Astronomy And Cancer Research Bond Over Big Data

Astronomy and the ongoing fight against cancer may appear to have very little in common at first glance, however, the two have been joined together by the algorithms that read big data.

Between all of us on this planet, we create 2.5 quintillion bytes of data, in fact 90% of the world’s data has been created within the last two years alone. This dramatic increase in the amount of data we produce has in turn driven a revolution in even smarter computers and devices that are able to make sense of all of that information. The medical sector is just one sector that is benefitting from the closer relationship between data and machines.

The unique collaboration that has formed began at a cross disciplinary meeting in Cambridge to discuss data management. Here Dr Nicholas Walton an astronomer met James Brenton from the Cancer Research UK Cambridge institute. From here the experts drew upon similarities, Professor Carlos Caldas explains: “Astronomers are looking at pictures of the sky, but they can’t sift through millions of pictures by hand, so they use imaging algorithms that can analyse and classify objects. We obtain images from humans in the form of scans. Could we deploy the same algorithms to read that data?”

With the answer being yes, the algorithm has been advocating the study of cancer ever since. By using the astronomy algorithm, it is possible to automatically classify hundreds of thousands of cells, identify how cells relate to each other and precisely count them. This in turn speeds up diagnosis and allows the examining of new information that in the past may have been overlooked.

Scientists at Cancer Research have also announced that they have made a breakthrough in the way that they read breast cancer cells, it means that they are now able to create a 3D map that links the shape of the breast cancer cells to genes turning in and off, matching it to real disease outcomes.

Leave a Reply

Your email address will not be published. Required fields are marked *