Graph Kernels for Molecular Structure−Activity Relationship Analysis with Support Vector Machines

摘要: The support vector machine algorithm together with graph kernel functions has recently been introduced to model structure-activity relationships (SAR) of molecules from their 2D structure, without the need for explicit molecular descriptor computation. We propose two extensions this approach double goal reduce computational burden associated and enhance its predictive accuracy: description by a Morgan index process definition second-order Markov random walks on structures. Experiments mutagenicity data sets validate proposed extensions, making possible complementary alternative other modeling strategies.