Research Consortium Harnesses AI and Spatial Biology to Advance Cancer Discovery

AI has the potential to transform cancer care, yet progress remains constrained by fragmented, inaccessible data that hinder advances in early diagnosis and precision therapy. Unlocking patterns missed by conventional methods requires large, well-annotated datasets integrating molecular, imaging, and spatial data. To close this gap, a new collaboration aims to build one of the world’s most comprehensive multimodal cancer datasets by combining spatial profiling with artificial intelligence (AI).

PharosAI, a research consortium uniting King’s College London, Queen Mary University of London, Guy’s and St Thomas’ NHS Foundation Trust and Barts Health NHS Trust, will deploy the 10x Genomics Xenium spatial platform to create AI-ready cancer datasets and an integrated suite of analytical tools. The initiative will initially focus on breast cancer before expanding to lung and pancreatic cancers, with plans to incorporate thousands of clinically annotated tissue samples.

The program will convert decades of archived NHS cancer samples into high-resolution, spatially resolved datasets while linking genomic, transcriptomic, imaging and spatial biology data to custom AI models. Xenium was selected to support reproducible results across thousands of archival tissues, aided by a high-throughput workflow and the ability to generate custom-designed gene panels in collaboration with 10x Genomics teams. These capabilities will enable assays aligned with molecular features most relevant to specific cancers.

Backed by £18.9 million from the UK Government’s Research Ventures Catalyst, with additional support from charities and industry partners, PharosAI will assemble large-scale datasets, computational models and analytical tools intended to accelerate earlier diagnosis, enable precision therapies and speed discovery of new treatments. The consortium will make datasets securely available to a broad community of researchers and innovators, with the program running through 2027.

“Turning biological insight into impact requires scaled generation of consistent, high-quality data,” said Serge Saxonov, Chief Executive Officer and Co-founder of 10x Genomics. “With Xenium, PharosAI can convert decades of archived NHS cancer samples into robust, high-quality, spatially resolved datasets. This foundation is what makes it possible to move earlier, more precisely and with greater confidence toward the next generation of breakthroughs in cancer research.”

Related Links
10x Genomics, Inc. 
PharosAI