University of Cambridge
- Environmentally-sustainable science: how to quantify and reduce the carbon footprint of computational science. We developed the Green Algorithms project to promote best practices.
- Combining machine learning, genomics and medical imaging to better understand diseases, in particular cardiovascular ones.
- Helping clinicians leverage artificial intelligence tools for patient care.
- Biostatistics modelling for clinical studies (human and veterinary medicine)
I am currently a Research Associate in Biomedical Data Science at the University of Cambridge. I spend half of my time leading the Green Algorithms initiative to promote more environmentally sustainable computational science and the other half thinking of ways to combine machine learning, genomics and medical imaging to better understand cardiovascular diseases.
I first studied in Paris (France) at Lycée Saint-Louis and ENSAE Paris where I earned a BSc and a French Diplôme d’Ingénieur (MSc) studying mainly mathematics and statistics, but also theoretical physics and economics. In 2017, I headed to the University of Oxford, where I completed an MSc in Statistics and Machine Learning. I joined Cambridge and the Cambridge-Baker Systems Genomics Initiative in 2018 for a PhD in Health Data Science supported by the MRC-DTP. My PhD, completed in 2022, looked at machine learning tools used to predict protein-protein interactions and the carbon footprint of computational research. I stayed in the Department of Public Health and Primary Care for a postdoc in biomedical data science and green computing. I am also a College Post-Doctoral Associate at Jesus College, Cambridge, an Associate of the Senior Common Room at King’s College, Cambridge, and an Associate Fellow of Advance HE.
As part of the SSI fellowship, I hope to raise awareness around the environmental impacts of computational science and continue to help scientists across all fields to quantify and reduce the carbon footprint of their work.