Kernel Functions for Attributed Molecular Graphs – A New Similarity Based Approach To ADME Prediction in Classification and Regression Holger Fröhlich*, Jörg. K. Wegner, Florian Sieker and Andreas Zell Centre for Bioinformatics Tübingen (ZBIT) Sand 1, 72076 Tübingen, Germany To receive all correspondence; E-mail: {holger.froehlich}@informatik.uni-tuebingen.de Keywords: molecular graph mining, graph representation, reduced graph representation, molecular similarity, Kernel Methods, Support Vector Machines Abbreviations: Support Vector Machine – SVM, Human Intestinal Absorption – HIA, Blood Brain Barrier – BBB, Search and Optimization of Lead Structures – SOL Received on: Full Paper Kernel methods, like the well-known Support Vector Machine (SVM), have gained a growing interest during the last years for designing QSAR/QSPR models having a high predictive strength. One of the key concepts of SVMs is the usage of a so-called kernel function, which can be thought of as a special similarity measure. In this paper we consider kernels for molecular structures, which are based on a graph representation of chemical compounds. The similarity score is calculated by computing an optimal assignment of the atoms from one molecule to those of another one, including information on specific chemical properties, membership to a substructure (e.g. aromatic ring, carbonyl group, etc.) and neighborhood for each atom. We show that by using this kernel we can achieve a generalization performance comparable to a classical model with a few descriptors, which are a-priori known to be relevant for the problem, and significantly better results than with and without performing an