Design of experiments and artificial neural network linked genetic algorithm for modeling and optimization of L-asparaginase production by Aspergillus terreus MTCC 1782

Optimizing recombinant antibody fragment production: A comparison of artificial intelligence and statistical modeling

Maximizing the recombinant protein yield necessitates optimizing the production medium. This can be done using a variety of methods, including the conventional "one-factor-at-a-time" approach and more recent statistical and mathematical methods such as artificial neural network (ANN), genetic algorithm, etc. Every approach has advantages and disadvantages of its own, yet even when a technique has flaws, it is nevertheless used to get the best results. Here, one categorical variable and four numerical parameters, including post-induction time, inducer concentration, post-induction temperature, and pre-induction cell density, were optimized using the 232 experimental assays of the central composite design. The direct and indirect effects of factors on the yield of anti-epithelial cell adhesion molecule extracellular domain fragment antibody were examined using statistical methods. The analysis of variance results indicate that the response surface methodology (RSM) model is effective in predicting the amount of produced single-chain fragment variable (p-value = 0.0001 and R2 = 0.905). For ANN modeling, the evaluation using normalized root mean square error (NRMSE) and R2 values shows a good fit (R2 = 0.942) and accurate predictions (NRMSE = 0.145). The analysis of error parameters and R2 of a dataset, which contained 30 data points randomly selected from the complete dataset, showed that the ANN model had a higher R2 value (0.968) compared to the RSM model (0.932). Furthermore, the ANN model demonstrated stronger predictive ability with a lower NRMSE (0.048 vs. 0.064). Induction at the cell density of 0.7 and an isopropyl β-D-1-thiogalactopyranoside concentration of 0.6 mM for 32 h at 30°C in BW25113 was the ideal culture condition leading to the protein yield of 259.51 mg/L. Under the optimum conditions, the output values predicted by the ANN model (259.83 mg/L) were more in line with the experimental data (259.51 mg/L) than the RSM (276.13 mg/L) expected value. This outcome demonstrated that the ANN model outperforms the RSM in terms of prediction accuracy.

Cunninghamella echinulata DSM1905 biofilm-based L-asparaginase production in pneumatically-driven bioreactors

We evaluated by comparing the performance of three pneumatically-driven bioreactors in the production of L-asparaginase (L-ASNase), an enzyme used to treat leukaemia and lymphoma. A two-step screening process was conducted to detect Cunninghamella spp. strains producing L-ASNase. Cunninghamella echinulata DSM1905 produced the highest levels of L-ASNase during screening assays. Subsequently, fermentations were performed in bubble column (BCR), airlift (ALR), and hybrid fixed-bed airlift (FB-ALR) bioreactors to determine the best upstream bioprocess. Mycelial biomass production was higher in BCR than in ALR and FB-ALR (p ≤ 0.0322). The activity of L-ASNase produced in FB-ALR, in which the fungus grew as a consistent biofilm, was significantly higher (p ≤ 0.022) than that from ALR, which was higher than that of BCR (p = 0.036). The specific activity of ALR and FB-ALR presented no differences (p = 0.073), but it was higher than that of BCR (p ≤ 0.032). In conclusion, C. echinulata DSM1905, grown under the biofilm phenotype, produced the highest levels of L-ASNase, and FB-ALR was the best upstream system for enzyme production.

Challenges in developing cell culture media using machine learning

Microbial and mammalian cells are widely used in the food, pharmaceutical, and medical industries. Developing or optimizing culture media is essential to improve cell culture performance as a critical technology in cell culture engineering. Methodologies for media optimization have been developed to a great extent, such as the approaches of one-factor-at-a-time (OFAT) and response surface methodology (RSM). The present review introduces the emerging machine learning (ML) technology in cell culture engineering by combining high-throughput experimental technologies to develop highly efficient and effective culture media. The commonly used ML algorithms and the successful applications of employing ML in medium optimization are summarized. This review highlights the benefits of ML-assisted medium development and guides the selection of the media optimization method appropriate for various cell culture purposes.

GA-coupled ANN model for predicting porosity in alginate gel scaffolds

Alginate gel scaffolds are biocompatible and biodegradable materials that have been used in a variety of tissue engineering applications. The porosity of alginate gel scaffolds is an important property that affects their performance. However, it is difficult to predict the porosity of alginate gel scaffolds accurately. In this study, a GA-coupled ANN model was developed to predict the porosity of alginate gel scaffolds. The model was trained on a dataset of 107 scaffolds with known porosities. The model was able to achieve a mean absolute error of 0.13, which suggests that it is able to accurately predict the porosity of alginate gel scaffolds. The alginate scaffold was fabricated by a microfluidic technique using a syringe pump and a flow device. The crosslinker solution was poured into the Petri dish to crosslink the polymer to the gel structure. The Archimedes method was used to determine the scaffold's apparent porosity. The artificial neural network has been used to model the porosity of the gel scaffold using the input parameters such as alginate-pluronic viscosity, surface tension, and contact angle etc. The maximum porosity was modelled to be 96.4 % using GA whereas the experimental value for the same was measured to be 92.8 ± 2 %. A 3.7% variation in the porosity was found from modelled value. To the best of our knowledge, this study is the first to develop an integrated ANN-coupled GA model to predict the maximum porosity of the gel scaffold. The result indicates that artificial intelligence has great potential for optimizing the parameters to fabricate the gel scaffold that can be used for tissue engineering applications.

A review of algorithmic approaches for cell culture media optimization

Cell culture media composition and culture conditions play a crucial role in product yield, quality and cost of production. Culture media optimization is the technique of improving media composition and culture conditions to achieve desired product outcomes. To achieve this, there have been many algorithmic methods proposed and used for culture media optimization in the literature. To help readers evaluate and decide on a method that best suits their specific application, we carried out a systematic review of the different methods from an algorithmic perspective that classifies, explains and compares the available methods. We also examine the trends and new developments in the area. This review provides recommendations to researchers regarding the suitable media optimization algorithm for their applications and we hope to also promote the development of new cell culture media optimization methods that are better suited to existing and upcoming challenges in this biotechnology field, which will be essential for more efficient production of various cell culture products.

Bioprocessing and purification of extracellular L-asparaginase produced by endophytic Colletotrichum gloeosporioides and its anticancer activity

L-asparaginase is an enzyme commonly used to treat acute lymphoblastic leukemia. Commercialized bacterial L-asparaginase has been reported to cause several life-threatening complications during treatment, hence the need to seek alternative sources of L-asparaginase. In this study, the novelty of upstream and downstream bioprocessing of L-asparaginase from a fungal endophyte, Colletotrichum gloeosporioides, and the cytotoxicity evaluation was demonstrated. Six variables (carbon source and concentration, nitrogen source and concentration, incubation period, temperature, pH and agitation rate) known to influence L-asparaginase production were studied using One-Factor-At-A-Time (OFAT) approach, with four significant variables further optimized using Response Surface Methodology (RSM). The crude extract produced using optimized condition was purified, characterized and examined for its anticancer effect. Purification of fungal L-asparaginase was performed via ultrafiltration and size exclusion chromatography, which are less common techniques. The protein profile and monomeric weight of L-asparaginase were determined using SDS-PAGE and Western blot. Cytotoxicity of purified L-asparaginase on leukemic Jurkat E6 and oral carcinoma cells were studied using MTS assay for 24 h and 48 h. OFAT results from optimization showed that glucose and L-asparagine concentrations, incubation period and temperature, were significant factors affecting L-asparaginase production by C. gloeosporioides. RSM analysis further evidence the significant interaction between glucose and L-asparagine concentrations in inducing L-asparaginase production. Purified L-asparaginase was profiled with specific activity of 255.02 IU/mg protein, purification fold of 6.12, and 34.63% of enzyme recovery. SDS and Western blot revealed that the purified L-asparaginase might be a tetramer with monomeric units of 25 kDa. Purified L-asparaginase was discovered to be more efficient against Jurkat leukemic cells than against H103 oral carcinoma cells, as lower IC₅₀ value was observed for Jurkat cell lines (46 .36 ± 1.52 µg/mL for Jurkat and 125.56 ± 7.28 µg/mL for H103). In short, purified L-asparaginase derived from endophytic C. gloeosporioides showed high purity and significant anticancer effect toward cancer cells. This study therefore demonstrated the potential of fungal L-asparaginase as alternative chemotherapy drug in the future.

Machine learning modeling for solubility prediction of recombinant antibody fragment in four different E. coli strains

The solubility of proteins is usually a necessity for their functioning. Recently an emergence of machine learning approaches as trained alternatives to statistical models has been evidenced for empirical modeling and optimization. Here, soluble production of anti-EpCAM extracellular domain (EpEx) single chain variable fragment (scFv) antibody was modeled and optimized as a function of four literature based numerical factors (post-induction temperature, post-induction time, cell density of induction time, and inducer concentration) and one categorical variable using artificial neural network (ANN) and response surface methodology (RSM). Models were established by the CCD experimental data derived from 232 separate experiments. The concentration of soluble scFv reached 112.4 mg/L at the optimum condition and strain (induction at cell density 0.6 with 0.4 mM IPTG for 24 h at 23 °C in Origami). The predicted value obtained by ANN for the response (106.1 mg/L) was closer to the experimental result than that obtained by RSM (97.9 mg/L), which again confirmed a higher accuracy of ANN model. To the author's knowledge this is the first report on comparison of ANN and RSM in statistical optimization of fermentation conditions of E.coli for the soluble production of recombinant scFv.

Enrichment of laccase production by Phoma herbarum isolate KU4 under solid-state fermentation by optimizing RSM coefficients using genetic algorithm

The process parameters were optimized to obtain enhanced enzyme activity from the fungus Phoma herbarum isolate KU4 using rice straw and saw dust as substrate under solid-state fermentation using Response surface methodology (RSM). Genetic algorithm was used to validate the RSM for maximum laccase production. Six variables, viz., pH of the media, initial moisture content, copper sulphate concentration, concentration of tannic acid, inoculum concentration and incubation time were found to be effective and optimized for enhanced production. Maximum laccase production was achieved by RSM at pH 5·0 and 86% of initial moisture content of the culture medium, 150 µmol l^-1 of CuSO₄ , 1·5% tannic acid and 0·128 g inoculum g^-1 dry substrate inoculum size on the fourth day of fermentation. The highest laccase activity was observed as 79 008 U g^-1 , which is approximately sixfold enhanced production compared to the unoptimized condition (12 085·26 U g^-1 ).

Optimization and techno-economic analysis of biodiesel production from Calophyllum inophyllum oil using heterogeneous nanocatalyst

The present research work is aimed at reducing the consumption of reactants by process optimization and economic analysis of large-scale commercial plant using techno-economic analysis. The statistical optimization of biodiesel production from Calophyllum inophyllum oil using Zn doped CaO nanocatalyst was used to optimize the conversion efficiency and green chemistry value. The environmental studies on transesterification reaction were done using green chemistry parameters like carbon efficiency, atom economy, reaction mass efficiency, stoichiometric factor and environmental factor. The biodiesel conversion 91.95% was achieved when maintaining the methanol to oil ratio 9.66:1, concentration of catalyst 5% (w/v), time 81.31 min and temperature 56.71 °C with green chemistry value of 0.873. Techno-economic analysis of biodiesel production from Calophyllum inophyllum oil was executed used optimized lab-scale data. The techno-economic analysis of 21 million kg/year biodiesel production plant was investigated. The annual biodiesel revenue of 15,224,000 $/yr and the payback period was about 1.15 years.

Isolation, Purification, Characterisation and Application of L-ASNase: A Review

BACKGROUND

L-ASNase (L-asparagine aminohydrolase EC 3.5.1.1) is used for the conversion of L-asparagine to L-aspartic acid and ammonia and also it was found as an agent of chemotherapeutic property according to recent patents. It is known as an anti-cancer agent and recently it has received an immense attention. Various microorganisms have the ability to secrete the L-ASNase. It is famous world-wide as anti-tumor medicine for acute lymphoblastic leukemia and lymphosarcoma. L-ASNase helps in deamination of Asparagine and Glutamine.

SOURCE

L-ASNase mainly found in two bacterial sources; Escherichia coli and Erwinia carotovora. Isolation from plants: Endophytes were also a great source of L-ASNase. It was isolated from four types of plants named as; C. citratus, O. diffusa, M. koengii, and also P. bleo.

APPLICATIONS

L-ASNase is used as a potential anti-tumor medicine. It plays a very much essential role for the growth of tumor cells. Tumor cells require a lot of asparagine for their growth. But ASNase converts to aspartate and ammonia from asparagine. So the tumor cell does not proliferate and fails to survive. The L-ASNase is used as the medicine for the major type of cancer like acute lymphocytic leukemia (ALL), brain. It also used as a medicine for central nervous system (CNS) tumors, and also for neuroblastoma. Two types of L-ASNase have been found.

CONCLUSION

L-ASNase becomes a powerful anti-tumor medicine and researchers should develop a potent strain of asparaginase which can produce asparaginase in the industrial level. It is also used in the pharmaceutical industry and food industry on a broader scale.

Modelling the removal of volatile pollutants under transient conditions in a two-stage bioreactor using artificial neural networks

A two-stage biological waste gas treatment system consisting of a first stage biotrickling filter (BTF) and second stage biofilter (BF) was tested for the removal of a gas-phase methanol (M), hydrogen sulphide (HS) and α-pinene (P) mixture. The bioreactors were tested with two types of shock loads, i.e., long-term (66h) low to medium concentration loads, and short-term (12h) low to high concentration loads. M and HS were removed in the BTF, reaching maximum elimination capacities (EC_max) of 684 and 33 gm^-3h^-1, respectively. P was removed better in the second stage BF with an EC_max of 130 gm^-3h^-1. The performance was modelled using two multi-layer perceptrons (MLPs) that employed the error backpropagation with momentum algorithm, in order to predict the removal efficiencies (RE, %) of methanol (RE_M), hydrogen sulphide (RE_HS) and α-pinene (RE_P), respectively. It was observed that, a MLP with the topology 3-4-2 was able to predict RE_M and RE_HS in the BTF, while a topology of 3-3-1 was able to approximate RE_P in the BF. The results show that artificial neural network (ANN) based models can effectively be used to model the transient-state performance of bioprocesses treating gas-phase pollutants.

Harnessing QbD, Programming Languages, and Automation for Reproducible Biology

Building robust manufacturing processes from biological components is a task that is highly complex and requires sophisticated tools to describe processes, inputs, and measurements and administrate management of knowledge, data, and materials. We argue that for bioengineering to fully access biological potential, it will require application of statistically designed experiments to derive detailed empirical models of underlying systems. This requires execution of large-scale structured experimentation for which laboratory automation is necessary. This requires development of expressive, high-level languages that allow reusability of protocols, characterization of their reliability, and a change in focus from implementation details to functional properties. We review recent developments in these areas and identify what we believe is an exciting trend that promises to revolutionize biotechnology.

The protective effect of Agaricus blazei Murrill, submerged culture using the optimized medium composition, on alcohol-induced liver injury

Agaricus blazei Murrill (ABM), an edible mushroom native to Brazil, is widely used for nonprescript and medicinal purposes. Alcohol liver disease (ALD) is considered as a leading cause for a liver injury in modern dietary life, which can be developed by a prolonged or large intake of alcohol. In this study, the medium composition of ABM was optimized using response surface methodology for maximum mycelial biomass and extracellular polysaccharide (EPS) production. The model predicts to gain a maximal mycelial biomass and extracellular polysaccharide at 1.047 g/100 mL, and 0.367 g/100 mL, respectively, when the potato is 29.88 g/100 mL, the glucose is 1.01 g/100 mL, and the bran is 1.02 g/100 mL. The verified experiments showed that the model was significantly consistent with the model prediction and that the trends of mycelial biomass and extracellular polysaccharide were predicted by artificial neural network. After that, the optimized medium was used for the submerged culture of ABM. Then, alcohol-induced liver injury in mice model was used to examine the protective effect of ABM cultured using the optimized medium on the liver. And the hepatic histopathological observations showed that ABM had a relatively significant role in mice model, which had alcoholic liver damage.

Optimization of L-asparaginase production by Serratia marcescens (NCIM 2919) under solid state fermentation using coconut oil cake

Background

The present study focused on utilization of agrowaste byproducts generated from oil mill for L-asparaginase enzyme production using Serratia marcescens under solid state fermentation. Classical and statistical methods were employed to optimize the process variables and the results were compared.

Results

The classical one factor at a time (OFAT) and response surface methodology (RSM) are employed to optimize the fermentation process. When used as the sole carbon source in SSF, coconut oil cake (COC) showed maximum enzyme production. The optimal values of substrate amount, initial moisture content, pH and temperature were found to be 6 g, 40%, 6 and 35°C respectively under classical optimization method with maximum enzyme activity of 3.87 (U gds-1). Maximum enzyme activity of 5.86 U gds-1 was obtained at the predicted optimal conditions of substrate amount 7.6 g of COC, initial moisture content of substrate 50%, temperature 35.5°C and pH 7.4. Validation results proved that a good relation existed between the experimental and the predicted model.

Conclusions

RSM optimization approach enhances the enzyme production to 33% when compared to classical method. Utilization of coconut oil cake as a low cost substrate in SSF for L-asparaginase production makes the process economical and also reduces the environmental pollution by converting the oil mill solid waste into a useful bioproduct.

Artificial intelligence techniques to optimize the EDC/NHS-mediated immobilization of cellulase on Eudragit L-100

Two artificial intelligence techniques, namely artificial neural network (ANN) and genetic algorithm (GA) were combined to be used as a tool for optimizing the covalent immobilization of cellulase on a smart polymer, Eudragit L-100. 1-Ethyl-3-(3-dimethyllaminopropyl) carbodiimide (EDC) concentration, N-hydroxysuccinimide (NHS) concentration and coupling time were taken as independent variables, and immobilization efficiency was taken as the response. The data of the central composite design were used to train ANN by back-propagation algorithm, and the result showed that the trained ANN fitted the data accurately (correlation coefficient R² = 0.99). Then a maximum immobilization efficiency of 88.76% was searched by genetic algorithm at a EDC concentration of 0.44%, NHS concentration of 0.37% and a coupling time of 2.22 h, where the experimental value was 87.97 ± 6.45%. The application of ANN based optimization by GA is quite successful.