Analysis of the tendency for the electronic conductivity to change during alcoholic fermentation

Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges

Machine learning (ML), particularly deep learning (DL), has made rapid and substantial progress in synthetic biology in recent years. Biotechnological applications of biosystems, including pathways, enzymes, and whole cells, are being probed frequently with time. The intricacy and interconnectedness of biosystems make it challenging to design them with the desired properties. ML and DL have a synergy with synthetic biology. Synthetic biology can be employed to produce large data sets for training models (for instance, by utilizing DNA synthesis), and ML/DL models can be employed to inform design (for example, by generating new parts or advising unrivaled experiments to perform). This potential has recently been brought to light by research at the intersection of engineering biology and ML/DL through achievements like the design of novel biological components, best experimental design, automated analysis of microscopy data, protein structure prediction, and biomolecular implementations of ANNs (Artificial Neural Networks). I have divided this review into three sections. In the first section, I describe predictive potential and basics of ML along with myriad applications in synthetic biology, especially in engineering cells, activity of proteins, and metabolic pathways. In the second section, I describe fundamental DL architectures and their applications in synthetic biology. Finally, I describe different challenges causing hurdles in the progress of ML/DL and synthetic biology along with their solutions.

Valorisation of fresh waste grape through fermentation with different exogenous probiotic inoculants

The disposal of fresh waste grape berries restraining the sustainable development of vineyards. The aims of this study were to evaluate the effects of different exogenous probiotic inoculants on the fermentation of fresh waste grape berries. In the fermentation process, the variations of pH and EC value, chemical characteristics of the fermentation products, as well as the microbial communities' composition were simultaneously observed. In addition, the feasibility of using the fermentation products as chemical fertilizer substitute in agricultural production also has been verified in this study. The results indicated that the different probiotic inoculants has shown clear impacts on the variation trends of pH and EC value in the grape waste fermentation. Lactobacillus casei and Zygosaccharomyces rouxii are ideal probiotics for the fermentation of waste grape, which enhanced the contents of free Aa and other nutrients in fermentation products. Compared with Fn treatment (without exogenous inoculants), the total free Aa contents in Fs (inoculation with Z. rouxii) and Fm (inoculation with L. casei and Z. rouxii mixture) treatments have improved by 199.1% and 325.5%, respectively. The microbial communities' composition during the fermentation process also been greatly influenced by the different inoculants. At the genus level, Lactobacillus and Pseudomonas were the dominant bacteria, while Saccharomyces and Candida were the dominant fungi in the fermentation. Using the fermentation products as chemical fertilizer substitute has enhanced the quality of Kyoho grape. Compared with traditional chemical fertilization treatment (T1), application with fermented grape waste (T2) has significantly improved VC and soluble solid contents in grape berries by 16.89% and 20.12%, respectively. In conclusion, fermentation with suitable probiotics was an efficient approach for the disposal and recycling of fresh waste grape in vineyards.

Bioremediation of Wastewater Using Yeast Strains: An Assessment of Contaminant Removal Efficiency

The main goal of wastewater treatment is to significantly reduce organic compounds, micronutrients (nitrogen and phosphorus) and heavy metals and other contaminants (pathogens, pharmaceuticals and industrial chemicals). In this work, the efficiency of removing different contaminants (COD, NO₃^-, NO₂^-, NH₄⁺, PO₄^3-, SO₄^2-, Pb²⁺, Cd²⁺) from synthetic wastewater was tested using five different yeast strains: Kluyveromyces marxianus CMGBP16 (P1), Saccharomyces cerevisiae S228C (P2), Saccharomyces cerevisiae CM6B70 (P3), Saccharomyces cerevisiae CMGB234 (P4) and Pichia anomala CMGB88 (P5). The results showed a removal efficiency of up to 70% of COD, 97% of nitrate, 80% of nitrite, 93% of phosphate and 70% of sulfate ions for synthetic wastewater contaminated with Pb²⁺ (43 mg/L) and Cd²⁺ ions (39 mg/L). In contrast, the results showed an increase in ammonium ions, especially in the presence of Pb²⁺ ions. The yeast strains showed a high capacity to reduce Pb²⁺ (up to 96%) and Cd²⁺ (up to 40%) ions compared to the initial concentrations. In presence of a crude biosurfactant, the removal efficiency increased up to 99% for Pb²⁺ and 56% for Cd²⁺ simultaneously with an increase in yeast biomass of up to 11 times. The results, which were obtained in the absence of aeration and in neutral pH conditions, proved a high potential for practical applications in the biotreatment of the wastewater and the recovery of Pb and Cd ions, with a high benefit-cost ratio.

Machine learning approaches for biomolecular, biophysical, and biomaterials research

A fluent conversation with a virtual assistant, person-tailored news feeds, and deep-fake images created within seconds-all those things that have been unthinkable for a long time are now a part of our everyday lives. What these examples have in common is that they are realized by different means of machine learning (ML), a technology that has fundamentally changed many aspects of the modern world. The possibility to process enormous amount of data in multi-hierarchical, digital constructs has paved the way not only for creating intelligent systems but also for obtaining surprising new insight into many scientific problems. However, in the different areas of biosciences, which typically rely heavily on the collection of time-consuming experimental data, applying ML methods is a bit more challenging: Here, difficulties can arise from small datasets and the inherent, broad variability, and complexity associated with studying biological objects and phenomena. In this Review, we give an overview of commonly used ML algorithms (which are often referred to as "machines") and learning strategies as well as their applications in different bio-disciplines such as molecular biology, drug development, biophysics, and biomaterials science. We highlight how selected research questions from those fields were successfully translated into machine readable formats, discuss typical problems that can arise in this context, and provide an overview of how to resolve those encountered difficulties.

Electrohydrodynamic Processing of Potato Protein into Particles and Fibers

Potato protein particles and fibers were produced using electrohydrodynamic processing (electrospray and electrospinning). The effect of different solvents and protein concentration on the morphology of the potato protein particles and fibers was investigated. Electrosprayed particles with average diameters ranging from 0.3 to 1.4 µm could be obtained using water and mixtures of water: ethanol (9:1) and water:glycerol (9:1). Electrosprayed particles were also obtained using the solvent hexafluoro-2-propanol (HFIP) at a protein concentration of 5% wt/v. For protein concentrations above 10% wt/v, using HFIP, electrospun fibers were produced. The release of vitamin B12, as a model bioactive compound, from potato protein electrospun fibers, was also investigated, demonstrating their potential to be utilized as encapsulation and delivery systems.

Biosystems Design by Machine Learning

Biosystems such as enzymes, pathways, and whole cells have been increasingly explored for biotechnological applications. However, the intricate connectivity and resulting complexity of biosystems poses a major hurdle in designing biosystems with desirable features. As -omics and other high throughput technologies have been rapidly developed, the promise of applying machine learning (ML) techniques in biosystems design has started to become a reality. ML models enable the identification of patterns within complicated biological data across multiple scales of analysis and can augment biosystems design applications by predicting new candidates for optimized performance. ML is being used at every stage of biosystems design to help find nonobvious engineering solutions with fewer design iterations. In this review, we first describe commonly used models and modeling paradigms within ML. We then discuss some applications of these models that have already shown success in biotechnological applications. Moreover, we discuss successful applications at all scales of biosystems design, including nucleic acids, genetic circuits, proteins, pathways, genomes, and bioprocesses. Finally, we discuss some limitations of these methods and potential solutions as well as prospects of the combination of ML and biosystems design.