Accurate Machine Learning for Predicting the Viscosities of Deep Eutectic Solvents.

Deep eutectic solvents (DESs) are emerging as environmentally friendly designer solvents for mass transport and heat transfer processes in industrial applications; however, the lack of accurate tools to predict and thus control their viscosities under both a range of environmental factors and formulations hinders their general application. While DESs may serve as designer solvents, with nearly unlimited combinations, this unfortunately makes it experimentally infeasible to comprehensively measure the viscosities of all DESs of potential industrial interest. To assist in the design of DESs, we have developed several new machine learning (ML) models that accurately and rapidly predict the viscosities of a diverse group of DESs at different temperatures and molar ratios using, to date, one of the most comprehensive data sets containing the properties of over 670 DESs over a wide range of temperatures (278.15-385.25 K). Three ML models, including support vector regression (SVR), feed forward neural networks (FFNNs), and categorical boosting (CatBoost), were developed to predict DES viscosity as a function of temperature and molar ratio and contrasted with multilinear and two-factor polynomial regression baselines. Quantum chemistry-based, COSMO-RS-derived sigma profile (σ-profile) features were used as inputs for the ML models. The CatBoost model is excellent at externally predicting DES viscosity, as indicated by high R2 (0.99) and low root-mean-square-error (RMSE) and average absolute relative deviations (AARD) (5.22%) values for the testing data sets, and 98% of the data points lie within the 15% of AARD deviations. Furthermore, SHapley additive explanation (SHAP) analysis was employed to interpret the ML results and rationalize the viscosity predictions. The result is an ML approach that accurately predicts viscosity and will aid in accelerating the design of appropriate DESs for industrial applications.

Improved ethanol productivity and ethanol tolerance through genome shuffling of Saccharomyces cerevisiae and Pichia stipitis

Genome shuffling by recursive protoplast fusion between Saccharomyces cerevisiae and Pichia stipitis also known as Scheffersomyces stipitis resulted in a promising yeast hybrid strain with superior qualities than those of the parental strains in enhancing biofuel production. Our study focused on the substrate utilization, ethanol fermentation, and ethanol tolerance of the hybrids and the parental strains. The parental strain S. cerevisiae is limited to utilize only hexose sugars, and this leads to decrease in the ethanol yield when they are subjected to ethanol production from lignocellulosic biomass which is rich in pentose sugars. To overcome this limitation, we constructed a hybrid yeast strain through genome shuffling which can assimilate all the sugars present in the fermentation medium. After two rounds of recursive protoplast fusion, there was a higher increase in substrate utilization by hybrid SP2-18 compared to parental strain S. cerevisiae. SP2-18 was able to consume 34% of xylose sugar present in the fermentation medium, whereas S. cerevisiae was not able to utilize xylose. Further, the hybrid strain SP2-18 was able to reach an ethanol productivity of 1.03 g L−1 h−1, ethanol yield 0.447 g/g, and ethanol concentration 74.65 g L−1 which was relatively higher than that of the parental strain S. cerevisiae. Furthermore, the hybrid SP2-18 was found to be stable in the production of ethanol. The random amplified polymorphic DNA profile of the yeast hybrid SP2-18 shows the polymorphism between the parental strains indicating the migration of specific sugar metabolizing genes from P. stipitis, while the maximum similarity was with the parent S. cerevisiae

No disponible

Improved ethanol productivity and ethanol tolerance through genome shuffling of Saccharomyces cerevisiae and Pichia stipitis.

Genome shuffling by recursive protoplast fusion between Saccharomyces cerevisiae and Pichia stipitis also known as Scheffersomyces stipitis resulted in a promising yeast hybrid strain with superior qualities than those of the parental strains in enhancing biofuel production. Our study focused on the substrate utilization, ethanol fermentation, and ethanol tolerance of the hybrids and the parental strains. The parental strain S. cerevisiae is limited to utilize only hexose sugars, and this leads to decrease in the ethanol yield when they are subjected to ethanol production from lignocellulosic biomass which is rich in pentose sugars. To overcome this limitation, we constructed a hybrid yeast strain through genome shuffling which can assimilate all the sugars present in the fermentation medium. After two rounds of recursive protoplast fusion, there was a higher increase in substrate utilization by hybrid SP2-18 compared to parental strain S. cerevisiae. SP2-18 was able to consume 34% of xylose sugar present in the fermentation medium, whereas S. cerevisiae was not able to utilize xylose. Further, the hybrid strain SP2-18 was able to reach an ethanol productivity of 1.03 g L-1 h-1, ethanol yield 0.447 g/g, and ethanol concentration 74.65 g L-1 which was relatively higher than that of the parental strain S. cerevisiae. Furthermore, the hybrid SP2-18 was found to be stable in the production of ethanol. The random amplified polymorphic DNA profile of the yeast hybrid SP2-18 shows the polymorphism between the parental strains indicating the migration of specific sugar metabolizing genes from P. stipitis, while the maximum similarity was with the parent S. cerevisiae.