 from respective original strains. Free-radical scavenging and acrylamide reduction improvements were intermediate. Fusant-09 L-asparaginase is strongly recommended for sustainable economic anti-leukemic and food industry applications.

Stochastic modeling and meta-heuristic multivariate optimization of bioprocess conditions for co-valorization of feather and waste frying oil toward prodigiosin production

Serratia marcescens strain UCCM 00009 produced a mixture of gelatinase and keratinase to facilitate feather degradation but concomitant production of prodigiosin could make waste feather valorization biotechnologically more attractive. This article describes prodigiosin fermentation through co-valorization of waste feather and waste frying peanut oil by S. marcescens UCCM 00009 for anticancer, antioxidant, and esthetic applications. The stochastic conditions for waste feather degradation (WFD), modeled by multi-objective particle swarm-embedded-neural network optimization (ANN-PSO), revealed a gelatinase/keratinase ratio of 1.71 for optimal prodigiosin production and WFD. Luedeking-Piret kinetics revealed a non-exclusive, non-growth-associated prodigiosin yield of 9.66 g/L from the degradation of 88.55% waste feather within 96 h. The polyethylene glycol (PEG) 6000/Na⁺ citrate aqueous two-phase system-purified serratiopeptidase demonstrated gelatinolytic and keratinolytic activities that were stable for 240 h at 55 °C and pH 9.0. In vitro evaluations revealed that the prodigiosin inhibited methicillin-resistant Staphylococcus aureus at IC₅₀ of 4.95 µg/mL, the plant-pathogen, Sclerotinia sclerotiorum, at IC₅₀ of 2.58 µg/mL, breast carcinoma at IC₅₀ of 0.60 µg/mL and 2,2-diphenyl-1-picryl-hydrazyl hydrate (DPPH) free-radical at IC₅₀ of 96.63 µg/mL). The pigment also demonstrated commendable textile dyeing potential of fiber and cotton fabrics. The technology promises cost-effective prodigiosin development through sustainable waste feather-waste frying oil co-management.

Overproduction of a thermo-stable halo-alkaline protease on agro-waste-based optimized medium through alternate combinatorial random mutagenesis of Stenotrophomonas acidaminiphila

•

Alternate combinatorial random mutagenesis selected a protease high-yielding mutant.

•

Medium optimization led to 25.55-fold raise in specific protease yield in bioreactor.

•

20% PEG-1500/Na+ 15% citrate recovered 74% activity yield with 52.55 purity.

•

Activity was retained at elevated physicochemical levels but inhibited by PMSF.

•

Keratinolytic and blood-stain removal activities confer industrial potential on protease.

A strain of Stenotrophomonas acidaminiphila, isolated from fermenting bean-processing wastewater, produced alkaline protease in pretreated cassava waste-stream, but with low yield. Strain improvement by alternate combinatorial random mutagenesis and bioprocess optimization using comparative statistical and neural network methods enhanced yield by 17.8-fold in mutant kGy-04-UV-25. Kinetics of production by selected mutant modeled by logistic and modified Gompertz functions revealed higher specific growth rate in mutant than in the parent strain, likewise volumetric and specific productivities. Purification by PEG/Na⁺ citrate aqueous two-phase system recovered 73.87% yield and 52.55-fold of protease. Its activity was stable at 5–35% NaCl, 45–75°C, and was significantly enhanced by 1–15 mM sodium dodecyl sulfate (SDS). The protease was inhibited by low concentrations of phenyl-methyl-sulfonyl fluoride but was activated by 1–5 mM Mn²⁺ suggesting a manganese-dependent serine‑protease. The 45.7 kDa thermo-halo-stable alkaline protease demonstrated keratinolytic and blood-stain removal potentials showing prospects in textile and detergent industries, respectively.

Artificial neural network modeling and statistical optimization of medium components to enhance production of exopolysaccharide by Bacillus sp. EPS003

Microbial Exopolysaccharides (EPS) have a wide range of applications in food, cosmetics, agriculture, pharmaceutical industries, and environmental bioremediation. The present study aims at enhancing the production of EPS from a soil-isolate Bacillus sp. EPS003. Effects of carbon and nitrogen sources and process conditions were evaluated one factor at a time. Box-Behnken design has been used and a 2.5-fold increase in yield is reported after optimizing the most influential parameters sucrose, yeast extract, and peptone as identified by the Plackett-Burman method. An artificial neural network (ANN) with two different topologies (EPS-NN1 and EPS-NN2) was developed. On comparing prediction accuracy, EPS-NN2 formulated as one input layer with four input variables (sucrose, yeast extract, peptone, biomass), a single hidden layer with seven neurons and EPS yield in the output layer showed a high coefficient of determination (R²-0.98) and low error (NRMSE-0.024). This study concludes that the consideration of biomass value has increased the prediction accuracy of the model.

A novel strain of Stenotrophomonas acidaminiphila produces thermostable alkaline peptidase on agro-industrial wastes: process optimization, kinetic modeling and scale-up

Bacterial alkaline peptidases, especially from Bacillus species, occupy the frontline in global enzyme market, albeit with poor production economics. Here, we report the deployment of response surface methodology approximations to optimize fermentation parameters for enhanced yield of alkaline peptidase by the non-Bacillus bacterium; Stenotrophomonas acidaminiphila. Shake flask production under optimized conditions was scaled up in a 5-L bench-scale bioreactor. Logistic and modified Gompertz models revealed significant fits for biomass formation, total protein, and substrate consumption models. Maximum specific growth rate (µ_max = 0.362 h^-1) of the bacterium in the optimized medium did not differ significantly from those in Luria-Bertani and trypticase soy broths. The aqueous two-phase system-purified 45.7 kDa alkaline protease retained 83% activity which improved with increasing sodium dodecyl sulfate concentration thus highlighting potential laundry application. Maximum enzyme activity occurred at 75ºC and pH 10.5 but was inhibited by 5 mM phenyl-methyl-sulfonyl fluoride suggesting a serine-protease nature.

Modelling of fermentative bioethanol production from indigenous Ulva prolifera biomass by Saccharomyces cerevisiae NFCCI1248 using an integrated ANN-GA approach

Third generation biomass (marine macroalgae) has been projected as a promising alternative energy resource for bioethanol production due to its high carbon and no lignin composition. However, the major challenge in the technologies of production lies in the fermentative bioconversion process. Therefore, in the present study the predictive ability of an integrated artificial neural network with genetic algorithm (ANN-GA) in the modelling of bioethanol production was investigated for an indigenous marine macroalgal biomass (Ulva prolifera) by a novel yeast strain, Saccharomyces cerevisiae NFCCI1248 using six fermentative parameters, viz., substrate concentration, fermentation time, inoculum size, temperature, agitation speed and pH. The experimental model was developed using one-variable-at-a-time (OVAT) method to analyze the effects of the fermentative parameters on bioethanol production and the obtained regression equation was used as a fitness function for the ANN-GA modelling. The ANN-GA model predicted a maximum bioethanol production at 30 g/L substrate, 48 h fermentation time, 10% (v/v) inoculum, 30 °C temperature, 50 rpm agitation speed and pH 6. The maximum experimental bioethanol yield obtained after applying ANN-GA was 0.242 ± 0.002 g/g RS, which was in close proximity with the predicted value (0.239 g/g RS). Hence, the developed ANN-GA model can be applied as an efficient approach for predicting the fermentative bioethanol production from macroalgal biomass.

L-asparaginase production in solid-state fermentation using Aspergillus niger: process modeling by artificial neural network approach

L-asparaginase has proven itself as a potential anti-cancer drug and in the mitigation of acrylamide formation in the food industry. In the present investigation, a novel utilization of niger (Guizotia abyssinica) de-oiled cake as the sole source for the cost-effective production of L-asparaginase was evaluated and compared with different agro-substrates in solid-state fermentation. The substrate provided a favorable C/N content for the L-asparaginase production as evident from the chemical composition (CHNS analysis) of the substrate. The influential process parameters viz; autoclaving time, moisture content, temperature and pH were optimized and modeled using machine-learning based artificial neural network (ANN) and statistical-based response surface methodology (RSM). The maximum enzyme activity of 34.65 ± 2.18 IU/gds was observed at 30.3 min of autoclaving time, 62% moisture content, 30 °C temperature and 6.2 pH in 96 h. A 1.36 fold improvement in enzyme activity was observed on utilizing optimized parameters. In comparison with RSM, the ANN model showed superior prediction with a low mean squared error of 0.072, low root mean squared error of 0.268 and 0.99 value of regression coefficient. The present study demonstrates the novel utilization of inexpensive and readily available agro-industrial waste for the development of cost-effective L-asparaginase production process.

Bioprocess Optimization of Nutritional Parameters for Enhanced Anti-leukemic L-Asparaginase Production by Aspergillus candidus UCCM 00117: A Sequential Statistical Approach

Sequential optimization of bioprocess nutritional conditions for production of glutaminase-near-free L-asparaginase by Aspergillus candidus UCCM 00117 was conducted under shake flask laboratory conditions. Catalytic and anti-cancer activities of the poly-peptide were evaluated using standard in vitro biochemical methods. Medium nutrients were selected by one-factor-at-a-time (OFAT) approach while Plackett-Burman design (PBD) screened potential factors for optimization. Path of steepest ascent (PSA) and response surface methodology (RSM) of a Min-Run-Res V fractional factorial of a central composite rotatable design (CCRD) were employed to optimize factor levels towards improved enzyme activity. A multi-objective approach using desirability function generated through predictor importance and weighted coefficient methodology was adopted for optimization. The approach set optimum bioprocess conditions as 49.55 g/L molasses, 64.98% corn steep liquor, 44.23 g/L asparagine, 1.73 g/L potassium, 0.055 g/L manganese and 0.043 g/L chromium (III) ions, at a composite desirability of 0.943 and an L-asparaginase activity of 5216.95U. The Sephadex-200 partially-purified polypeptide had a specific activity of 476.84 U/mg; 0.087U glutaminase activity, 36.46% yield and 20-fold protein purification. Anti-cancer activity potentials of the catalytic poly-peptide were dose-dependent with IC₅₀ (µg/mL): 4.063 (HL-60), 13.75 (HCT-116), 15.83 (HeLa), 11.68 (MCF-7), 7.61 (HepG-2). The therapeutic enzyme exhibited 15-fold more cytotoxicity to myeloid leukemia cell line than to normal (HEK 238 T) cell. Optimum temperature and pH for activity were within physiological range. However, significant interactions between exposure time and levels of each of temperature and pH made interpretations of residual enzyme activities difficult. The manganese-dependent L-asparaginase from Aspergillu s candidus UCCM 00117 is recommended for further anticancer drug investigations.