BioPPSy

Computationally predicts the pharmacokinetic properties of drug candidates using Quantitative Structure Property Relationships (QSPR) modelling. Assembles a set of tools and databases for predicting the physical properties of small molecules. The program models a given property's dependence on a collection of molecular and structural descriptors using a training set of molecules. Neural networks and support vector regression are available, as well as linear models. The models generated by this analysis can then be used to predict the properties of compounds during the development of new and novel drugs. The program and its databases are all open-source.