A network-based approach to drug repositioning and its applications

Drug development is still a time consuming and costly process, and the breadth of available data in this area makes it more complicated. The process of finding additional indications for existing drugs is known as Drug Repositioning (DR). DR is a way to save time and costs when compared to the de novo drug development process. Computational methods can guide wet lab experimental design by narrowing the scope of candidate targets to accelerate drug discovery and can provide supporting evidence for experimental results. Usually, the therapeutic effect of drugs occurs through their targets in the cell. Therefore, it is necessary to consider the relationship between the three concepts of drug, target, and disease together.Network modelling is one of the successful methodologies of systems biology since biological networks typically present a suitable model for relationships between different biological concepts. We tried to integrate different level and various data related to drugs, diseases and protein targets in one network model. Given the nature of existing data, the use of semi-supervised learning methods is crucial. We have developed a label propagation method to predict drug-target, drug-disease and disease-target interactions (Heter-LP) (Lotfi Shahreza et al. ۲۰۱۷), which integrates various data sources at different levels. The predicted interactions are the most prominent relationships among the millions of relationships suggested to the related researchers for further investigation. Now, we try to present some of applications of Heter-LP and its worth full results. Here its application on identifying of most probable drugs and targets of three challenged topics for drug companies (rare diseases, animal health and aging) are investigated.

کلیدواژه ها:

Semi-supervised learning ، heterogeneous networks ، systems biology ، label propagation ، Heter-LP.