Machine learning-assisted high-throughput screening for Anti-MRSA compounds.

BACKGROUND: Antimicrobial resistance is a major public health threat, and new agents are needed. Computational approaches have been proposed to reduce the cost and time needed for compound screening. AIMS: A machine learning (ML) model was developed for the in silico screening of low molecular weight molecules. METHODS: We used the results of a high-throughput Caenorhabditis elegans methicillin-resistant Staphylococcus aureus (MRSA) liquid infection assay to develop ML models for compound prioritization and quality control. RESULTS: The compound prioritization model achieved an AUC of 0.795 with a sensitivity of 81% and a specificity of 70%. When applied to a validation set of 22,768 compounds, the model identified 81% of the active compounds identified by high-throughput screening (HTS) among only 30.6% of the total 22,768 compounds, resulting in a 2.67-fold increase in hit rate. When we retrained the model on all the compounds of the HTS dataset, it further identified 45 discordant molecules classified as non-hits by the HTS, with 42/45 (93%) having known antimicrobial activity. CONCLUSION: Our ML approach can be used to increase HTS efficiency by reducing the number of compounds that need to be physically screened and identifying potential missed hits, making HTS more accessible and reducing barriers to entry.

Impact of tannin addition on the antioxidant activity and sensory character of Malagousia white wine.

Enological tannins are assessed as promising alternative to SO2 in order to control oxidative process during winemaking, due to allergic reactions incurred by sulfite sensitive individuals. In the present study, the commercial enological Tara tannin "Vitanil B″ was added, as alternative to the addition of sulfites, at different concentrations (100-500 mg/L) in white wine from grapes of Vitis vinifera L. var. Malagousia in order to enhance antioxidant stability and sensory character of the wine. Considering photometric analyses and chromatic parameters results, tannin addition (300 mg/L) in Malagousia enhanced total phenolic content, antioxidant and antiradical activity and prevented color deterioration, for a storage period of 100 d, compared to control and sulfited wines. Moreover, aroma quality, body, after taste and overall acceptance of wine treated with 300 mg/L tannin, were highly appreciated and received the highest scores. The overall evaluation of tannin addition was performed by Principal Component Analysis, leading to discrimination of wines, according to photometric, color and sensory analysis parameters. Conclusively, tannin addition resulted in a considerable increase of total phenolic content, antioxidant and antiradical activity, compared to the control and sulfited wines, maintaining the sensory parameters and overall acceptance of Malagousia wine.

Effect of ethanol, glycerol, glucose/fructose and tartaric acid on the refractive index of model aqueous solutions and wine samples.

The refractive index is a basic optical property of materials. This study explores the effect of ethanol, glycerol, tartaric acid and glucose/fructose on the refractive index in model aqueous solutions and in dry white wines. Various model aqueous solutions consisting of these components were prepared and the refractive index was measured at 20 °C and each component was studied both alone and in mixtures with the others. The refractive index of white dry wines samples was also measured. A linear regression analysis was performed and linear multi-dependence equations were derived. The resulting regression models had a coefficient of determination over 97.3%. Glucose/fructose was found to have the greatest effect on the refractive index, followed by tartaric acid and glycerol while ethanol had the smallest effect. The knowledge of the correlation of the concentration of each wine component to the refractive index can be of value for the estimation of fermentation kinetics.

Effect of ethanol, glycerol, glucose and tartaric acid on the viscosity of model aqueous solutions and wine samples.

Viscosity is a property that exerts great influence on the body of wines, since it affects the sensation of thickness in the mouth. The present study refers to the quantitative correlation of the major components of wine, alcohol, reduced sugar, glycerol and total acidity, in its viscosity. Various model aqueous solutions consisting of these components were prepared and viscosity was measured at 20 °C. Each component was studied either alone or in mixtures with the others. Viscosity of white dry wines samples was also measured. From the experimental results, linear multi-dependence equations were derived, which correlate the viscosity with the concentration of the components of the solutions, each of them alone and in combination. Glucose was found to affect viscosity of model aqueous solutions the most, whereas ethanol had the least effect. The knowledge of these factors may have a practical value in optimizing wine's body.