We are delighted to sponsor the 2026 Green Templeton lecture series – Innovation and the Future of Health: Find, Fail, Fly – which sets the tone for a thought provoking programme exploring the future of health innovation. The first session, held on 12 February at the EP Abraham Lecture Theatre, spotlighted one of the most ambitious frontiers in modern healthcare: the use of AI supercomputing to accelerate cancer vaccine development.
The lecture, delivered by Lennard Lee (Research Fellow, Green Templeton and Associate Professor, Nuffield Department of Medicine;) and Anthony Hsieh (Chief Science Lead, UK Cancer Vaccine AI Scientist and Supercomputing Project), examined whether we have reached a true global AI inflection point – and what that means for population health.
Their central argument was clear: while AI already shapes everyday life, its greatest public benefit may lie in its ability to unlock faster, more precise, and more scalable approaches to disease prevention and treatment. Their Oxford based project aims to leverage sovereign AI infrastructure to transform cancer vaccine development through ultra high speed analysis of tumour genomes.
A key focus was the complexity of cancer immunity. Tumour cells present unique peptide-HLA combinations (neoepitopes) that can be used to train the immune system to deliver highly targeted responses. Lennard’s and Anthony’s project employs AI supercomputers and a closed-loop design to rapidly and precisely select the appropriate peptide-HLA pairs. Their model mirrors the structure of generative pre-trained transformers (GPT), such as ChatGPT, and requires a high number of tumour cell genome and health outcomes data for accurate training.
An important theme was the complexity of cancer immunity. Tumours display distinctive peptide-HLA combinations, known as neoepitopes, which offer an opportunity to guide the immune system towards highly specific anti-cancer actions. Lennard and Anthony’s initiative harnesses AI-powered supercomputers alongside a closed-loop system to identify the most suitable peptide-HLA pairs. Their model mirrors the structure of generative pre-trained transformers like ChatGPT and relies on extensive tumour genome sequencing and patient outcome data to ensure robust model training.
The importance of speed in cancer vaccine development was highlighted as a key issue. To address this, the team is building an “engine” for iterative vaccine design - mirroring the architecture of generative AI models which will enable rapid identification of immunogenic neoepitopes and accelerate vaccine production.
The session sparked lively discussion across the multidisciplinary audience of clinicians, researchers, policy experts, students, and innovators - demonstrating the broad relevance of AI driven biomedical innovation.
Read the full write up of lecture 1: A new horizon in AI powered cancer vaccine development.
We’ll bring readers an update on the 2026 series of lectures as it continues.
Our content explained
Every piece of content we create is correct on the date it’s published but please don’t rely on it as legal advice. If you’d like to speak to us about your own legal requirements, please contact one of our expert lawyers.