Gene prioritization using a probabilistic knowledge model

We are interested in exploiting domain knowledge for the task of candidate gene prioritization. In this paper, we present a new gene prioritization method that learns a probabilistic knowledge model and exploits it to prioritize candidate genes. The knowledge model is represented by a network of associations among domain concepts (e.g., genes) and is extracted from a domain database (e.g., protein-protein interaction database). This knowledge model is then used to perform probabilistic inferences and applied to the task of gene prioritization. We evaluate our new method on five diseases and show that it outperforms a recently described network-based method for candidate gene prioritization.