(1811) Views (1575) Full article downloads
Authors: Seyyedeh Soghra Mousavi, Hanieh Bokharaie, Shadi Rahimi, et al
PublishedDate August 2010 Volume 2010:3 Pages 59 - 66
Seyyedeh Soghra Mousavi 1 , Hanieh Bokharaie 2 , Shadi Rahimi 3 , Sima Azadi Soror 4 , Mehrdad Hamidi 5 1 Department of Biotechnology, School of Pharmacy, Zanjan University of Medical Science, Zanjan, Iran; 2 Genetic Group, Biology Department, Faculty of Basic Sciences, Science and Research Branch, IslamicAzad University, Tehran, Iran; 3 Department of Biology, Faculty of Science, Tarbiat Moallem University, Tehran, Iran: 4 Plant Protection Department, Faculty of Agriculture, Bu-Ali Sina University,Hamedan, Iran; 5 Department of Pharmaceutics, School of Pharmacy, Zanjan University of Medical Science, Zanjan, Iran
Abstract: In recent years, due to vital need for novel fungicidal agents,investigation on natural antifungal resources has been increased. The special features exhibited by neural network classifiers make them suitable for handling complex problems like analyzing differentproperties of candidate compounds in computer-aided drug design. In this study, by using a Levenberg–Marquardt (LM) neural network (the fastest of the training algorithms), the relation between someimportant thermodynamic and physico-chemical properties of coumarin compounds and their biological activities (tested against Candida albicans ) has been evaluated. A set of already reported antifungalbioactive coumarin and some well-known physical descriptors have been selected and using LM training algorithm the best architecture of neural model has been designed for forecasting the new bioactive...