Find a Data Champion

I am a PhD student at the MRC Biostatistics Unit, interested in applying machine learning techniques to biological data. I have worked on classification of cancer (sub)types using XGBoost models. I am currently working on trying to uncover biological details about the immune system using graph data and graph machine learning.

 I am a Geoinformatics Engineer. I have been actively contributing to the geospatial domain in both Academia and Industry since 2015. During this time I have used my expertise to make end-to-end solutions from data acquisition, data management and provision of services in the application areas of Urban planning, Vehicle tracking, Rescue services, Location based services and Archaeology.

I have over 30 years experience of Scientific Computing. I have worked on Image analysis of Light Microscopy images, Scientific IT Support (13 years), Data-driven web applications of mathematical models and Bioinformatics Training at the Institute of Food Research (Now the Quadram Institute). I have been involved in an EU Framework Database Workshop. I strive to include good data-handling and reproducibility practices into all training materials.

I'm a research fellow working to improve data management practices broadly across the materials and chemical sciences, with the aim to accelerate discovery and enable new data-driven approaches in the physical sciences. I lead the development of the decentralised open source RDM platform, datalab, used by several labs in Cambridge and beyond to track sample provenance, ingest raw characterisation data from instruments and easily disseminate data within and between labs. datalab has been designed primarily with materials chemistry and battery groups in mind, but has been extended to work for polymer research, direct air capture and autonomous labs. I also work extensively on API standardisation for crystal structure databases, via my involvement in OPTIMADE. I am very happy to discuss how people can engage with this work if they are in this domain, or how the approach could be adopted by other domains.

Before starting my current role, I completed my undergraduate studies in Theoretical Physics at the University of Manchester, after which I joined the University of Cambridge for an MPhil in Scientific Computing and subsequent PhD in Physics where I worked on crystal structure prediction for battery materials. I then joined UCLouvain in Belgium for a postdoc and research fellowship, before making my way back to Cambridge in 2025 as a Leverhulme Trust Early Career Research Fellow.