Network-based methods for disease-gene prediction

TL;DR

This paper introduces a novel network-based method called Random Watcher-Walker ($RW^2$) for predicting disease-related genes using the Human Interactome, addressing challenges of data incompleteness and lack of negative examples.

Contribution

The paper presents $RW^2$, an extended random walk approach that learns rich representations of disease genes from the Interactome, outperforming existing methods.

Findings

$RW^2$ achieves competitive accuracy in disease gene prediction.

Connectivity alone is insufficient for classifying disease-related genes.

The method demonstrates robustness through sensitivity analysis.

Abstract

We predict disease-genes relations on the Human Interactome network using a methodology that jointly learns functional and connectivity patterns surrounding proteins. Contrary to other data structures, the Interactome is characterized by high incompleteness and absence of explicit negative knowledge, which makes predictive tasks particularly challenging. To exploit at best latent information in the network, we propose an extended version of random walks, named Random Watcher-Walker ($RW^2$), which is able to learn rich representations of disease genes (or gene products) features. 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. In contrast with previous studies, our results demonstrate that connectivity alone is not sufficient to classify disease-related genes.