Prediction of gene functions is a major challenge to biol- ogists in the post-genomic era. Interactions between genes and their products compose networks and can be used to infer gene functions. Most previous studies used heuris- tic approaches based on either local or global informa- tion of gene interaction networks to assign unknown gene functions. In this study, we propose a graph kernel-based method that can capture the structure of gene interaction networks to predict gene functions. We conducted an ex- perimental study on a test-bed of P53-related genes. The experimental results demonstrated better performance for our proposed method as compared with baseline methods.