Position: Data Scientist + Bioinformatician
Department: Centre for Genomic Pathogen Surveillance, Wellcome Sanger Institute
Keywords: machine learning, bacterial evolution, antimicrobial resistance, genomics
I work as a data scientist, taking large amounts of data from the real world, and using it to discover rules about how the world works. I have developed expertise in machine learning, genomics, antibiotic resistance and infectious disease. I develop machine learning (ML) algorithms for identifying antibiotic resistant infections. These algorithms can be used to monitor antibiotic resistance in public health surveillance systems, to improve the decisions we make about when and how to prescribe antibiotics, and could in the future be used by doctors to prescribe the right antibiotics to treat infections.
The data I use to build these algorithms often comes from wealthier communities linked with large universities. ML algorithms are sensitive to bias, so I am working to test whether this data collection strategy lowers performance in low-income settings, and develop ways to prevent this. This includes developing methods to correct for this bias, and developing capacity for low-income areas to collect and contribute their own data.
I also work to educate the public, policy makers and experts on how to prevent the spread of superbugs and produce trustworthy AI products. I achieve this through writing, speaking and designing activities which encourage people to explore why things go wrong, in nature and in ML.
My work allows me to collaborate with people all over the world from biology, computing, physics, mathematics, public health, global development and policy. This diverse network allows me to bring together key partners to make progress on pressing global issues.
Get in touch: nw17 [at] sanger.ac.uk