| Abstrakt: |
Researchers at Uniwersytet Mikolaja Kopernika w Toruniu have published a study on the use of artificial neural networks (ANNs) to predict the antimicrobial activity of imidazole derivatives against Enterococcus faecalis. The study found that the designed regression model accurately predicted the minimum inhibitory concentration for E. faecalis growth, with a coefficient of correlation of 0.91 for the training set, 0.91 for the test set, and 0.97 for the validation set. The classification model also successfully categorized the compounds as predictively active or inactive against the microorganism. The researchers concluded that ANNs can streamline the compound synthesis process and expedite the discovery of promising antimicrobial substances. [Extracted from the article] |
