Optimization of the drug-likeness of chemical libraries

A scoring scheme for the classification of molecules into drugs and non-dru gs was established. It was set up by using atom type descriptors for encodi ng the molecular structures and by training a feed-forward neural network f or classifying the molecules. The approach was parameterized by using large databases of drugs and non-drugs - the Available Chemicals Directory (ACD) with 169 331 molecules and the World Drug Index (WDI) with 38 416 molecule s. It was able to reveal features in the molecular descriptors that either qualify or disqualify a molecule for being a drug. The method classified ab out 80% of the ACD and the WDI correctly. It was extended to the applicatio n for crop protection compounds and can be used to prioritize compounds for synthesis, purchase, or biological testing. An enhancement allows to optim ize the drug character of combinatorial libraries.