Artificial neural network applied to prediction of fluorquinolone antibacterial activity by topological methods

A new topological method that makes it possible to predict the properties o f molecules on the basis of their chemical structures is applied in the pre sent study to quinolone antimicrobial agents. This method uses neural netwo rks in which training algorithms are used as well as different concepts and methods of artificial intelligence with a suitable set of topological desc riptors. This makes it possible to determine the minimal inhibitory concent ration (MIC) of quinolones. Analysis of the results shows that the experime ntal and calculated values are highly similar. It is possible to obtain a Q SAR interpretation of the information contained in the network after the tr aining has been carried out.