Jul 2026· Journal of Bioscience and Bioengineering· Vol 142, pp. 332-341· 0 citations· 50 references
Medicine
TL;DR
A strategy combining single-factor experiments and an ANN machine learning model was used to enhance the production of 1-DNJ by Bacillus amyloliquefaciens using a combination of single-factor experiments and artificial neural network (ANN) models.
Abstract
The iminosugar 1-deoxynojirimycin (1-DNJ) is a pharmaceutically significant natural alkaloid with expanding therapeutic and nutraceutical applications. Its microbial biosynthesis offers a sustainable and scalable alternative to plant extraction. However, process optimization is constrained by the complex, non-linear interactions between nutritional and physicochemical fermentation parameters. Herein, the study aimed to enhance the production of 1-DNJ by Bacillus amyloliquefaciens using a combination of single-factor experiments and artificial neural network (ANN) models. LC-MS/MS analysis confirmed the strain produced 1-DNJ from soluble starch and peptone. A strategy combining single-factor experiments and an ANN machine learning model was then used to enhance 1-DNJ yield. The culture medium obtained through single-factor optimisation had α-glucosidase inhibitory activity of 82.55% and a 1-DNJ titer of 1064 ± 4.64 mg/L. A computationally efficient ANN, constructed with a weighted resilient backpropagation algorithm (rprop+) and six hidden neurons, was then trained on this limited dataset. The model identified refined fermentation conditions, predicting a further increase to 87.47% inhibition and a titer of 1179 ± 8.44 mg/L. Sensitivity analysis of the validated ANN pinpointed inoculum volume and fermentation temperature as the most critical process variables. This machine learning framework is a viable technical approach for optimising 1-DNJ fermentation. The identified key fermentation parameters lay a solid foundation for subsequent research.
The fermentation behaviour of Lactobacillus delbrueckii subsp. bulgaricus, Streptococcus thermophilus, and Lactobacillus acidophilus during synbiotic yogurt production enriched with freeze-dried banana powder was investigated in this study with the aim of characterizing microbial interactions, optimizing growth conditions, and developing a machine learning-based tool to predict the fermentation process. Fermentation experiments were performed under controlled temperature (40–43 °C), and prebiotic concentrations (0–30 g·l-1). Machine learning algorithms, including decision tree regression (DTR), random forests (RF), and Gaussian process regression (GPR), were then employed to predict bacterial growth behaviour and identify optimal fermentation conditions. GPR provided an adjusted coefficient of determination (R2adj) value greater than 0.82 for each bacterial strain, making GPR the best machine learning model. Therefore, it was integrated into the software to create a virtual simulation environment capable of representing fermentation dynamics. Based on modelling, the optimum fermentation conditions were determined as 41.5 °C and 20 g·l-1 freeze-dried banana powder concentration. Overall, the findings demonstrate that banana powder boosts probiotic growth, and machine learning enables efficient optimization and monitoring of the synbiotic yogurt fermentation process.
Melissa Şahin, B. Ergüden, Fatih Tarlak· Journal of Food and Nutritio...· 0 citations
Esterases play an important role in flavor regulation during food fermentation. In this study, a high esterase-producing strain, Monascus purpureus Y146, was used to optimize esterase production via one-factor-at-a-time experiments (OFAT), response surface methodology (RSM), and an artificial neural network with genetic algorithm (ANN-GA) approach. The esterase was partially purified and characterized, and its application in rice wine fermentation was evaluated using HS-SPME-GC-MS. The results showed that the esterase activity of the Y146 strain reached up to 1248.02 U/mL, a 4.68-fold increase over the unoptimized condition, under conditions of 16% seed inoculation, 10 g/L L-arginine addition at 84 h, pH 7, and 8.69 d of fermentation. The partially purified esterase preparation exhibited optimal activity at 30 °C and pH 7, showed enhanced activity in the presence of 2 mM Fe2+, and had an approximate half-life of 9 h. HS-SPME-GC-MS analysis identified ethyl caprate as the only aroma-active compound (OAV > 1) detected in the control group. Following addition of the partially purified esterase preparation, increased diversity and abundance of volatile compounds were observed, with the number of aroma-active compounds increasing from one to six, including ethyl undecanoate, ethyl hexanoate, ethyl palmitate, ethyl linoleate, 1-dodecanol, and 2,4-Di-tert-butylphenol. These findings highlight the potential application of the M. purpureus Y146-derived partially purified esterase preparation in flavor-oriented fermented food systems.
ABSTRACT Candida albicans is a common opportunistic pathogenic fungus capable of causing severe infections when host immunity is compromised or when the normal microbial flora is disrupted. The widespread use of antifungal agents has led to the increasing emergence of drug resistance, underscoring the urgent need for novel antifungal strategies. Bacillus altitudinis AS19 has been found to produce a substance with specific antimicrobial activity against C. albicans under iron-deficient conditions. In this study, the fermentation medium and culture conditions for siderophore production by AS19 were optimized using response surface methodology (RSM) and an artificial neural network-genetic algorithm (ANN-GA) model. The ANN-GA model demonstrated superior optimization performance compared with RSM. The optimal conditions were pH 6.363, sucrose 29.730 g/L, and KH2PO4 0.185 g/L, under which the yield increased more than twofold compared with the pre-optimization level of 26.53%. To further investigate the antimicrobial mechanism, molecular docking and dynamics simulations were employed to virtually screen siderophores with anti-C. albicans activity and identify their potential targets. Among the candidates, Nocardamin Glucuronide was prioritized as the top hit, and the presence of desferrioxamine-type siderophores produced by AS19 was subsequently confirmed by LC-MS, validating the in silico predictions. In addition, in vitro assays were performed to determine the minimum inhibitory concentration, minimum fungicidal concentration, and time-kill kinetics of the crude siderophore extract. The time-kill curve clearly demonstrated its potent antimicrobial activity against C. albicans. Overall, this study provides both a theoretical basis and experimental evidence for the development of novel siderophore-based antimicrobial agents targeting C. albicans. IMPORTANCE Candida albicans is a common opportunistic fungal pathogen responsible for severe infections in immunocompromised individuals, while increasing antifungal resistance has reduced the effectiveness of current treatments. In this study, a natural compound with specific anti-C. albicans activity produced by Bacillus altitudinis AS19 under iron-deficient conditions was investigated. Artificial intelligence-based models were used to optimize fermentation conditions, significantly improving production efficiency. Molecular simulations were performed to explore the potential antimicrobial mechanism, and in vitro assays confirmed its antifungal activity. These results provide a basis for developing novel antifungal agents targeting C. albicans. Candida albicans is a common opportunistic fungal pathogen responsible for severe infections in immunocompromised individuals, while increasing antifungal resistance has reduced the effectiveness of current treatments. In this study, a natural compound with specific anti-C. albicans activity produced by Bacillus altitudinis AS19 under iron-deficient conditions was investigated. Artificial intelligence-based models were used to optimize fermentation conditions, significantly improving production efficiency. Molecular simulations were performed to explore the potential antimicrobial mechanism, and in vitro assays confirmed its antifungal activity. These results provide a basis for developing novel antifungal agents targeting C. albicans.
Chenjian Li, Zexin Gao, Hong-Hai Ke et al.· Applied and Environmental Mi...· 0 citations
Dalbavancin is a potent next-generation lipoglycopeptide antibiotic, but the biosynthesis of its essential precursor, A40926B0, is severely hindered in its native producer Nonomuraea gerenzanensis. Complex competing metabolic pathways and strict transcriptional repression in this strain lead to critical industrial bottlenecks, including extreme product heterogeneity and notoriously low yields. To address these challenges, this study presents a systematic strategy to construct a high-producing strain and optimize the fermentation process for A40926B0. First, random mutagenesis of the strain N. gerenzanensis IPB-9 was performed using a 10 MeV high-energy electron linear accelerator. Screening identified mutant M0318, achieving a 43.6% increase in A40926B0 titer (808.8 mg/L). Concurrently, RNA-Seq analysis of N. gerenzanensis L70 was processed and seven endogenous strong promoters were quantitatively characterized and validated by using an eGFP reporter system and RT-qPCR to expand the genetic toolbox. Applying this toolkit, the strongest identified promoter (orf1597*p) was engineered to overexpress dbv3, the core pathway-specific positive regulator, in the M0318 chassis. This rational intervention further boosted A40926B0 production to 1.03 g/L. Furthermore, a comprehensive bioprocess optimization was executed. Following single-factor evaluations of shake-flask parameters, a Box-Behnken design (BBD)-based response surface methodology (RSM) was employed for systematic medium formulation, successfully elevating the titer to 1.41 g/L. Finally, this optimized process was successfully scaled to a 15 L bioreactor and the final A40926B0 titer reached 2.27 g/L, representing a 303.2% increase over the initial process, laying a foundation for the industrial-scale production of A40926B0.
Xue-yan Liu, Yan-qiu Liu, Yi-Lei Zheng et al.· Synthetic and Systems Biotec...· 0 citations
This study aimed to optimize the enzyme-assisted extraction of juice from soursop (Annona muricata) using α-amylase to improve juice yield and quality. Soursop is rich in bioactive compounds and has significant market potential, but conventional extraction methods often result in limited yield and suboptimal quality. Enzymatic extraction was explored as a solution, using Response Surface Methodology with a Box-Behnken Design to optimize three processing variables: α-amylase concentration (0–1.25%), incubation temperature (40–60 °C), and incubation time (30–240 minutes). Samples with 1:1 (w/w) pulp-to-water ratio were subjected to the different combinations of processing variables. A reduced quadratic model (R² = 0.99) significantly explained the variations in juice yield. The optimized conditions, with the use of 0.41% α-amylase incubated at 51.99 °C for 63.53 minutes, resulted in a maximum yield of 80.04%. Despite enzymatic and thermal treatment, antioxidant activity (DPPH, FRAP, ABTS) was effectively retained, and total phenolic content increased significantly. HPLC analysis confirmed elevated levels of individual phenolic compounds and detected resveratrol (0.27 mg/100 mL) in the optimized juice. The optimized extract also exhibited higher total soluble solids, increased titratable acidity, and noticeable color changes. These findings demonstrate the effectiveness of α-amylase treatment in enhancing juice extractability and bioactive compound retention, offering promising implications for functional beverage development.
Jan Irish H. Estanislao, Anna Rina B. Evangelista-Albacea, M. Ilano et al.· Natural and Life Sciences Co...· 0 citations
Lactococcus lactis SH6 was engineered for heterologous heparosan production, and its growth medium was optimized using a combination of experimental design and machine learning (ML). One-factor-at-a-time shake flask experiments revealed glucose (10 g/L) and yeast extract (17.5 g/L) as the best substrates, producing 50 mg/L heparosan. Plackett-Burman analysis and steepest ascent optimization revealed significant factors, and a central composite design (CCD) optimized nutrient concentrations, predicting 85 mg/L heparosan (validated at 81 mg/L). ML-Gaussian process regression was applied after CCD optimization to fine-tune and cross-check the optimal medium (glucose 8.94 g/L, yeast extract 22.89 g/L, ascorbate 0.38 g/L, β-glycerophosphate 28.2 g/L), producing 85.28 mg/L heparosan (predicted 88.8 mg/L) at the flask scale. Earlier nisin induction (2 h) at the bioreactor scale increased heparosan titers to 119.7 mg/L, and linear glucose feeding (1.5 g/L.h) extended the production phase to 133 mg/L. Medium optimization resulted in nearly doubling heparosan yield compared to the unoptimized medium, setting a new standard for L. lactis. This work offers a design-of-experiments-ML solution as a viable approach to designing high-yielding, animal-product-free heparosan production methods in a Generally Regarded as Safe (GRAS) microbe.
Siddharth Guhan, Thilakraj S, S. Sivaprakasam et al.· Preparative Biochemistry & B...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
