An artificial intelligence approach to Bacillus amyloliquefaciens CCMI 1051 cultures: application to the production of anti-fungal compounds

Construction of a machine-learning model to predict the optimal gene expression level for efficient production of D-lactic acid in yeast

The modification of gene expression is being researched in the production of useful chemicals by metabolic engineering of the yeast Saccharomyces cerevisiae. When the expression levels of many metabolic enzyme genes are modified simultaneously, the expression ratio of these genes becomes diverse; the relationship between the gene expression ratio and chemical productivity remains unclear. In other words, it is challenging to predict phenotypes from genotypes. However, the productivity of useful chemicals can be improved if this relationship is clarified. In this study, we aimed to construct a machine-learning model that can be used to clarify the relationship between gene expression levels and D-lactic acid productivity and predict the optimal gene expression level for efficient D-lactic acid production in yeast. A machine-learning model was constructed using data on D-lactate dehydrogenase and glycolytic genes expression (13 dimensions) and D-lactic acid productivity. The coefficient of determination of the completed machine-learning model was 0.6932 when using the training data and 0.6628 when using the test data. Using the constructed machine-learning model, we predicted the optimal gene expression level for high D-lactic acid production. We successfully constructed a machine-learning model to predict both D-lactic acid productivity and the suitable gene expression ratio for the production of D-lactic acid. The technique established in this study could be key for predicting phenotypes from genotypes, a problem faced by recent metabolic engineering strategies.

Optimization of Bacillus amyloliquefaciens BLB369 Culture Medium by Response Surface Methodology for Low Cost Production of Antifungal Activity

Bacillus amyloliquefaciens BLB369 is an important plant growth-promoting bacterium, which produces antifungal compounds. A statistics-based experimental design was used to optimize a liquid culture medium using inexpensive substrates for increasing its antifungal activity. A Plackett–Burman design was first applied to elucidate medium components having significant effects on antifungal production. Then the steepest ascent method was employed to approach the experimental design space, followed by an application of central composite design. Three factors were retained (candy waste, peptone, and sodium chloride), and polynomial and original trigonometric models fitted the antifungal activity. The trigonometric model ensured a better fit. The contour and surface plots showed concentric increasing levels pointing out an optimized activity. Hence, the polynomial and trigonometric models showed a maximal antifungal activity of 251.9 (AU/mL) and 255.5 (AU/mL) for (19.17, 19.88, 3.75) (g/L) and (19.61, 20, 3.7) (g/L) of candy waste, peptone, and NaCl, respectively. This study provides a potential strategy for improving the fermentation of B. amyloliquefaciens BLB369 in low-cost media for large-scale industrial production.

A Data Mining Approach to Improve Inorganic Characterization of Amanita ponderosa Mushrooms

Amanita ponderosa are wild edible mushrooms that grow in some microclimates of Iberian Peninsula. Gastronomically this species is very relevant, due to not only the traditional consumption by the rural populations but also its commercial value in gourmet markets. Mineral characterisation of edible mushrooms is extremely important for certification and commercialization processes. In this study, we evaluate the inorganic composition of Amanita ponderosa fruiting bodies (Ca, K, Mg, Na, P, Ag, Al, Ba, Cd, Cr, Cu, Fe, Mn, Pb, and Zn) and their respective soil substrates from 24 different sampling sites of the southwest Iberian Peninsula (e.g., Alentejo, Andalusia, and Extremadura). Mineral composition revealed high content in macroelements, namely, potassium, phosphorus, and magnesium. Mushrooms showed presence of important trace elements and low contents of heavy metals within the limits of RDI. Bioconcentration was observed for some macro- and microelements, such as K, Cu, Zn, Mg, P, Ag, and Cd. A. ponderosa fruiting bodies showed different inorganic profiles according to their location and results pointed out that it is possible to generate an explanatory model of segmentation, performed with data based on the inorganic composition of mushrooms and soil mineral content, showing the possibility of relating these two types of data.

Fermentation factors influencing the production of bacteriocins by lactic acid bacteria: a review

Lactic acid bacteria (LAB) are the major interest in food industry primarily by virtue of their biopreservative properties.

The artificial neural network approach based on uniform design to optimize the fed-batch fermentation condition: application to the production of iturin A

Background

Iturin A is a potential lipopeptide antibiotic produced by Bacillus subtilis. Optimization of iturin A yield by adding various concentrations of asparagine (Asn), glutamic acid (Glu) and proline (Pro) during the fed-batch fermentation process was studied using an artificial neural network-genetic algorithm (ANN-GA) and uniform design (UD). Here, ANN-GA based on the UD data was used for the first time to analyze the fed-batch fermentation process. The ANN-GA and UD methodologies were compared based on their fitting ability, prediction and generalization capacity and sensitivity analysis.

Results

The ANN model based on the UD data performed well on minimal statistical designed experimental number and the optimum iturin A yield was 13364.5 ± 271.3 U/mL compared with a yield of 9929.0 ± 280.9 U/mL for the control (batch fermentation without adding the amino acids). The root-mean-square-error for the ANN model with the training set and test set was 4.84 and 273.58 respectively, which was more than two times better than that for the UD model (32.21 and 483.12). The correlation coefficient for the ANN model with training and test sets was 100% and 92.62%, respectively (compared with 99.86% and 78.58% for UD). The error% for ANN with the training and test sets was 0.093 and 2.19 respectively (compared with 0.26 and 4.15 for UD). The sensitivity analysis of both methods showed the comparable results. The predictive error of the optimal iturin A yield for ANN-GA and UD was 0.8% and 2.17%, respectively.

Conclusions

The satisfactory fitting and predicting accuracy of ANN indicated that ANN worked well with the UD data. Through ANN-GA, the iturin A yield was significantly increased by 34.6%. The fitness, prediction, and generalization capacities of the ANN model were better than those of the UD model. Further, although UD could get the insight information between variables directly, ANN was also demonstrated to be efficient in the sensitivity analysis. The results of these comparisons indicated that ANN could be a better alternative way for fermentation optimization with limited number of experiments.

Medium optimization of antifungal activity production by Bacillus amyloliquefaciens using statistical experimental design

In order to overproduce biofungicides agents by Bacillus amyloliquefaciens BLB371, a suitable culture medium was optimized using response surface methodology. Plackett-Burman design and central composite design were employed for experimental design and analysis of the results. Peptone, sucrose, and yeast extract were found to significantly influence antifungal activity production and their optimal concentrations were, respectively, 20 g/L, 25 g/L, and 4.5 g/L. The corresponding biofungicide production was 250 AU/mL, corresponding to 56% improvement in antifungal components production over a previously used medium (160 AU/mL). Moreover, our results indicated that a deficiency of the minerals CuSO(4), FeCl(3) · 6H(2)O, Na(2)MoO(4), KI, ZnSO(4) · 7H(2)O, H(3)BO(3), and C(6)H(8)O(7) in the optimized culture medium was not crucial for biofungicides production by Bacillus amyloliquefaciens BLB371, which is interesting from a practical point of view, particularly for low-cost production and use of the biofungicide for the control of agricultural fungal pests.

Modeling and optimization of poly(3hydroxybutyrate-co-3hydroxyvalerate) production from cane molasses by Azohydromonas lata MTCC 2311 in a stirred-tank reactor: effect of agitation and aeration regimes

The effects of agitation and aeration rates on copolymer poly(3-hydroxybutyrate-co-3-hydroxyvalerate) [P(3HB-co-3HV)] production by Azohydromonas lata MTCC 2311 using cane molasses supplemented with propionic acid in a bioreactor were investigated. The experiments were conducted in a three-level factorial design by varying the impeller (150–500 rev min−1) and aeration (0.5–1.5 vvm) rates. Further, the data were fitted to mathematical models [quadratic polynomial equation and artificial neural network (ANN)] and process variables were optimized by genetic algorithm-coupled models. ANN and hybrid ANN-GA were found superior for modeling and optimization of process variables, respectively. The maximum copolymer concentration of 7.45 g l−1 with 21.50 mol% of 3HV was predicted at process variables: agitation speed, 287 rev min−1; and aeration rate, 0.85 vvm, which upon validation gave 7.20 g l−1 of P(3HB-co-3HV) with 21 mol% of 3HV with the prediction error (%) of 3.38 and 2.32, respectively. Agitation speed established a relative high importance of 72.19% than of aeration rate (27.80%) for copolymer accumulation. The volumetric gas–liquid mass transfer coefficient (k  L  a) was strongly affected by agitation and aeration rates. The highest P(3HB-co-3HV) productivity of 0.163 g l−1 h−1 was achieved at 0.17 s−1 of k  L  a value. During the early phase of copolymer production process, 3HB monomers were accumulated, which were shifted to 3HV units (9–21%) during the cultivation period of 24–42 h. The enhancement of 7.5 and 34% were reported for P(3HB-co-3HV) production and 3HV content, respectively, by hybrid ANN-GA paradigm, which revealed the significant utilization of cane molasses for improved copolymer production.

Artificial intelligence based modeling and optimization of poly(3-hydroxybutyrate-co-3-hydroxyvalerate) production process by using Azohydromonas lata MTCC 2311 from cane molasses supplemented with volatile fatty acids: a genetic algorithm paradigm

The present work describes the optimization of medium variables for the production of poly(3-hydroxybutyrate-co-3-hydroxyvalerate) [P(3HB-co-3HV)] by Azohydromonas lata MTCC 2311 using cane molasses supplemented with propionic acid. Genetic algorithm (GA) has been used for the optimization of P(3HB-co-3HV) production through the simulation of artificial neural network (ANN) and response surface methodology (RSM). The predictions by ANN are better than those of RSM and in good agreement with experimental findings. The highest P(3HB-co-3HV) concentration and 3HV content have been reported as 7.35 g/l and 16.84 mol%, respectively by hybrid ANN-GA. Upon validation, 7.20 g/l and 16.30 mol% of P(3HB-co-3HV) concentration and 3HV content have been found in the shake flask, whereas 6.70 g/l and 16.35 mol%, have been observed in a 3 l bioreactor, respectively. The specific growth rate and P(3HB-co-3HV) accumulation rate of 0.29 per h and 0.16 g/lh determined with cane molasses are comparable to those observed on pure substrates.