Machine learning for drug target identification

Traditionally, in drug discovery, target identification to develop novel agents for any given disease is carried out on a case-by-case basis. In this model, individual scientists act as project champions for targets based on available literature and local expertise. This approach has weaknesses n that it is ad-hoc in nature and it is almost impossible to maintain an overview over an increasingly vast scientific literature. There are efforts underway in the pharmaceutical industry to apply a more systemic approach (for instance, OpenTargets initiative). This PhD iCASE studentship will focus on the development of an innovative integrated resource, which uses machine learning to facilitate a systematic or genome scale ranking of potential targets, and will build on the School of Medicine expertise in the areas of type 2 diabetes and metabolic syndrome.
Project provides training in Interdisciplinary & Quantitative Skills.