Can machine learning algorithms perform better than multiple linear regression in predicting nitrogen excretion from lactating dairy cows

Rational design of deep eutectic solvents for the stabilization of dehydrogenases: an artificial neural network prediction approach

Stabilized enzymes are crucial for the industrial application of biocatalysis due to their enhanced operational stability, which leads to prolonged enzyme activity, cost-efficiency and consequently scalability of biocatalytic processes. Over the past decade, numerous studies have demonstrated that deep eutectic solvents (DES) are excellent enzyme stabilizers. However, the search for an optimal DES has primarily relied on trial-and-error methods, lacking systematic exploration of DES structure-activity relationships. Therefore, this study aims to rationally design DES to stabilize various dehydrogenases through extensive experimental screening, followed by the development of a straightforward and reliable mathematical model to predict the efficacy of DES in enzyme stabilization. A total of 28 DES were tested for their ability to stabilize three dehydrogenases at 30°C: (S)-alcohol dehydrogenase from Rhodococcus ruber (ADH-A), (R)-alcohol dehydrogenase from Lactobacillus kefir (Lk-ADH) and glucose dehydrogenase from Bacillus megaterium (GDH). The residual activity of these enzymes in the presence of DES was quantified using first-order kinetic models. The screening revealed that DES based on polyols serve as promising stabilizing environments for the three tested dehydrogenases, particularly for the enzymes Lk-ADH and GDH, which are intrinsically unstable in aqueous environments. In glycerol-based DES, increases in enzyme half-life of up to 175-fold for Lk-ADH and 60-fold for GDH were observed compared to reference buffers. Furthermore, to establish the relationship between the enzyme inactivation rate constants and DES descriptors generated by the Conductor-like Screening Model for Real Solvents, artificial neural network models were developed. The models for ADH-A and GDH showed high efficiency and reliability (R2 > 0.75) for in silico screening of the enzyme inactivation rate constants based on DES descriptors. In conclusion, these results highlight the significant potential of the integrated experimental and in silico approach for the rational design of DES tailored to stabilize enzymes.

Multilayer perceptron and support vector regression models for feline parturition date prediction

A crucial challenge in feline obstetric care is the accurate prediction of the parturition date during late pregnancy. The classic simple linear regression (SLR) model, which employed the fetal biparietal diameter (BPD) as the single input feature, was frequently applied for such prediction with limited accuracy. Since Multilayer Perceptron (MLP) and Support Vector Regression (SVR) are now two of the most potent scientific regression models, this study, for the first time, introduced such models as the new promising tools for feline parturition date prediction. The following features were candidate inputs for our models: biparietal diameter (BPD), litter size, and maternal weight. We observed and compared the performance results for each model. As the best-performed model, MLP delivered the highest coefficient score (0.972 ± 0.006), lowest mean absolute error score (1.110 ± 0.060), and lowest mean squared error score (1.540 ± 0.141), respectively. For the first time in this study, BPD, litter size, and maternal weight were considered the essential features for the innovative MLP and SVR modeling. With the optimized model parameters and the described analytical platform, further verification of these advanced models in feline obstetric practices is feasible.

Application of Multivariate Regression and Artificial Neural Network Modelling for Prediction of Physicochemical Properties of Grape-Skin Compost

The reusability of by-products in the food industry is consistent with sustainable and greener production; therefore, the aim of this paper was to evaluate the applicability of multiple linear regression (MLR), piecewise linear regression (PLR) and artificial neural network models (ANN) to the prediction of grape-skin compost's physicochemical properties (moisture, dry matter, organic matter, ash content, carbon content, nitrogen content, C/N ratio, total colour change of compost samples, pH, conductivity, total dissolved solids and total colour change of compost extract samples) during in-vessel composting based on the initial composting conditions (air-flow rate, moisture content and day of sampling). Based on the coefficient of determination for prediction, the adjusted coefficient of determination for calibration, the root-mean-square error of prediction (RMSEP), the standard error of prediction (SEP), the ratio of prediction to deviation (RPD) and the ratio of the error range (RER), it can be concluded that all developed MLR and PLR models are acceptable for process screening. Furthermore, the ANN model developed for predicting moisture and dry-matter content can be used for quality control (RER >11). The obtained results show the great potential of multivariate modelling for analysis of the physicochemical properties of compost during composting, confirming the high applicability of modelling in greener production processes.

Finding optimum climatic parameters for high tomato yield in Benin (West Africa) using frequent pattern growth algorithm

Tomato is one of the most appreciated vegetables in the world. Predicting its yield and optimizing its culture is important for global food security. This paper addresses the challenge of finding optimum climatic values for a high tomato yield. The Frequent Pattern Growth (FPG) algorithm was considered to establish the associations between six climate variables: minimum and maximum temperatures, maximum humidity, sunshine (Sun), rainfall, and evapotranspiration (ET), collected over 26 years in the three agro-ecological Zones of Benin. Monthly climate data were aggregated with yield data over the same period. After aggregation, the data were transformed into 'low', 'medium', and 'high' attributes using the threshold values defined. Then, the rules were generated using the minimum support set to 0.2 and the confidence to 0.8. Only the rules with the consequence 'high yield' were screened. The best yield patterns were observed in the Guinean Zone, followed by the Sudanian. The results indicated that high tomato yield was associated with low ET in all areas considered. Minimum and maximum temperatures, maximum humidity, and Sun were medium in every Zone. Moreover, rainfall was high in the Sudanian Zone, unlike the other regions where it remained medium. These results are useful in assessing climate variability's impact on tomato production. Thus, they can help farmers make informed decisions on cultivation practices to optimize production in a changing environment. In addition, the findings of this study can be considered in other regions and adapted to other crops.

The application of machine learning to air pollution research: A bibliometric analysis

Machine learning (ML) is an advanced computer algorithm that simulates the human learning process to solve problems. With an explosion of monitoring data and the increasing demand for fast and accurate prediction, ML models have been rapidly developed and applied in air pollution research. In order to explore the status of ML applications in air pollution research, a bibliometric analysis was made based on 2962 articles published from 1990 to 2021. The number of publications increased sharply after 2017, comprising approximately 75% of the total. Institutions in China and United States contributed half of all publications with most research being conducted by individual groups rather than global collaborations. Cluster analysis revealed four main research topics for the application of ML: chemical characterization of pollutants, short-term forecasting, detection improvement and optimizing emission control. The rapid development of ML algorithms has increased the capability to explore the chemical characteristics of multiple pollutants, analyze chemical reactions and their driving factors, and simulate scenarios. Combined with multi-field data, ML models are a powerful tool for analyzing atmospheric chemical processes and evaluating the management of air quality and deserve greater attention in future.