ABSTRACT
Although, coumarins are a group of compounds which are naturally found in some plants, they can be synthetically produced as well. Because of their diverse derivatives, origin and properties most of them can be used for medicinal purposes. For example, they can be used against fungal diseases or in studying structure and biological properties of antifungal agents to discover new compounds with the similar activity. A Structure Property/Activity Relationship [SAR] can be utilized in prediction of biological activity of desired molecules. In order to represent a relationship between the physicochemical properties of coumarin compounds and their biological activities, 68 coumarins and coumarin derivatives with already reported antifungal activities were selected ' and eleven attributes were generated. The descriptors were used to perform artificial neural network [ANN] and to build a model for predicting effectiveness of the new ones. The correlation coefficient between the experimental and the predicted MIC values pertaining to all the coumarins was O.984. This study paves the way for further researches about antifungal activity of coumarins, and offers a powerful tool in modeling and prediction of their bioactivities