Highlighting extraordinary discoveries in our science is a key aim for the Rosalind Franklin Institute’s Artificial Intelligence theme. Our AI team along with colleagues from University of Oxford and UCL have now received funding that will help them just that – a new grant from the Alfred P. Sloan Foundation will help the team build tools designed to help highlight interesting proteins within cells.
Imaging techniques within Structural Biology are now capable of capturing proteins in action in the cell. This ground-breaking work means structural biologists are now capturing huge amounts of data, which cannot be processed by the scientists alone.
Colleagues in a wide range of fields face similar problems with large datasets. The Sloan Foundation grant will bring together researchers from structural biology, astrophysics and ecology to build systems which will find unusual and interesting discoveries.
Dr Mark Basham, the Franklin’s Artificial Intelligence and Informatics Science Director, said: “We are very excited to be moving forward with this project. It promises to be an interesting project working with researchers from such a wide range of backgrounds, and harnessing the best of machine learning and human classification.”
These discoveries will then be reviewed by citizen science participants via the Zooniverse platform, creating a dynamic system which draws on insights from machine learning and humans. This will give the researchers the most interesting results.
Professor Chris Lintott is Professor of Astrophysics at the University of Oxford and project leader, he hopes to utilise the system to find unusual and interesting objects in large scale astronomical surveys.
He explained: “We’ve learnt how serendipitous discoveries can drive science forward from previous astronomical Zooniverse projects, ranging from Galaxy Zoo’s Green Peas to Boyajian’s Star, ‘the most interesting star in the Milky Way’, even if it turns out not to host an alien megastructure. With new projects such as the Vera Rubin Observatory’s LSST survey nearly ready to provide an unprecedented flood of information, astronomers around the world are honing their techniques for getting the most out of such large datasets – but the problem of preparing for surprise has been neglected.”
Professor Kate Jones’ team at UCL will look for surprises in audio recordings from ecological monitoring projects, testing whether identifying rare events – such as gunshots – might contribute to assessments of the health of an ecosystem.