Isambard-AI, by Bristol Centre for Supercomputing (BriCS), at University of Bristol, is set to become the UK’s fastest and most powerful supercomputer following build completion in Summer 2025. Purpose-built for AI research, it is designed to provide open-source intelligence and is already transforming research and driving AI-led breakthroughs in critical areas like automated drug discovery and climate research.
Professor Simon McIntosh-Smith, Director of BriCS and professor in high-performance computing at University of Bristol, described the supercomputer as ‘potentially world-changing’.
Speaking to BBC Radio Bristol, Professor McIntosh-Smith said: “We’ve actually got a little bit of the system already up and running, we already have people using it to do things like look for new drugs and new vaccines to treat people.”
He added that the team are using the computer to develop treatments for heart disease, emphysema and different types of cancers.
“It can do a lot of the grunt work, a lot of the things that would just be beyond humans, simulating the way that drugs actually work inside the body, at the molecular level.
“Where artificial intelligence comes into it, is rather than trying all possible combinations of things it actually tries a whole bunch of random possibilities, looks at which are most promising, and then hones in on those.
“We could be saving millions of lives with some of the things that we’re talking about here and I find that tremendously exciting – it’s brilliant to be able to actually be doing it right here in Bristol.”
Elizabeth Blackwell Institute supports a growing AI in Health research community at Bristol. The 2024 AI in Health award 2024 was designed to help colleagues make their research AI-ready. One project ‘Assessment of the integration of molecular docking with AI-based design of personalised vaccines’ led by Imre Berger and Iart Luca Shytaj builds on their online AI-based platform Custommune capable of designing personalised epitopes for preventive and therapeutic vaccines.
Luca Shytaj, Senior Lecturer in the School of Cellular and Molecular Medicine said: “Support from Elizabeth Blackwell Institute enabled us to explore integrating AI into a software we developed to predict how the immune system recognizes external threats, in particular viruses, and to test these predictions in the laboratory. We focused on HIV and cytomegalovirus (CMV), which cause lifelong infections for which no approved vaccines exist. Developing personalised vaccines (tailored to an individual’s immune system) could help address this challenge.
“While our AI predictions were not always as precise as the current gold standard, they successfully identified two new potential vaccine targets for CMV. This suggests that AI can offer a fresh perspective on immune recognition of viruses, uncovering new insights that could aid personalised vaccine development.”
Professor Pat Kehoe, Director of Elizabeth Blackwell Institute said: “Harnessing AI for healthcare improvement has vast potential, extending beyond vaccine development to other forms of drug target identification and development; more optimal use of harnessing important clinical information from patient registries; and how AI can be integrated to bring efficiencies and improved diagnoses into healthcare settings. We will be also supporting researchers to look at how with the development of AI it does not give rise to any unintended forms of marginalisation and health inequalities.”
Upcoming AI in Health workshops:
Artificial intelligence in Health: socio-digital transformation, ethics and governance
Tuesday 6 May 2025 11:30 – 13:30, Life Sciences Building, Tyndall Avenue, BS8 1TQ
More info and book
Artificial intelligence in Health: genomics, protein design and drug discovery
Thursday, 22 May 2025 11:30 – 13:30, Life Sciences Building, Tyndall Avenue, BS8 1TQ
More info and book