The recognition of disease genes has long been an important goal of biomedical research, which may contribute to the improvement of medical care and to the understanding of gene functions, interactions, and pathways. Because of it's importance, many contributions have been made by previous studies.

With the rapidly increasing availability of public data , machine learning methods may contribute to a better understanding of disease genes. Here we propose two novel multipath methods, HeteSim_MultiPath (HSMP) and HeteSim_SVM (HSSVM), based on gene-phenotype heterogeneous networks.