Unravelling Signalling Heterogeneity using DEEP Learning and MECHANIstic Modelling

Signalling enables cells to respond to external cues, but the inherent heterogeneity of individual cell responses,essential for multicellular organization, complicates disease treatment. Heterogeneity arises from drivers atsystem and molecular scales, intertwined through feedback loops, making quantitative understanding andprediction challenging. I will address this by pioneering transformative computational methods that predictphospho-signalling responses by integrating deep learning with mechanistic modelling to integratesystems and molecular scales.By using unbiased pattern recognition of deep learning models, I will learn cell states and simplephosphorylation rate laws. These will be combined with mechanistic models, integrating biologicalknowledge, to build simple and interpretable models that predict signalling responses from baseline omicsprofiles across distinct time-resolved and perturbational conditions. I will apply these methods to investigatedrivers of heterogeneity in receptor tyrosine kinase (RTK) and rat sarcoma (RAS) signalling, in response togrowth factors and targeted inhibitors in cancer cell lines. I will validate the approach by reprogrammingpatient-derived organoids using model-proposed inhibitor combinations.The proposed research will advance our fundamental understanding of signalling regulation and co-regulationwith cellular states. Given the vital role of RTK and RAS signalling in human health, it also holds the potentialfor translational impact. More broadly, the proposed computational methods are versatile and could be appliedto a broad range of biological and non-biological systems.