Instruments at the Franklin have been procured from a wide variety of different manufacturers and produce a vast range of different filetypes, reflecting the different experimental techniques that are practiced at the institute. The generated data, which is expected to reach dozens of terabytes per day by 2022, needs to be safely archived, processed automatically, and catalogued to facilitate retrieval later. The Franklin relies on both private and public cloud, combined with storage on Ceph object store, as well as dedicated software packages and webapps to accomplish these goals.
Artificial Intelligence and Informatics plays a key role in augmenting the other scientific themes at the Rosalind Franklin Institute, applying the latest methods in AI and machine learning to enhance performance in areas such as data processing and analysis. Data is critical to many areas of AI, including machine learning, and so the team is also responsible for data storage and management at the Franklin.
One of the big challenges in modern science is handling the vast quantities of data collected by state-of-the-art equipment of the type housed at the Franklin. That’s where AI and machine learning techniques come in: tasks that would take researchers months or even years to carry out manually can be automated, generating order-of-magnitude efficiencies in the processing and analysis of data. By training a machine learning algorithm to spot patterns or anomalies in these huge volumes of data, time-consuming tasks can be sped up considerably – freeing researchers to focus on what’s important.
Dr Mark Basham, Head of AI at the Franklin, says: ‘The main purpose of this theme is to augment all the other themes. There are plenty of situations now in which humans become limited in what they can do: in structural biology, for instance, the equipment we have at the Franklin is capable of producing so much raw imaging data – such as images of the internal structure of cells – that it can create bottlenecks from an analysis point of view. It’s not about removing the human being from the process – it’s about using AI and machine learning to save time for the researchers, remove bottlenecks, and highlight the things that they will be most interested in.
Structural biology is just one example, though. Our team will be working across all the scientific themes at the Franklin to add value to the work they’re doing. Researchers will be able to come to us with a problem they think can be solved with the help of AI.’
The AI and Informatics theme is also responsible for the general management of data at the Franklin, making sure any data collected on its instruments is stored safely and effectively, and made accessible to researchers for mining and processing. The theme’s methods can also be applied to areas such as manufacturing – for example, to create efficiencies in the quality assurance process.
Dr Basham, who gained a PhD in computational physics from the University of Reading and joined the Franklin from a data analysis and management role at Diamond Light Source, says: ‘We need to be careful of the hype around AI and machine learning, but there are certainly some amazingly powerful techniques available – all of which require high-quality data at a quantity to have a transformative effect. At the Franklin, the AI and Informatics theme is about exploiting cutting-edge methods and high-quality experimental data, automating the mundane to highlight the extraordinary.’
Dr Mark Basham
Head of Artificial IntelligenceView profile
Dr Mark Basham
Head of Artificial Intelligence
Dr Mark Basham is Head of AI at the Rosalind Franklin Institute, and a Research Fellow at Diamond Light Source. Mark was awarded his Physics PhD in surface science simulation from the University of Reading, he then moved to data […]
AI Masters Projects
By taking on a Rosalind Franklin Institute challenge, the students will be helping solve a complex, real-world problem faced by scientists at the Franklin. The purpose of these projects are to engage students, who are looking to embark on research careers, with the Franklin science and to allow them to build links and networks outside of their host institutions. In addition, the projects aim to strengthen the links between researchers at member universities and the Franklin.