Applications of neural networks to recovery of biological products

Lentinula edodes substrate formulation using multilayer perceptron-genetic algorithm: a critical production checkpoint

Shiitake (Lentinula edodes) is one of the most widely grown and consumed mushroom species worldwide. They are a potential source of food and medicine because they are rich in nutrients and contain various minerals, vitamins, essential macro- and micronutrients, and bioactive compounds. The reuse of agricultural and industrial residues is crucial from an ecological and economic perspective. In this study, the running length (RL) of L. edodes cultured on 64 substrate compositions obtained from different ratios of bagasse (B), wheat bran (WB), and beech sawdust (BS) was recorded at intervals of 5 days after cultivation until the 40th day. Multilayer perceptron-genetic algorithm (MLP-GA), multiple linear regression, stepwise regression, principal component regression, ordinary least squares regression, and partial least squares regression were used to predict and optimize the RL and running rate (RR) of L. edodes. The statistical values showed higher prediction accuracies of the MLP-GA models (92% and 97%, respectively) compared with those of the regression models (52% and 71%, respectively) for RL and RR. The high degree of fit between the forecasted and actual values of the RL and RR of L. edodes confirmed the superior performance of the developed MLP-GA models. An optimization analysis on the established MLP-GA models showed that a substrate containing 15.1% B, 45.1% WB, and 10.16% BS and a running time of 28 days and 10 h could result in the maximum L. edodes RL (10.69 cm). Moreover, the highest RR of L. edodes (0.44 cm d-1) could be obtained by a substrate containing 30.7% B, 90.4% WB, and 0.0% BS. MLP-GA was observed to be an effective method for predicting and consequently selecting the best substrate composition for the maximal RL and RR of L. edodes.

Using Mathematical Optimization Models to Improve the Efficiency of Duckweeds (Wolffia arrhiza and Lemna minor) Micropropagation

The method of plant micropropagation is widely used to obtain genetically homogeneous and infection-free plants for the needs of various industries and agriculture. Optimization of plant growth and development conditions plays a key role in economically successful micropropagation. Computer technologies have provided researchers with new approaches for modeling and a better understanding of the role of the factors involved in plant growth in vitro. To develop new models for optimizing growth conditions, we used plants with a high speed of vegetative in vitro reproduction, such as duckweed (Wolffia arrhiza and Lemna minor). Using the development of the optimal modeling of the biological processes, we have obtained the prescriptions for an individually balanced culture medium that enabled us to obtain 1.5-2.0 times more duckweed biomass with a 1.5 times higher protein concentration in the dry mass. Thus, we have demonstrated that the method of optimization modeling of the biological processes based on solving multinomial tasks from the series of quadratic equations can be used for the optimization of trophic needs of plants, specifically for micropropagation of duckweeds in vitro.

Current trends in chromatographic prediction using artificial intelligence and machine learning

Artificial intelligence (AI) and machine learning (ML) gained tremendous growth and are rapidly becoming popular in various fields of prediction due to their potential abilities, accuracy, and speed. Machine learning algorithms employ historical data to analyze or predict information using patterns or trends. AI and ML were most employed in chromatographic predictions and particularly attractive options for liquid chromatography method development, as they can help achieve desired results faster, more accurately, and more efficiently. This review aims at exploring various AI and ML models employed in the determination of chromatographic characteristics. This review also aims to provide deep insight into reported artificial neural network (ANN) associated techniques which maintained better accuracy and significant possibilities for chromatographic characteristics prediction in liquid chromatography over classical linear models and also emphasizes the integration of a fuzzy system with an ANN, as this integrated study provides more efficient and accurate methods in chromatographic prediction than other linear models. This study also focuses on the retention prediction of a target molecule employing QSRR methodology combined with an ANN, highlighting a more effective technique than the QSRR alone. This approach showed the benefits of combining AI or ML algorithms with the QSRR to obtain more accurate retention predictions, emphasizing the potential of artificial intelligence and machine learning for overcoming adversities in analytical chemistry.

Hybrid Models for the simulation and prediction of chromatographic processes for protein capture

The biopharmaceutical industries are continuously faced with the pressure to reduce the development costs and accelerate development time scales. The traditional approach of heuristic-based or platform process-based optimization is soon getting obsolete, and more generalized tools for process development and optimization are required to keep pace with the emerging trends. Thus, advanced model-based methods that can reduce the can ensure accelerated development of robust processes with minimal experiments are necessary. Though mechanistic models for chromatography are quite popular, their success is limited by the need to have accurate knowledge of adsorption isotherms and mass transfer kinetics. As an alternative, in this work, a hybrid modeling approach is proposed. Thereby, the chromatographic unit behavior is learned by a combination of neural network and mechanistic model while fitting suitable experimental breakthrough curves. Since this approach does not require identifying suitable mechanistic assumptions for all the phenomena, it can be developed with lower effort. Thus, allowing the scientists to concentrate their focus on process development. The performance of the hybrid model is compared with the mechanistic Lumped kinetic Model for in-silico data and experiments conducted on a system of industrial relevance. The flexibility of the hybrid modeling approach results in about three times higher accuracies compared to Lumped Kinetic Model. This is validated for five different isotherm models used to simulate data, with the hybrid model showing about two to three times lower prediction errors in all the cases. Not only in prediction, but we could also show that the hybrid model is more robust in extrapolating across process conditions with about three times lower error than the LKM. Additionally, it could be demonstrated that an appropriately tailored formulation of the hybrid model can be used to generate representations for the underlying principles such as adsorption equilibria and mass transfer kinetics.

A hybrid model based on general regression neural network and fruit fly optimization algorithm for forecasting and optimizing paclitaxel biosynthesis in Corylus avellana cell culture

BACKGROUND

Paclitaxel is a well-known chemotherapeutic agent widely applied as a therapy for various types of cancers. In vitro culture of Corylus avellana has been named as a promising and low-cost strategy for paclitaxel production. Fungal elicitors have been reported as an impressive strategy for improving paclitaxel biosynthesis in cell suspension culture (CSC) of C. avellana. The objectives of this research were to forecast and optimize growth and paclitaxel biosynthesis based on four input variables including cell extract (CE) and culture filtrate (CF) concentration levels, elicitor adding day and CSC harvesting time in C. avellana cell culture, as a case study, using general regression neural network-fruit fly optimization algorithm (GRNN-FOA) via data mining approach for the first time.

RESULTS

GRNN-FOA models (0.88-0.97) showed the superior prediction performances as compared to regression models (0.57-0.86). Comparative analysis of multilayer perceptron-genetic algorithm (MLP-GA) and GRNN-FOA showed very slight difference between two models for dry weight (DW), intracellular and extracellular paclitaxel in testing subset, the unseen data. However, MLP-GA was slightly more accurate as compared to GRNN-FOA for total paclitaxel and extracellular paclitaxel portion in testing subset. The slight difference was observed in maximum growth and paclitaxel biosynthesis optimized by FOA and GA. The optimization analysis using FOA on developed GRNN-FOA models showed that optimal CE [4.29% (v/v)] and CF [5.38% (v/v)] concentration levels, elicitor adding day (17) and harvesting time (88 h and 19 min) can lead to highest paclitaxel biosynthesis (372.89 µg l^-1).

CONCLUSIONS

Great accordance between the predicted and observed values of DW, intracellular, extracellular and total yield of paclitaxel, and also extracellular paclitaxel portion support excellent performance of developed GRNN-FOA models. Overall, GRNN-FOA as new mathematical tool may pave the way for forecasting and optimizing secondary metabolite production in plant in vitro culture.

Modeling of paclitaxel biosynthesis elicitation in Corylus avellana cell culture using adaptive neuro-fuzzy inference system-genetic algorithm (ANFIS-GA) and multiple regression methods

Paclitaxel as a microtubule-stabilizing agent is widely used for the treatment of a vast range of cancers. Corylus avellana cell suspension culture (CSC) is a promising strategy for paclitaxel production. Elicitation of paclitaxel biosynthesis pathway is a key approach for improving its production in cell culture. However, optimization of this process is time-consuming and costly. Modeling of paclitaxel elicitation process can be helpful to predict the optimal condition for its high production in cell culture. The objective of this study was modeling and forecasting paclitaxel biosynthesis in C. avellana cell culture responding cell extract (CE), culture filtrate (CF) and cell wall (CW) derived from endophytic fungus, either individually or combined treatment with methyl-β-cyclodextrin (MBCD), based on four input variables including concentration levels of fungal elicitors and MBCD, elicitor adding day and CSC harvesting time, using adaptive neuro-fuzzy inference system (ANFIS) and multiple regression methods. The results displayed a higher accuracy of ANFIS models (0.94-0.97) as compared to regression models (0.16-0.54). The great accordance between the predicted and observed values of paclitaxel biosynthesis for both training and testing subsets support excellent performance of developed ANFIS models. Optimization process of developed ANFIS models with genetic algorithm (GA) showed that optimal MBCD (47.65 mM) and CW (2.77% (v/v)) concentration levels, elicitor adding day (16) and CSC harvesting time (139 h and 41 min after elicitation) can lead to highest paclitaxel biosynthesis (427.92 μg l-1). The validation experiment showed that ANFIS-GA method can be a promising tool for selecting the optimal conditions for maximum paclitaxel biosynthesis, as a case study.

Mathematical Modeling of Growth and Paclitaxel Biosynthesis in Corylus avellana Cell Culture Responding to Fungal Elicitors Using Multilayer Perceptron-Genetic Algorithm

Paclitaxel is the top-selling anticancer medicine in the world. In vitro culture of Corylus avellana has been made known as a promising and inexpensive strategy for producing paclitaxel. Fungal elicitors have been named as the most efficient strategy for enhancing the biosynthesis of secondary metabolites in plant cell culture. In this study, endophytic fungal strain HEF₁₇ was isolated from C. avellana and identified as Camarosporomyces flavigenus. C. avellana cell suspension culture (CSC) elicited with cell extract (CE) and culture filtrate (CF) derived from strain HEF₁₇, either individually or combined treatment, in mid and late log phase was processed for modeling and optimizing growth and paclitaxel biosynthesis regarding CE and CF concentration levels, elicitor adding day, and CSC harvesting time using multilayer perceptron-genetic algorithm (MLP-GA). The results displayed higher accuracy of MLP-GA models (0.89-0.95) than regression models (0.56-0.85). The great accordance between the predicted and observed values of output variables (dry weight, intracellular, extracellular and total yield of paclitaxel, and also extracellular paclitaxel portion) for both training and testing subsets supported the excellent performance of developed MLP-GA models. MLP-GA method presented a promising tool for selecting the optimal conditions for maximum paclitaxel biosynthesis. An Excel^® estimator, HCC-paclitaxel, was designed based on MLP-GA model as an easy-to-use tool for predicting paclitaxel biosynthesis in C. avellana CSC responding to fungal elicitors.

Artificial neural network-based model for the prediction of optimal growth and culture conditions for maximum biomass accumulation in multiple shoot cultures of Centella asiatica

An artificial neural network (ANN)-based modelling approach is used to determine the synergistic effect of five major components of growth medium (Mg, Cu, Zn, nitrate and sucrose) on improved in vitro biomass yield in multiple shoot cultures of Centella asiatica. The back propagation neural network (BPNN) was employed to predict optimal biomass accumulation in terms of growth index over a defined culture duration of 35 days. The four variable concentrations of five media components, i.e. MgSO₄ (0, 0.75, 1.5, 3.0 mM), ZnSO₄ (0, 15, 30, 60 μM), CuSO₄ (0, 0.05, 0.1, 0.2 μM), NO₃ (20, 30, 40, 60 mM) and sucrose (1, 3, 5, 7 %, w/v) were taken as inputs for the ANN model. The designed model was evaluated by performing three different sets of validation experiments that indicated a greater similarity between the target and predicted dataset. The results of the modelling experiment suggested that 1.5 mM Mg, 30 μM Zn, 0.1 μM Cu, 40 mM NO₃ and 6 % (w/v) sucrose were the respective optimal concentrations of the tested medium components for achieving maximum growth index of 1654.46 with high centelloside yield (62.37 mg DW/culture) in the cultured multiple shoots. This study can facilitate the generation of higher biomass of uniform, clean, good quality C. asiatica herb that can efficiently be utilized by pharmaceutical industries.

Predicting In vitro Culture Medium Macro-Nutrients Composition for Pear Rootstocks Using Regression Analysis and Neural Network Models

Two modeling techniques [artificial neural network-genetic algorithm (ANN-GA) and stepwise regression analysis] were used to predict the effect of medium macro-nutrients on in vitro performance of pear rootstocks (OHF and Pyrodwarf). The ANN-GA described associations between investigating eight macronutrients (NO[Formula: see text], NH[Formula: see text], Ca(2+), K(+), Mg(2+), PO[Formula: see text], SO[Formula: see text], and Cl(-)) and explant growth parameters [proliferation rate (PR), shoot length (SL), shoot tip necrosis (STN), chlorosis (Chl), and vitrification (Vitri)]. ANN-GA revealed a substantially higher accuracy of prediction than for regression models. According to the ANN-GA results, among the input variables concentrations (mM), NH[Formula: see text] (301.7), and NO[Formula: see text], NH[Formula: see text] (64), SO[Formula: see text] (54.1), K(+) (40.4), and NO[Formula: see text] (35.1) in OHF and Ca(2+) (23.7), NH[Formula: see text] (10.7), NO[Formula: see text] (9.1), NH[Formula: see text] (317.6), and NH[Formula: see text] (79.6) in Pyrodwarf had the highest values of VSR in data set, respectively, for PR, SL, STN, Chl, and Vitri. The ANN-GA showed that media containing (mM) 62.5 NO[Formula: see text], 5.7 NH[Formula: see text], 2.7 Ca(2+), 31.5 K(+), 3.3 Mg(2+), 2.6 PO[Formula: see text], 5.6 SO[Formula: see text], and 3.5 Cl(-) could lead to optimal PR for OHF and optimal PR for Pyrodwarf may be obtained with media containing 25.6 NO[Formula: see text], 13.1 NH[Formula: see text], 5.5 Ca(2+), 35.7 K(+), 1.5 Mg(2+), 2.1 PO[Formula: see text], 3.6 SO[Formula: see text], and 3 Cl(-).

Time-dependent fermentation control strategies for enhancing synthesis of marine bacteriocin 1701 using artificial neural network and genetic algorithm

The artificial neural network (ANN) and genetic algorithm (GA) were combined to optimize the fermentation process for enhancing production of marine bacteriocin 1701 in a 5-L-stirred-tank. Fermentation time, pH value, dissolved oxygen level, temperature and turbidity were used to construct a "5-10-1" ANN topology to identify the nonlinear relationship between fermentation parameters and the antibiotic effects (shown as in inhibition diameters) of bacteriocin 1701. The predicted values by the trained ANN model were coincided with the observed ones (the coefficient of R(2) was greater than 0.95). As the fermentation time was brought in as one of the ANN input nodes, fermentation parameters could be optimized by stages through GA, and an optimal fermentation process control trajectory was created. The production of marine bacteriocin 1701 was significantly improved by 26% under the guidance of fermentation control trajectory that was optimized by using of combined ANN-GA method.

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 K2HPO4 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 (R2) 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) K2HPO4. 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.

Improvement of trypanocidal metabolites production by Aspergillus fumigatus using neural networks

An optimization procedure using artificial neural networks was developed to determine the optimal combination of parameters, such as medium culture, initial pH, temperature and time of fermentation for maximal trypanocidal metabolites production by Aspergillus fumigatus. A data set of 81 experiments was carried out and an artificial neural network was trained to identify the optimal conditions for this process. Good correlation was obtained between the experimental and predicted values of lysis of the trypomastigote forms of Trypanosoma cruzi (r2 = 0.9990). The simulations of fermentation performance were undertaken on combinations of input variables and the highest level of activity against T. cruzi was obtained from the chloroform extract of the modified Jackson medium culture, initial pH of 6.0, incubated at 40 degrees C for 144 h. It displayed lysis of 95% of the trypomastigote forms of T. cruzi and the red blood cells remained normal.

Modelling of glucoamylase thermal inactivation in the presence of starch by artificial neural network

Thermal inactivation is suspected to be a limiting factor for use of glucoamylase in starch saccharification at elevated temperatures. Thus, inactivation of the enzyme has been studied in the presence of reagents (enzyme, substrate and product in wide range of concentrations, and moderate stirring). The influence of substrate and glucose as stability modulators showed the complexity of the studied system. Hence, one might expect multilateral correlations that could depreciate some efforts for phenomenological modelling. These obstacles forced to apply artificial neural network (ANN) modelling to map the enzyme activity decays. For this purpose, a dynamic network with four hidden neurons was selected. The database containing 42 data vectors was used for neural model training and verification process. The standard error of calculations and correlation coefficient (0.997-0.999) for dynamic simulations has proved correctness of the developed ANN.