Drug Target Path Discovery on Semantic Biomedical Big Data

Systems chemical biology integrate chemistry, biology and computation tools as a whole system, which can help researchers to deeply study the interaction and relationship among small molecules, such as genes, proteins, targets, compounds and so on. With systems chemical biology, researchers can concentrate on new way of drug discovery, including drug target path discovery, which can not only help biomedical researchers to find evidences for existing disease associate genes, but also to design new effect medicine based on targets. Network based approaches are the state-of-art solutions for drug target path discovery, however, there are still some challenges: 1) The quality of the network dominate the efficiency and accuracy of the results, therefore a well designed network is quite important on drug target path discovery mission; 2) the existing network based approaches only work on small graph, it can not handle massive data well. In the paper, we designed a novel framework of systems chemical biology based on semantic big data. In the paper, we proposed a novel drug target path discovery approach. It can identify targets associated with specific medicines (disease) and the path of relationship based on a F semantic D-T network The ranking of candidate targets is performed through an improved parallel random walk with restart algorithm. The experimental studies show that the proposed approaches can efficiently discover drug target relationship path, meanwhile, the approaches have good scalability which are suitable for big data analysis.