The expanded human disease network combining protein-protein interaction information

Abstract

The human disease network (HDN) has become a powerful tool for revealing disease-disease associations. Some studies have shown that genes that share similar or same disease phenotypes tend to encode proteins that interact with each other. Therefore, protein-protein interactions (PPIs) may help us to further understand the relationships between diseases with overlapping clinical phenotypes. In this study, we constructed the expanded HDN (eHDN) by combining disease gene information with PPI information, and analyzed its topological features and functional properties. We found that the network is hierarchical and, most diseases are connected to only a few diseases, whereas a small part of diseases are linked to many different diseases. Diseases in a specific disease class tend to cluster together, and genes associated with the same disease are functionally related. Comparing the eHDN with the original HDN (oHDN, constructed using disease gene information) revealed high consistency over all topological and functional properties. This, to some extent, indicates that our eHDN is reliable. In the eHDN, we found some new associations among diseases resulting from the shared genes interacting with disease genes. The new eHDN will provide a valuable reference for clinicians and medical researchers.

Figure 1

The expanded HDN (eHDN). In the eHDN, each node corresponds to a distinct disease and is colored based on the disease class to which it belongs. The names of the 19 disease classes are shown on the right. Links between diseases in the same disease class are correspondingly colored and links connecting different disease classes are gray. The size of each node is proportional to the number of genes associated with the corresponding disease, and the thickness of the link is proportional to the number of genes shared by the diseases it connects. Diseases with >10 associated genes are named.

Figure 2

Analysis of the topological features in the eHDN. (a) The distribution of the number of genes associated with a disorder, (s). (b) Distribution of the degree (k). (c) The distribution of the clustering coefficient follows C(k) ∼k⁻¹, a straight line of slope-1 on a log-log plot.

Figure 3

Analysis of the functional properties in the eHDN. (a) Distribution of the GO homogeneity of a disease. A random control with the same number of genes chosen randomly is shown for comparison. (b) Distribution of the subcellular location homogeneity of a disease. A random control with the same number of genes chosen randomly is shown for comparison. (c) As an example of GSE7307, the distribution of P_ij values for the expression profiles of each disease gene pair that belongs to the same disorder (solid line) and the control (dashed line), representing the PCC distribution between all gene pairs, is shown. (d) For the GSE7307, the distribution of the average PCC (P_disease) between the expression profiles of all the genes associated with the same disorder (solid line) and the random control (dashed line) with the same number of genes chosen randomly is shown.