MACHINE LEARNING TECHNIQUES APPLIED TO LIGNOCELLULOSIC ETHANOL IN SIMULTANEOUS HYDROLYSIS AND FERMENTATION

Simultaneous fermentation and enzymatic biocatalysis-a useful process option?

Biotransformation with enzymes and de novo syntheses with whole-cell biocatalysts each have specific advantages. These can be combined to achieve processes with optimal performance. A recent approach is to perform bioconversion processes and enzymatic catalysis simultaneously in one-pot. This is a well-established process in the biorefinery, where starchy or cellulosic material is degraded enzymatically and simultaneously used as substrate for microbial cultivations. This procedure leads to a number of advantages like saving in time but also in the needed equipment (e.g., reaction vessels). In addition, the inhibition or side-reaction of high sugar concentrations can be overcome by combining the processes. These benefits of coupling microbial conversion and enzymatic biotransformation can also be transferred to other processes for example in the sector of biofuel production or in the food industry. However, finding a compromise between the different requirements of the two processes is challenging in some cases. This article summarises the latest developments and process variations.

Sugarcane wastes as microbial feedstocks: A review of the biorefinery framework from resource recovery to production of value-added products

Sugarcane industry is a major agricultural sector capable of producing sugars with byproducts including straw, bagasse, and molasses. Sugarcane byproducts are no longer wastes since they can be converted into carbon-rich resources for biorefinery if pretreatment of these is well established. Considerable efforts have been devoted to effective pretreatment techniques for each sugarcane byproduct to supply feedstocks in microbial fermentation to produce value-added fuels, chemicals, and polymers. These value-added chains, which start with low-value industrial wastes and end with high-value products, can make sugarcane-based biorefinery a more viable option for the modern chemical industry. In this review, recent advances in sugarcane valorization techniques are presented, ranging from sugarcane processing, pretreatment, and microbial production of value-added products. Three lucrative products, ethanol, 2,3-butanediol, and polyhydroxyalkanoates, whose production from sugarcane wastes has been widely researched, are being explored. Future studies and development in sugarcane waste biorefinery are discussed to overcome the challenges remaining.

Integrated biorefinery approaches for the industrialization of cellulosic ethanol fuel

Lignocellulosic biomass is an abundant and sustainable raw material, but its conversion into ethanol fuel has not yet achieved large-scale industrialization and economic benefits. Integrated biorefineries have been widely identified as the key to achieving this goal. Here, four promising routes were summarized to assemble the new industrial plants for cellulose-based fuels and chemicals, including 1) integration of cellulase production systems into current cellulosic ethanol processes; 2) combination of processes and facilities between cellulosic ethanol and first-generation ethanol; 3) application of enzyme-free saccharification processes and computational approaches to increase the bioethanol yield and optimize the integration process; 4) production of multiple products to maximize the value derived from the lignocellulosic biomass. Finally, the remaining challenges and perspectives of this field are also discussed.

Machine Learning at the Interface of Polymer Science and Biology: How Far Can We Go?

This Perspective outlines recent progress and future directions for using machine learning (ML), a data-driven method, to address critical questions in the design, synthesis, processing, and characterization of biomacromolecules. The achievement of these tasks requires the navigation of vast and complex chemical and biological spaces, difficult to accomplish with reasonable speed. Using modern algorithms and supercomputers, quantum physics methods are able to examine systems containing a few hundred interacting species and determine the probability of finding them in a particular region of phase space, thereby anticipating their properties. Likewise, modern approaches in chemistry and biomolecular simulation, supported by high performance computing, have culminated in producing data sets of escalating size and intrinsically high complexity. Hence, using ML to extract relevant information from these fields is of paramount importance to advance our understanding of chemical and biomolecular systems. At the heart of ML approaches lie statistical algorithms, which by evaluating a portion of a given data set, identify, learn, and manipulate the underlying rules that govern the whole data set. The assembly of a quality model to represent the data followed by the predictions and elimination of error sources are the key steps in ML. In addition to a growing infrastructure of ML tools to address complex problems, an increasing number of aspects related to our understanding of the fundamental properties of biomacromolecules are exposed to ML. These fields, including those residing at the interface of polymer science and biology (i.e., structure determination, de novo design, folding, and dynamics), strive to adopt and take advantage of the transformative power offered by approaches in the ML domain, which clearly has the potential of accelerating research in the field of biomacromolecules.

Polish Varieties of Industrial Hemp and Their Utilisation in the Efficient Production of Lignocellulosic Ethanol

Nowadays, more and more attention is paid to the development and the intensification of the use of renewable energy sources. Hemp might be an alternative plant for bioenergy production. In this paper, four varieties of Polish industrial hemp (Białobrzeskie, Tygra, Henola, and Rajan) were investigated in order to determine which of them are the most advantageous raw materials for the effective production of bioethanol. At the beginning, physical and chemical pretreatment of hemp biomass was carried out. It was found that the most effective is the alkaline treatment with 2% NaOH, and the biomasses of the two varieties were selected for next stages of research: Tygra and Rajan. Hemp biomass before and after pretreatment was analyzed by FTIR and SEM, which confirmed the effectiveness of the pretreatment. Next, an enzymatic hydrolysis process was carried out on the previously selected parameters using the response surface methodology. Subsequently, the two approaches were analyzed: separated hydrolysis and fermentation (SHF) and a simultaneous saccharification and fermentation (SSF) process. For Tygra biomass in the SHF process, the ethanol concentration was 10.5 g∙L⁻¹ (3.04 m³·ha⁻¹), and for Rajan biomass at the SSF process, the ethanol concentration was 7.5 g∙L⁻¹ (2.23 m³·ha⁻¹). In conclusion, the biomass of Polish varieties of hemp, i.e., Tygra and Rajan, was found to be an interesting and promising raw material for bioethanol production.

Use of Machine Learning Methods for Predicting Amount of Bioethanol Obtained from Lignocellulosic Biomass with the Use of Ionic Liquids for Pretreatment

The study objective was to model and predict the bioethanol production process from lignocellulosic biomass based on an example of empirical study results. Two types of algorithms were used in machine learning: artificial neural network (ANN) and random forest algorithm (RF). Data for the model included results of studying bioethanol production with the use of ionic liquids (ILs) and different enzymatic preparations from the following biomass types: buckwheat straw and biomass from four wastelands, including a mixture of various plants: stems of giant miscanthus, common nettle, goldenrod, common broom, fireweed, and hay (a mix of grasses). The input variables consisted of different ionic liquids (imidazolium and ammonium), enzymatic preparations, enzyme doses, time and temperature of pretreatment, and type of yeast for alcoholic fermentation. The output value was the bioethanol concentration. The multilayer perceptron (MLP) was used in the artificial neural networks. Two model types were created; the training dataset comprised 120 vectors (14 elements for Model 1 and 11 elements for Model 2). Assessment of the optimum random forest was carried out using the same division of experimental points (two random datasets, containing 2/3 for training and 1/3 for testing) and the same criteria used for the artificial neural network models. Data for mugwort and hemp were used for validation. In both models, the coefficient of determination for neural networks was <0.9, while for RF it oscillated around 0.95. Considering the fairly large spread of the determination coefficient, two hybrid models were generated. The use of the hybrid approach in creating models describing the present bioethanol production process resulted in an increase in the fit of the model to R2 = 0.961. The hybrid model can be used for the initial classification of plants without the necessity to perform lengthy and expensive research related to IL-based pretreatment and further hydrolysis; only their lignocellulosic composition results are needed.