A Feature-Learning based method for the disease-gene prediction problem
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 characterised 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 (RW2), which is shown to
perform better than other state-of-the-art algorithms. We also show that the
performance of RW2 and other compared state-of-the-art algorithms is
extremely sensitive to the interactome used, and to the adopted disease
categorisations, since this influences the ability to capture regularities in
presence of sparsity and incompleteness.