Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

LEAD SUPERVISOR:  Prof Eric O’Neill, Department of Oncology

Co-supervisor: Prof Helen Byrne, Mathematical Institute

Commercial partner:


Pancreatic cancers remain intractable, resulting in high mortality. Thus, there is an urgent need for innovative ways to tackle this disease. Aberrant epigenetics is a key “Hallmark of cancer" that cancer cells use to drive de-differentiation of normal cells into an embryonic squamous-like state which favours uncontrolled proliferation. We recently identified the epigenetic mechanism defining these phenotypic changes and found that a combination of biologically-targeted agents (Metformin and Vitamin C) could restore epigenetic control and revert squamous pancreatic cancer cells to a more regulated differentiated state [1].  Although we observe a shift towards normal cell epigenetics, this drug combination is not fully optimised to drive the phenotypic shift. Therefore, we aim to use an innovative data-driven artificial intelligence (AI) approach developed by, based on existing algorithms[2], to delineate novel molecules that can demonstrate improved and robust re-normalisation of epigenetic status and pancreatic differentiation, in order to offer new treatments for this hitherto intractable cancer.  

Our aim is to develop mechanistic mathematical models for AI-derived molecules targeting pancreatic cancer.

The proposed project will explore the mechanism of action of molecules predicted by a AI/Machine Learning platform ( to modify cellular phenotype. This project will centre on the development of mechanistic models [3,4] to better understand how these novel agents achieve phenotypic changes through the perturbation of relevant cellular signalling networks. These molecules are likely to have multiple cellular targets, perturbing a number of signalling pathways, which may all combine to achieving phenotypic normalisation of the cell. Thus, mechanistic modelling is required to understand how such a ‘multi-intervention’ molecule functions to alter cell signalling networks. The models will then be employed to further refine the platform discovery and optimisation engine, and provide a mechanistic underpinning of data-driven drug-discovery platform to identify optimised drugs for this therapeutic indication.

[1] Eyres et al. (2021) Gastroenterology. 2021:S0016-5085(21)00682-X.

[2] Pham et al. (2021). Nat. Mach. Intell. 3, 247–257

[3] Kay et al (2017). PLoS Comp Biol. 2017; 13(2): e1005400.

[4] MacLean et al. (2015) PNAS. 2015; 112(9): 2652-2657.


Apply using course: DPhil in Oncology

MRC logo