Research

Our Cellular and Molecular Systems Medicine theme focuses on the prediction and use of natural or engineered biological machinery to address key challenges in health. Recent advances in this space include protein drug design using generative AI, cell therapies involving genetic modification of immune cells to destroy pathogens, and precision gene therapies.

Cellular and Molecular Systems Medicine lies at the interface of AI, systems modelling, data science, genomics, and molecular biology. It benefits from advances in computing, UK AI capacity, and falling costs for DNA sequencing & synthesis. In this realm, the synergy between AI, machine learning, and mechanistic models offers a particularly powerful toolkit for unravelling the complexities of biological systems and driving innovation. By harnessing the complementary strengths of these approaches, research in this space can accelerate the pace of discovery and translation, ultimately revolutionizing the practice of medicine and improving patient outcomes.

Projects in this theme aim to elucidate biological mechanisms of disease, devise therapeutic strategies, or predict treatment responses. The supervisory pool comprises expertise in AI, biomedicine, engineering biology, chemistry, mathematics, and physics. The theme benefits from close links with the University of Edinburgh Centre for Engineering Biology and the Edinburgh Genome Foundry, as well as with NHS Scotland and industry partners.

The Biomedical & Health Informatics theme has broad application from molecular to population level, focusing on signal processing and statistical machine learning applied in healthcare. There is scope within this theme both for methodological development (e.g. new data analytics and information processing methods e.g. time-series analysis and signal processing, to developing novel machine learning methods which can be generic/validated in clinical datasets), and also applied work focusing on mining (large-scale) clinical datasets.

Translation of the developed approaches into real-world use requires explainable models that can deal with mixed type variables (continuous, ordinal, categorical) present in clinical data, and we would encourage ultimately the development of tools (e.g. embedding models into apps or websites) that can be readily used. PhD students will be uniquely positioned to leverage on accessing large-scale clinical datasets for research via trusted research environments (known as safe havens in Scotland). The University of Edinburgh is uniquely placed to explore translating research outputs and embedding them into clinical practice with NHS/clinical colleagues co-located with academic researchers facilitating inter-disciplinary working in a rich collaborative environment. Example research areas include mining different types of physiological signals such as electrocardiogram, electroencephalogram etc.; mining data from ubiquitous devices such as smartphones and (wearable) sensors for healthcare applications; tracking disease-specific and multi-morbidity trajectories from large scale electronic health records; facilitating diagnosis via designing clinical decision support tools mining multimodal data including self-reports, health records, and assay results; disease risk prediction modeling; and synthetic data generation.

Projects in this theme will address these challenges by developing and applying methods which are directly motivated by the complex medical datasets available within each specific application.

The genome contains the complete set of DNA that provides instructions for cells and tissues to develop and function. Genomic medicine integrates insights from the genome with information about a person’s health to design and apply improved diagnostic tools and treatments, as an essential component for personalised medicine. Research in genomic medicine goes beyond identification of risk factors and aims at pinpointing underlying causal mechanisms, often at various biological scales. 

Mathematics, statistics and AI/ML methodologies play a crucial role in deciphering, extracting knowledge and prioritising information from high-throughput and high-dimensional molecular ‘omics data. The technology in this space has been developing with immense speed over the past decade and continues to do so, together with major AI/ML methodological developments and opportunities, within both academia and industry. 

The UK continues to be a world-leader in genomic medicine, having generated multiple publicly available biobank-scale databases such as the UK Biobank and Generation Scotland. The School of Informatics has close links and multiple ongoing collaborations with the Institute of Genetics and Cancer, home to the MRC Human Genetics Unit (HGU), Edinburgh Centre for Genomic and Experimental Medicine (CGEM) and the Edinburgh Cancer Research Centre (ECRC).

This research theme is targeted at arguably the most widely used general class of data in medicine, whereby devices capture images of the human body to aid diagnosis, understanding of disease pathophysiology and prediction of disease evolution. It is a hallmark modality for clinical decision making. With AI we see a radical shift in how data originating from imaging devices are analysed with notable penetration of AI into the market (e.g. in 2023, 396 of the 520 FDA approved AI medical algorithms were in radiology). Key challenges remain in generalisation, fairness, and multi-modal learning with considerable activity in this field also heavily influenced by foundational models also including vision-language models.  

This theme benefits by an ever-growing ecosystem in Edinburgh and Scotland. For example, Edinburgh is home to CHAI – EPSRC AI Hub for Causality in Healthcare AI with Real Data aiming to see how causality can help address questions of generalisation and fairness. There is also large pull from large scale imaging research groupings, for example, Edinburgh Imaging is the University’s academic hub and expertise with respect to imaging/analysis/experiments and facilities and SINAPSE is a Scottish wide network of imaging scientists both clinical, technical and academic.  

Projects in this theme will aim to address these challenges by devising new theoretically grounded but applicable solutions that can scale to address ever pressing needs in interpreting and understanding medical images.