IP Review Winter 2019/20

4 technology to analyse and predict the molecules that could potentially bind to a particular glycoprotein in order to find a treatment for Ebola virus infections that had caused the death of over 11,000 people in Africa and other parts of the world. More recently, Merck has been using AtomNet to scan its existing medicines in order to identify any opportunities to re-purpose them to fight existing or upcoming diseases. It is hoped that AI technology could deliver benefits in areas of drug discovery that typically attract less funding. Big pharmaceutical companies are focused on finding a cure for the most prevalent and debilitating diseases, such as cancer and Alzheimer’s, and this is unlikely to change. Growing use of AI in identifying re-purposing opportunities could help to find cures for other diseases that affect smaller sub- groups of the population or people in countries where funding for drug discovery programmes is in short supply. Pharnext is an example of a company deploying machine learning to identify compounds for the treatment of rare disorders, and it currently has a compound going through clinical trials for the treatment of a rare neurodegenerative condition called Charcot-Marie-Tooth disease. As the original compound has already been shown to be safe, the re-purposed version can make it to market more quickly as certain aspects of the clinical trials are not needed. Designing a new drug candidate Although the design of a new drug candidate using AI was considered to be possible, it is only recently that it has been shown that AI can be used to design a new molecule from scratch and which has been validated in vitro and in vivo . For example, the use of generative tensorial reinforcement learning (GENTRL) has been shown to be useful in designing novel inhibitors of the discoidin domain receptor 1 (DDR1), a kinase target associated with fibrosis. It took 23 days to identify six lead candidates. The candidates were then synthesised and one compound tested in a rodent model. In less than two months a new small molecule DDR1 inhibitor was designed using AI, synthesised and validated in an animal model. The ability to design new drug candidates using AI is now a reality and, hopefully, will lead to significant improvements in drug discovery and healthcare. From diagnostics to precision medicine Another key area of opportunity for AI systems is precision medicine. Despite innovation activity in this area being slow to gather pace initially, the application of AI and machine learning technologies has opened an exciting field of drug discovery and development. This upturn in activity has been fuelled by the recent explosion in the volume of patient data that is available in a digital format – everything from genetic data to patients’ health records, lifestyle factors and sensor data from wearable devices. AI-based diagnostic tools are able to analyse and process this data in order to design treatments for individual patients, depending on the presence of various biomarkers and other predispositions. One notable example of success is an AI- based eye-imaging tool, which is widely used in clinical practice to diagnose diabetic retinopathy. Whilst diagnostic applications of AI are a major step forward, use of the technology in the development of patient-tailored treatments for specific diseases is still a work in progress. In the US, a team of research scientists and biologists led by haematologist, Dr Pamela Becker, Professor of Medicine at the University of Washington IP review winter 2019/20