A Graph Kernel Incorporating Molecule´s Stereisomerism Information

The prediction of molecule´s properties through Quantitative Structure Activity (resp. Property) Relationships are two active research fields named QSAR and QSPR. Within these frameworks Graph kernels allow to combine a natural encoding of a molecule by a graph with classical statistical tools such as SVM or kernel ridge regression. Unfortunately some molecules encoded by a same graph and differing only by the three dimensional orientations of their atoms in space have different properties. Such molecules are called stereoisomer´s. These latter properties can not be predicted by usual graph methods which do not encode stereoisomerism. In this paper we propose a new graph encoding of molecules taking explicitly into account stereoisomerism and propose a new kernel between these structures in order to predict properties related to stereoisomerism.