Radial basis function neural networks for modeling growth rates of the basidiomycetes Physisporinus vitreus and Neolentinus lepideus

How temperature variation affects white-rot fungi mycelial growth dynamics: a nonlinear mixed models approach

This study aimed to model mycelial growth in a factorial experiment with two species of white rot fungi growing at five temperatures. The nonlinear models evaluated were logistic, Gompertz, Weibull and von Bertalanffy. The adjustments were performed first by evaluating the fixed and mixed-effects models with random effects, added to the fixed parameters. Then, the best adjusted model was improved by an adequated covariance structure, and dummy variables were added to the parameters asymptote (α) and abscissa of the inflection point (β) in the model in order to verify the effect of the experiment factors, species and temperatures on the regression parameters. The criteria used to compare models were residual variance and Akaike information criterion. Gompertz and von Bertalanffy mixed-effects models were better adjusted. The parameters differed between species. Moreover, the linear and quadratic effects of temperature evaluated in each species were significant. The models were reparametrized in order to consider two parameters of interest: velocity (μ) at the inflection point and lag time (λ). The maximum growth velocity was obtained at 25.4 °C by S. ostrea, while T. villosa was achieved at 30.5 °C; both fungi suffered less lag time by increasing the temperature.

Machine learning approach for predicting Fusarium culmorum and F. proliferatum growth and mycotoxin production in treatments with ethylene-vinyl alcohol copolymer films containing pure components of essential oils

Fusarium culmorum and F. proliferatum can grow and produce, respectively, zearalenone (ZEA) and fumonisins (FUM) in different points of the food chain. Application of antifungal chemicals to control these fungi and mycotoxins increases the risk of toxic residues in foods and feeds, and induces fungal resistances. In this study, a new and multidisciplinary approach based on the use of bioactive ethylene-vinyl alcohol copolymer (EVOH) films containing pure components of essential oils (EOCs) and machine learning (ML) methods is evaluated. Bioactive EVOH-EOC films were made incorporating cinnamaldehyde (CINHO), citral (CIT), isoeugenol (IEG) or linalool (LIN). Several ML methods (neural networks, random forests and extreme gradient boosted trees) and multiple linear regression (MLR) were applied and compared for modeling fungal growth and toxin production under different water activity (a_w) (0.96 and 0.99) and temperature (20 and 28 °C) regimes. The effective doses to reduce fungal growth rate (GR) by 50, 90 and 100% (ED₅₀, ED₉₀, and ED₁₀₀) of EOCs in EVOH films were in the ranges 200 to >3330, 450 to >3330, and 660 to >3330 μg/fungal culture (25 g of partly milled maize kernels in Petri dish), respectively, depending on the EOC, a_w and temperature. The type of EVOH-EOC film and EOC doses significantly affected GR in both species and ZEA and FUM production. Temperature also affected GR and a_w only affected GR and FUM production of F. proliferatum. EVOH-CIT was the most effective film against both species and ZEA and FUM production. Usually, when the EOC levels increased, GR and mycotoxin levels in the medium decreased although some treatments in combination with certain a_w and temperature values induced ZEA production. Random forest models predicted the GR of F. culmorum and F. proliferatum and ZEA and FUM production better than neural networks or extreme gradient boosted trees. The MLR mode provided the worst performance. This is the first approach on the ML potential in the study of the impact that bioactive EVOH films containing EOCs and environmental conditions have on F. culmorum and F. proliferatum growth and on ZEA and FUM production. The results suggest that these innovative packaging systems in combination with ML methods can be promising tools in the prediction and control of the risks associated with these toxigenic fungi and mycotoxins in food.

Laccase-Catalyzed Surface Modification of Thermo-Mechanical Pulp (TMP) for the Production of Wood Fiber Insulation Boards Using Industrial Process Water

Low-density wood fiber insulation boards are traditionally manufactured in a wet process using a closed water circuit (process water). The water of these industrial processes contains natural phenolic extractives, aside from small amounts of admixtures (e.g., binders and paraffin). The suitability of two fungal laccases and one bacterial laccase was determined by biochemical characterization considering stability and substrate spectra. In a series of laboratory scale experiments, the selected commercial laccase from Myceliophtora thermophila was used to catalyze the surface modification of thermo-mechanical pulp (TMP) using process water. The laccase catalyzed the covalent binding of the phenolic compounds of the process water onto the wood fiber surface and led to change of the surface chemistry directly via crosslinking of lignin moieties. Although a complete substitution of the binder was not accomplished by laccase, the combined use of laccase and latex significantly improved the mechanical strength properties of wood fiber boards. The enzymatically-treated TMP showed better interactions with the synthetic binder, as shown by FTIR-analysis. Moreover, the enzyme is extensively stable in the process water and the approach requires no fresh water as well as no cost-intensive mediator. By applying a second-order polynomial model in combination with the genetic algorithm (GA), the required amount of laccase and synthetic latex could be optimized enabling the reduction of the binder by 40%.

Penetration capacity of the wood-decay fungus Physisporinus vitreus

Purpose

Bioincising is a biotechnological process for improving the permeability of refractory wood such as Norway spruce heartwood using the wood-decay fungus Physisporinus vitreus. The degradation of the bordered pit membranes by P. vitreus in its first stage of wood colonization enhances the uptake of preservatives and wood modification substances, whereas the strength of the material is not significantly reduced.

Methods

We propose to study bioincising by means of a mathematical model, because many factors affect the growth and effects of P. vitreus in Norway spruce in such a complex way that an evaluation of the optimal incubation conditions (i.e. water activity, temperature or pH) is very expensive or even not possible solely using laboratory experiments.

Results

Using a hyphal growth model we demonstrate here for the first time how to optimize bioincising by linking the microscopic growth behavior of P. vitreus with macroscopic system properties of the wood. Moreover, we propose universal measures of wood-decay fungi, i.e., penetration velocity, penetration work and penetration capacity, which may figure as measures for the efficiency of wood colonization. For example, our simulation shows that an increase of the hyphal growth rate (i.e. changing the incubation conditions) from 1 to 2 μm·d-1 results in an increase of the mycelium’s growth velocity from 0.8 to 1.75 μm·d-1 and an increase of the penetration capacity from 0.5 to 0.6 10-3·mm2·d-1 using a pit degradation rate of 2 μm·d-1.

Conclusions

Information about the penetration velocity, penetration work and penetration capacity is of significance for both its biotechnological use and the study of the colonization strategy of wood-decay fungi in general.

Optimization of auto-induction medium for G-CSF production by Escherichia coli using artificial neural networks coupled with genetic algorithm

Granulocyte colony-stimulating factor (G-CSF) is a cytokine widely used in cancer patients receiving high doses of chemotherapeutic drugs to prevent the chemotherapy-induced suppression of white blood cells. The production of recombinant G-CSF should be increased to meet the increasing market demand. This study aims to model and optimize the carbon source of auto-induction medium to enhance G-CSF production using artificial neural networks coupled with genetic algorithm. In this approach, artificial neural networks served as bioprocess modeling tools, and genetic algorithm (GA) was applied to optimize the established artificial neural network models. Two artificial neural network models were constructed: the back-propagation (BP) network and the radial basis function (RBF) network. The root mean square error, coefficient of determination, and standard error of prediction of the BP model were 0.0375, 0.959, and 8.49 %, respectively, whereas those of the RBF model were 0.0257, 0.980, and 5.82 %, respectively. These values indicated that the RBF model possessed higher fitness and prediction accuracy than the BP model. Under the optimized auto-induction medium, the predicted maximum G-CSF yield by the BP-GA approach was 71.66 %, whereas that by the RBF-GA approach was 75.17 %. These predicted values are in agreement with the experimental results, with 72.4 and 76.014 % for the BP-GA and RBF-GA models, respectively. These results suggest that RBF-GA is superior to BP-GA. The developed approach in this study may be helpful in modeling and optimizing other multivariable, non-linear, and time-variant bioprocesses.

The use of a radial basis neural network and genetic algorithm for improving the efficiency of laccase-mediated dye decolourization

A radial basis function neural network (RBF) and genetic algorithm (GA) were applied to improve the efficiency of the oxidative decolourization of the recalcitrant dye Reactive Black 5 (RB 5) by a technical laccase (Trametes spp.) and the natural mediator acetosyringone (ACS). The decolourization of RB 5 in aqueous solution was studied with a 3(4) factorial design including different levels of laccase (2, 100, 200 U L(-1)), acetosyringone (5, 50, 100 μM), pH value (3, 4.5, 6) and incubation time (10, 20, 30 min). The generated RBF network was mathematically evaluated by several statistical indices and revealed better results than a classical quadratic response surface (RS) model. The experimental data showed that within 10 min of incubation time a complete decolourization (>90%) was achieved by using the highest amount of laccase (200 U L(-1)) and acetosyringone (100 μM) at pH 6. By applying the RBF-GA methodology, the efficiency of the laccase-mediated decolourization was improved by minimising the required amount of laccase and acetosyringone by 25% and 21.7% respectively. Complete decolourization (>90%) was obtained within 10 min at the GA-optimised process conditions of laccase (150 U L(-1)) and acetosyringone (78.3 μM) at pH 5.67. These results illustrate that the RBF-GA methodology could be a powerful technique during scale-up studies.

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.

Modelling the effect of environmental factors on the hyphal growth of the basidiomycete Physisporinus vitreus

The present work investigated the effects of environmental factors on the growth of fungal colonies of the white-rot basidiomycetes Physisporinus vitreus using a lattice-free discrete modeling approach called the fungal growth model (FGM), in which hyphae and nutrients are considered as discrete structures. A discrete modeling approach enables the underlying mechanistic rule concerning the basic architecture and dynamics of fungal networks to be studied on the scale of a single colony. By comparing simulations of the FGM with laboratory experiments of fungal colonies growing on malt extract agar we show that the combined effects of water activity, temperature and pH on the radial growth rate of fungal mycelia on the macroscopic scale may be explained by a power law for the costs of hyphal maintenance and expansion on the microscopic scale. Information about the response of the fungal mycelium at the micro- scopic level to environmental conditions is essential for simulating its behavior in complex structure substrates such as wood, where the effect of the fungus on the wood (i.e. the degradation of the cell wall) changes the local environmental condition (e.g. the permeability of the substrate and therefore the water activity in a colonized wood cell lumen). Using a combination of diffusion and moisture processes with the FGM may increase our understanding of the colonization strategy of P. vitreus and help to optimize its growth behavior for biotechnological applications such as bioincising.

Evaluation of the interspecific competitive ability of the bioincising fungus Physisporinus vitreus

A hierarchical set of assays were used to evaluate the interspecific competitive ability of the bioincising fungus Physiporinus vitreus (response species). The competitiveness and growth mode of P. vitreus against a range of blue stain fungi and Trichoderma species (challenge species) was investigated in dual culture tests (a) and a spatially heterogeneous system of tessellation agar (b) on different media. In addition, the robustness of the bioincising process against biotic influences was determined by controlled interaction tests with different inocula of the challenge species (colony-forming units: 10(2), 10(4), 10(6) ml(-1)) on Norway spruce (Picea abies Karst.) heartwood. The results of the dual culture and tessellation agar tests revealed a significant (P ≤ 0.001) antagonistic potential (lethal effect) of the T. atroviride strain (15603.1), whereas no or only a slight effect of the blue stain fungi on P. vitreus was detectable. The interaction tests on Norway spruce heartwood confirmed that an increase in inoculum size of the challenge fungi correlated with an increased negative effect (Spearman's rho coefficient (ρ) = -0.521). Among the challenge species, T-15603.1 revealed the most negative effect on the homogeneous development of P. vitreus on wood and thus on the outcome of the bioincising process. To improve the uniformity of colonization and to reduce the rate of contamination, the incubation of wood in a sealed system (bioreactor) after sterilization is suggested.