The Conjunctive Disjunctive Node Kernel

Gene-disease associations are inferred on the basis of simi- larities between the proteins encoded by genes. Biological relationships used to define similarities range from interacting proteins, proteins that participate in pathways and protein expression profiles. Though graph ker- nel methods have become a prominent approach for association prediction, most solutions are based on a notion of information diffusion that does not capture the specificity of different network parts. Here we propose a graph kernel method that explicitly models the configuration of each gene’s con- text. An empirical evaluation on several biological databases shows that our proposal is competitive w.r.t. state-of-the-art kernel approaches.