I am interested in promoting data deposition in public libraries, such as GEO, in enabling findable datasets, focusing on improving the quality and richness of clinical data, data standards and metadata. My particular areas of interest are within IMIDs (immune-mediated inflammatory diseases, such as rheumatoid arthritis, psoriasis and Sjögren’s syndrome) and using clinical data with omics data in machine learning analyses.
I am a data scientist and researcher in the Centre for Translational Bioinformatics at Queen Mary University London. Part of my work is as a data manager using TranSMART, an open-sourced, web-based data warehouse for structured data from clinical trials and experimental medical studies, and as a repository for curated public data. The types of data stored are clinical data and omics. I support three projects, all in the IMID space (IMID-Bio UK, CLUSTER and NECESSITY), by curating and harmonising data across the different cohorts and the projects. Recently, I have been using machine learning techniques with these and public IMID datasets to explore and explain IMIDs.