Introduction
| Disease gene prediction is to find out genes that related to specific disease. Through previous studies, evidences showed that genes related to a specific or similar disease phenotype tend to be located in a specific neighborhood in the protein-protein interaction network. As the development of recent high-throughput technologies, more and more gene data have been produced. If machine learning methods can been introduce to this problem, we think the prediction result will be better. |
Input
 |
Parameter 1: gene-phenotype heterogeneous network.This heterogeneous network contains gene-gene association, gene-phenotype association and human phenotype
similarity netwrok. Just like left pannel. Parameter 2: Disease ID. Specific the disease to analysis. |
||
Output
|
genes satisfy the conditions like belows: 1. gene no links with specific disease in heterogeneous network 2. gene have high HeteSim scores |