Application of data science, genomics and machine learning

Rapid advances in proteomics, metabolomics, transcriptomics, genomics artificial intelligence and machine learning are already driving forward vasculitis research and offer huge potential. Areas of current and future interest in the Centre include:

• Analysis of EUVAS and UK & Ireland Vasculitis (UKIVAS) patient registries and linked datasets, using bioinformatic and machine learning approaches (with Data Sciences).
• Contribution to multicentre GWAS and Immunochip studies in ANCA vasculitis as part of the European Vasculitis Genetics Consortium, and the largest study in Takayasu arteritis led by our collaborators at the University of Pittsburgh.
• The role of adenosine deaminase 2 in monocyte and endothelial homeostasis and molecular mechanisms surrounding vascular injury in the ADA2 deficiency syndrome.
• Planning of the largest matched transcriptomic and proteomic analysis in large vessel vasculitis, in collaboration with international colleagues and the Sanger Centre.
• In collaboration with Faculty of Bioengineering, application of AI and machine learning techniques to interpret early changes in clinical signs and biomarkers in hyperinflammation syndromes, aiming to identify those at high risk and to optimise treatments protocols and clinical outcomes.