Cancer Grand Challenges Researchers to Put AI Co-Scientists to the Test in Cancer Research

• Three Cancer Grand Challenge teams have been selected to test AI co-scientists as part of AURORA, a new $10M program designed to help scientists speed up cancer discovery.
• Developed in Marinka Zitnik’s lab at Harvard Medical School with funding from Cancer Research UK through Cancer Grand Challenges, the agentic AI system will act as a research partner, helping scientists to navigate vast amounts of data and evidence, generate new ideas, and design and prioritize experiments. The researchers will remain responsible for scientific judgement and decision making.
• The selected teams will explore whether AI can help scientists in tackling some of the toughest challenges in cancer research, including developing next-generation CAR-T therapies, understanding how cancers initiate and evolve, and how tumors interact with the immune system.

BOSTON--(BUSINESS WIRE)--Cancer Grand Challenges today announced the first cohort of international teams selected to join AURORA, a pioneering project that aims to help scientists make faster progress against cancer’s toughest challenges using AI.

AURORA will test how AI co-scientists can work alongside researchers, helping them analyse vast amounts of data, generate new ideas and identify the most promising experiments at a speed and scale far beyond what is currently achievable through human capability alone. By combining AI with human expertise and experimental evidence, the program aims to accelerate scientific discovery while keeping researchers firmly at the centre of every decision.

Cancer Grand Challenges, the global research initiative founded by Cancer Research UK and the National Cancer Institute, brings together international teams of researchers to take on some of the toughest challenges in cancer. Following a competitive call inviting its funded teams to submit proposals for how agentic AI could accelerate progress in their areas of research, Cancer Grand Challenges is providing $4 million in funding to support three selected AURORA pioneer teams. The teams will apply AI co-scientists to build on research already underway, including developing next-generation CAR-T therapies, understanding the biological mechanisms that drive cancer, and learning how tumors interact with the immune system.

In March 2026, the initiative awarded $6 million in funding from Cancer Research UK to a team led by Marinka Zitnik, Associate Professor of Biomedical Informatics in the Blavatnik Institute at Harvard Medical School, to build, test and refine a core AI module. The technology will now be evaluated and used in real-world cancer research to help scientists make faster progress against some of the toughest challenges in the field. Cancer Grand Challenges has committed a total funding of $624 million, across 21 international teams tackling 18 challenges worldwide since its launch in 2016.

Marinka Zitnik, PhD, Associate Professor in the Department of Biomedical Informatics at Harvard Medical School, said:

“A key challenge for AI in science is understanding how it can best support researchers working on real-world problems. With AURORA, we're putting AI co-scientists into active cancer research programmes and rigorously evaluating its impact.

“By testing the system against real scientific questions and experimental evidence, we hope to build a trusted, rigorously evaluated tool that helps researchers accelerate discovery and uncover new insights into cancer research.”

In AURORA, researchers remain firmly in control, setting the scientific direction, evaluating the AI's recommendations and deciding which experiments to carry forward. As new findings emerge, the AI co-scientist learns from the results, helping scientists refine their understanding and accelerate the next stage of discovery. The AI co-scientists may also recommend not pursuing a hypothesis where the anticipated scientific value is limited, helping researchers focus resources where they are most likely to advance understanding. AURORA was built around an ecosystem of scientific tools, including ToolUniverse, developed at Harvard University.

Professor Charles Swanton, Chair of the Scientific Committee, Cancer Grand Challenges, said:

“Cancer presents scientists with an immense landscape of biological complexity. Agentic AI could help researchers navigate that complexity by bringing together evidence, exploring a wider range of possible explanations and identifying connections that might otherwise be difficult to see.

“Crucially, this is about combining the capabilities of AI with human scientific expertise. Scientists will remain at the centre of decision-making, assessing AI-generated hypotheses and determining what should be tested. Together, that could open up new avenues for understanding, preventing and treating cancer.”

AURORA is designed to support scientists throughout the research process. As an agentic AI system, it can plan and carry out a series of tasks towards a research goal, adapting its approach as it goes, under human oversight. It draws on scientific literature, experimental data, curated knowledge bases and specialised research tools to help scientists evaluate evidence, explore competing explanations and prioritise experiments to test new ideas.

The three AURORA pioneer teams will test the AI co-scientists across different areas of cancer research:

The NexTGen AURORA team, with Nicky McGranahan at University College London (UCL), will use AI to identify and prioritize promising new strategies for CAR-T therapy, exploring new targets and antigen combinations as well as ways to overcome resistance and engineer more effective treatments.

The PROMINENT AURORA team, with Nuria Lopez-Bigas at the Institute for Research in Biomedicine (IRB Barcelona), will investigate how tumor-promoting exposures contribute to cancer development, using AI to understand what makes otherwise normal cells vulnerable to becoming cancerous.

The MATCHMAKERS AURORA team, with Sergio Quezada and Welles Robinson at UCL, will bring together interacting AI co-scientists to identify the tumor antigens most likely to provoke an immune response and the T-cell states best equipped to recognize and attack tumors.

Cancer Grand Challenges selected the three AURORA pioneer teams from a strong pool of high-quality applications from Cancer Grand Challenge teams, following a rigorous scientific review by members of the Cancer Grand Challenges Scientific Committee and external AI experts. The review assessed each project proposal for scientific importance, fit with the AURORA AI co-scientist objectives, quality of human-AI interaction and route to experimental or clinical validation.

The three pioneer teams form the first major testing ground for AURORA. Feedback from their experiments will be fed into the shared AI system, helping to improve how it works and how its performance is assessed, while advancing research into cancer development, treatment and immune response. If successful, this could pave the way for further collaborations between AURORA and Cancer Grand Challenges teams.

The AURORA project is funded by Cancer Research UK through Cancer Grand Challenges.

Notes to editors

About Cancer Grand Challenges

Co-founded in 2020 by two of the largest funders of cancer research in the world: Cancer Research UK and the National Cancer Institute, Cancer Grand Challenges supports a global community of diverse, world-class research teams to come together, think differently and take on some of cancer’s toughest challenges. These are the obstacles that continue to impede progress and no one scientist, institution or country will be able to solve them alone. With awards of up to $34M, Cancer Grand Challenges teams are empowered to rise above the traditional boundaries of geography and discipline to make the progress against cancer we urgently need.

About Harvard Medical School

Harvard Medical School has more than 12,000 faculty working in the 11 basic and social science departments in the Blavatnik Institute and at the 15 Harvard-affiliated teaching hospitals and research institutes: Baker Center for Children and Families, Beth Israel Deaconess Medical Center, Boston Children’s Hospital, Brigham and Women’s Hospital, Cambridge Health Alliance, Dana-Farber Cancer Institute, Harvard Pilgrim Health Care Institute, Hebrew SeniorLife, Joslin Diabetes Center, Massachusetts Eye and Ear/Schepens Eye Research Institute, Massachusetts General Hospital, McLean Hospital, Mount Auburn Hospital, Spaulding Rehabilitation Hospital, and VA Boston Healthcare System.

AURORA projects

NexTGen — NexTGen AURORA AI Pioneer teams

Team: Nicholas (Nicky) McGranahan, University College London, Karin Straathof, Martin Pule and Alex Coulton, University College London, Catherine Bollard, Children’s National Hospital in Washington, D.C. and Robbie Majner, Dana-Farber Cancer Institute
Funding: $1.34 million

About the project: NexTGen is addressing the challenge of developing new therapies for children with solid tumors, focusing on next-generation engineered T-cell therapies. NexTGen will use AURORA to explore and prioritize next-generation CAR-T therapeutic strategies, including potential targets, antigen combinations, tumor microenvironment resistance mechanisms and engineering approaches. AI will analyze multiomic datasets, compare competing hypotheses and propose experiments, refining its reasoning through experimental feedback. Promising strategies will be tested using cell-killing assays, tumor-on-chip models and in vivo studies. NexTGen is funded by Cancer Research UK, the National Cancer Institute and The Mark Foundation for Cancer Research through Cancer Grand Challenges.

PROMINENT — Discovery of Tumor-Promoter Mechanisms

Team: Nuria Lopez-Bigas, Institute for Research in Biomedicine Barcelona and Emma Lundberg, Stanford University
Funding: $1.31 million

About the project: PROMINENT is investigating how cells and tissues can remain normal despite carrying cancer-driving mutations, and what causes them to transition to cancer. PROMINENT will use AURORA to identify mutations and contextual factors that enable tumor-promoting exposures to drive cancer development. AI will integrate scientific literature and large-scale datasets to generate and prioritize hypotheses for experimental testing, including investigating how sex, age and biological context influence cancer development. The project will use a temporal “time machine” validation approach to examine these mechanisms over time. PROMINENT is funded by Cancer Research UK, the National Cancer Institute and the Scientific Foundation of the Spanish Association Against Cancer through Cancer Grand Challenges.

MATCHMAKERS — Tumor Immunogenicity and T-cell Reactivity

Team: Sergio Quezada and Welles Robinson, University College London, and Peter Bruno, University of California, San Francisco
Funding: $1.34 million

About the project: MATCHMAKERS is working to decipher how T-cell receptors recognize cancer, with the aim of enabling more personalized immunotherapies. MATCHMAKERS will develop interacting AI co-scientists to identify the tumor antigens most likely to trigger an immune response and the T-cell states best able to recognize and attack tumors. The AI co-scientists will generate and prioritize hypotheses, test them experimentally and continuously refine their predictions using experimental feedback. MATCHMAKERS is funded by Cancer Research UK, the National Cancer Institute and The Mark Foundation for Cancer Research through Cancer Grand Challenges

The three projects will receive a combined $4 million in funding.