Gene Function Prediction with Gene Interaction Networks: A Context Graph Kernel Approach
This work addresses gene function prediction for biologists, offering an incremental improvement by incorporating indirect interactions over existing methods.
The paper tackled gene function prediction by using a gene's context graph within interaction networks, proposing a context graph kernel in a machine-learning framework. The approach demonstrated empirical superiority over linkage-assumption-based methods on a p53-related gene testbed, though no specific numerical gains were provided.
Predicting gene functions is a challenge for biologists in the post genomic era. Interactions among genes and their products compose networks that can be used to infer gene functions. Most previous studies adopt a linkage assumption, i.e., they assume that gene interactions indicate functional similarities between connected genes. In this study, we propose to use a gene's context graph, i.e., the gene interaction network associated with the focal gene, to infer its functions. In a kernel-based machine-learning framework, we design a context graph kernel to capture the information in context graphs. Our experimental study on a testbed of p53-related genes demonstrates the advantage of using indirect gene interactions and shows the empirical superiority of the proposed approach over linkage-assumption-based methods, such as the algorithm to minimize inconsistent connected genes and diffusion kernels.