Evolutionary Molecular Design in Virtual Fitness Landscapes

Multi-space classification for predicting GPCR-ligands

A classification of molecules depends on the descriptor set which is used to represent the compounds, and each descriptor could be regarded as one perception of a molecule. In this study we show that a combination of several classifiers that are grounded on separate descriptor sets can be superior to a single classifier that was built using all available descriptors. The task of predicting ligands of G-protein coupled receptors (GPCR) served as an example application. The perceptron, multilayer neural networks, and radial basis function (RBF) networks were employed for prediction. We developed classifiers with and without descriptor selection. Prediction accuracy was assessed by the area under the receiver operating characteristic (ROC) curve. In the case with descriptor selection both the selection and the rank order of the descriptors depended on the type and topology of the neural networks. We demonstrate that the overall prediction accuracy of the system can be improved by joining neural network classifiers of different type and topology using a "jury network" that is trained to evaluate the predictions from the individual classifiers. Seventy-one percent correct prediction of GPCR ligands was obtained.

Solid- and solution-phase synthesis of highly-substituted-pyrrolidine libraries

Starting from a complex bicyclic beta-lactam scaffold we have demonstrated the possible production of libraries of a new class of drug-like, highly substituted pyrrolidines. The choice of the type of substitution was made by optimizing various synthetic routes. The selection of each compound is the result of a filtration of a large virtual combinatorial chemical space, using simple criteria. The access to these complex pyrrolidines needed only four to six synthetic steps.