PharosAI awarded funding to explore AI ‘digital twins’ of human tissue

The project, called DESTINY, will investigate whether AI can predict molecular information that would otherwise require costly and time-consuming tests. The longer-term aim is to create ‘digital twins’ of human tissue: digital representations that capture its different biological characteristics.

If successful, this approach could help researchers better understand cancer, discover new drugs and develop more personalised approaches to diagnosis and treatment.

The funding will support an initial feasibility study to assess whether a larger project is technically and commercially viable. Successful projects from this phase of Innovate UK’s Frontier AI Discovery competition will be eligible to apply for up to £10 million in further funding.

PharosAI is one of the UK’s most ambitious programmes in cancer AI, backed by over £40 million in public and private investment. Bringing together large-scale, multimodal cancer data and advanced AI models, PharosAI aims to position the country as a global leader in this rapidly evolving field.

Building a fuller picture of human tissue

Understanding human tissue involves combining different types of information, including microscope images, DNA sequences, measurements of gene activity and proteins, and patients’ clinical records. AI models that learn from these complementary sources could reveal biological information that would be difficult to obtain from any one source alone.

DESTINY will build on the data and tissue resources brought together through PharosAI and its partners’ biobanks.

Professor Louise Jones, Chief Scientific Officer of PharosAI and Professor of Breast Pathology at Queen Mary University of London, said:

“DESTINY builds on PharosAI’s rich multimodal data spanning digital pathology, spatial transcriptomics, whole genome sequencing and proteomics to develop advanced AI models that can predict biological information from routine tissue samples. These digital twins of human tissue could enrich and expand the datasets available for research and, ultimately, transform how molecular analysis is carried out in clinical settings.”

Connecting data across institutional boundaries

Biomedical data is expensive to generate and often held separately by different institutions. Bringing it together for research can be challenging because of privacy, security and governance requirements, limiting the scale and diversity of data available to develop AI models.

DESTINY will use an approach called ‘federated learning’, which enables AI models to learn from data held by different organisations without bringing the data itself into one central location. So far, its use with complex combinations of biological and medical data remains less extensively explored than other approaches.

DESTINY will develop advanced AI models and federated learning methods designed to learn from larger, more diverse datasets across these organisations. The team will test whether these approaches can predict molecular information that is difficult or expensive to measure directly, using routinely collected tissue data. In the long term, the team aims to use these models to create ‘digital twins’ – digital representations of human tissue that predict information about its biological characteristics.

Professor Anita Grigoriadis, Chief Executive Officer of PharosAI and Professor of Molecular and Digital Pathology at King’s College London, said:

“DESTINY is about finding ways to make better use of the vast amounts of biomedical data already being generated across the NHS and research institutions. By combining different types of information and enabling AI models to learn securely across organisations, we hope to build more detailed digital representations of human tissue and predict important biological information.”

Professor Sir Mark Caulfield, Vice-Principal for Health at Queen Mary University of London, said:

“Queen Mary is delighted to participate in the DESTINY study where the PharosAI team will explore whether AI can predict valuable biological information from tissue samples. This could ultimately improve cancer diagnosis and treatment. Our Queen Mary team will bring expertise in cancer research and the evaluation of novel molecular signatures through these novel approaches.”

The award comes from Innovate UK’s Frontier AI Discovery competition, within its AI-Enabled Health and Life Sciences theme. Innovate UK is the UK’s national innovation agency, operating as part of UK Research and Innovation (UKRI). The project will be supported by Flower Labs, an AI company, and Michael Roberts, Professor of Applied AI at the University of Cambridge.

PharosAI is seeking collaborators developing new cancer treatments to explore how AI could support their research and development. For further information, please contact Dr Lucie Burgess, Chief Operating Officer/Chief Commercial Officer of PharosAI.