LAUSR

This paper describes QSAR studies by using the Online Chemical Modeling Environment, synthesis, in vitro antifungal activity of 1,3-oxazolylphosphonium derivatives and their acetylcholinesterase inhibitory potential. Three classification QSAR models were created using Random Forests (WEKA-RF), k-Nearest Neighbors and Associative Neural Networks methods and different combinations of descriptors. The predictive ability of the models was tested through cross-validation, giving a balanced accuracy BA=80-91%. All compounds demonstrated good antifungal properties and slight inhibition of acetylcholinesterase activity. The high percentage of coincidence between the QSAR predictions and the experimental results confirmed the high predictive power of the developed QSAR models that can be applied as tools for finding new potential inhibitors against of Candida spp. Furthermore, 1,3-oxazol-4-yl(triphenyl)phosphonium salts could be considered as promising candidates for the treatment of candidiasis and the disinfection of medical equipment.