EPSRC logo

Details of Grant 

EPSRC Reference: EP/V023233/1
Title: Turing AI Fellowship: clinAIcan - developing clinical applications of artificial intelligence for cancer
Principal Investigator: Yau, Professor C
Other Investigators:
Researcher Co-Investigators:
Project Partners:
AstraZeneca F. Hoffmann-La Roche (International) Hummingbird Diagnostics GmbH
Karolinska Institute Ovarian Cancer Action The Francis Crick Institute
UC Davis School of Medicine University of Birmingham University of Oxford
Department: School of Health Sciences
Organisation: University of Manchester, The
Scheme: EPSRC Fellowship - NHFP
Starts: 01 January 2021 Ends: 28 February 2022 Value (£): 1,211,857
EPSRC Research Topic Classifications:
Artificial Intelligence Statistics & Appl. Probability
EPSRC Industrial Sector Classifications:
Healthcare
Related Grants:
Panel History:
Panel DatePanel NameOutcome
06 Oct 2020 Turing AI Acceleration Fellowship Interview Panel C Announced
Summary on Grant Application Form
Cancer is an evolving disease. No two cancers are ever exactly the same, no two cancer cells are even likely to be the same at the molecular level. 'Omics technologies allow us to measure the molecular activity of cancer to determine how it changes as the cancer develops. However, this is difficult to do with real patients as we only ever have access to a cancer only when it has developed and, once diagnosed, the cancer will be treated, perturbing it from its natural untreated trajectory. It is never possible to directly measure what the cancer was like before diagnosis, in its earliest stages of development, nor what would happen to the cancer if it was untreated or treated in a different way.

In this project, we aim to develop artificial intelligence (AI) technologies that will allow us to describe how cancers evolve at the molecular level. We exploit the fact that cancer, whilst never exactly identical, they often share similar development trajectories which we can learn by collating information from across deep high-resolution molecular profiles of many cancers. As patients will never be diagnosed at exactly the same point of disease progression, each patient therefore occupies a unique point on the common disease trajectory. A collection of patients therefore should represent a continuum along these trajectories. AI can therefore help us to understand how cancers change over time by leveraging information from across many patients without us having to actually follow and observe cancers as they develop in individual patients.

In this research, we will develop models of cancer progression using a rich-body of modern AI techniques that we will make novel adaptations to enable their application to 'omics data. We will then use these technologies and work with a range of academic, industry and charity partners to identify prototypic applications of this research that might including helping to improve treatment decision making for cancer, provide patients with more detailed information about their disease and treatment options in an accessible way and to improve the efficiency and efficacy of cancer clinical trials.

Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Summary
Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:  
Further Information:  
Organisation Website: http://www.man.ac.uk