Predicting disease genes for complex diseases using random watcher-walker

In this paper we propose an extended version of random walks, named Random Watcher-Walker (RW2), to predict disease-genes relations on the Human Interactome network. $RW^2$ is able to learn rich representations of disease genes (or gene products) features by jointly considering functional and connectivity patterns surrounding proteins. Our method successfully compares with the best-known system for disease gene prediction and other state-of-the-art graph-based methods. We perform sensitivity analysis and apply perturbations to ensure robustness. Differently from previous studies, our results demonstrate that connectivity alone is not sufficient to classify disease-related genes.