Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Three GMS students from the WCHG recently competed in the Wellcome-Sanger Institute’s inaugural BioData Hackathon (#BioDataHack) and took home the top prize in their category.

hris Eijsbouts (2017), Chris Cole (2017), and Dr. Jonas Bovijn (2016) were part of a team of five that worked on a novel method for identifying drug targets as a part of AstraZeneca’s challenge. They will continue to develop their solution, “Topologically Informed Drug Discovery”, or TINDR, with the help of mentors at the company. 

The BioData Hackathon was hosted by the Wellcome Genome Campus in Hinxton, near Cambridge on July 2-3rd, and brought together almost 150 hackers from various areas of genetics and healthcare informatics. Teams comprised individuals of diverse skill sets from clinical medicine to statistics, computational biology, and business. Five organizations sponsored challenges and contestants were free to design innovative solutions drawing on their various expertise. Astrazeneca, a multinational pharmaceutical company with its headquarters in Cambridge, threw down the gauntlet with the broad challenge to “map drug-disease relationships using machine learning and/or AI”. The team, which also included Cambridge PhD student Timothy Jenkins, and King’s College London post-doctoral fellow Dr. Héléna Gaspar, attempted to predict potential drug targets for a particular disease based on information from protein-protein interaction networks. Relevant portions of the network were selected and fed into a convolutional Neural Network (CNN) to learn how drug targets tend to be “connected” to other proteins. This information was used to identify new proteins that had connectivity features similar to established drug targets.


The team is currently in talks with AstraZeneca to continue their work. In the meantime, they have created an R package which is still under development.