Abstract
During the last few years, the knowledge of drug, disease phenotype and protein has been rapidly accumulated and more and more scientists have been draw attention to inferring drug-disease associations by computational method. Development of an integrated approach for systematic discovering drug-disease associations by those informational data is an important issue. We combine three weighted networks of drug, genomic and disease phenotype data from available experimental data and knowledge then infer drug-disease associations by a hetero-network propagation approach. In the experiments, we adopt prostate cancer and colorectal cancer as our test data. We select the manually curated associations from comparative toxicogenomics database as our benchmark. The ranked results show that our proposed method obtains high specificity and sensitivity and clearly outperforms previous methods. We clearly demonstrate the feasibility and benefits of using network-based analyses of chemical, genomic and phenotype data to reveal drug-disease associations. The potential associations which were inferred by our method drew the biologists’ attention and provide new perspectives for toxicogenomics and drug reposition evaluation.