Zegami, the data visualization company helping organizations unlock their data potential, has been collaborating with MRC Weatherall Institute for Molecular Medicines (MRC WIMM) Centre for Computational Biology to help clean its data and assist with the training of its machine learning models, specifically around developing a better understanding of which proteins in genes bind, and where they do this in the genome.  All of this is key in the development of personalized gene therapy and medicine.

The MRC Weatherall Institute of Molecular Medicine at the University of Oxford was founded in 1989 to foster research in molecular and cell biology, with the aim of improving human health. Through its excellent basic and applied research, it has become a leading centre for translational medicine. Its research has resulted in improved understanding, diagnosis and treatment of a wide range of human diseases.

Zegami, spun out of the University in 2015, is supporting scientists in this renowned institute by speeding up the process of training machine learning tools to find the locations of important proteins that bind to the human genome that turn genes on and off. When these genes are incorrectly activated/deactivated they can cause disease, so accurately finding their control mechanisms is vital. Existing software often gets this wrong but using machine learning the Taylor and Hughes group have trained computers to ‘see’ these signals to get a more accurate catalogues of their positions. 

Jim Hughes, Professor of Gene Regulation at the MRC Weatherall Institute of Molecular Medicine at Oxford University, said:

“Our ability to sequence and reconstruct entire genomes has transformed our approach to research and medicine. We can now investigate, on the scale of the whole genome, how and in what situations, parts of that blueprint are used. This is enhancing our understanding of how our genome works in health and disease, but it also means we are generating huge amounts of data. This is an exciting opportunity for us, but also a problem in how best to ensure these data are clean, and accurate so that we can train machine learning methods effectively and efficiently to create new insights. Zegami allows us to visualize, sort, filter and label vast amounts of biological data for use in training machine learning models, solving a key challenge in this field. Zegami also allows us to easily publish all the data for scientists to understand how the models were created to help address the machine learning black box problem.”

Steve Taylor, Chief Scientific Officer at Zegami and co-leader of the Centre of Computational Biology at the MRC Weatherall Institute of Molecular Medicine, added:

“We are delighted to be working with the MRC WIMM Centre for Computational Biology and supporting them in their incredibly important work. The era of big data is delivering vast amounts of information for health practitioners, patients, researchers, and policy makers and data visualization has a huge role to play in terms of generating insight and creating actionable, on-demand knowledge for decision makers.”