Research Fellow (Biostatistician /Machine Learning Scientist)

Full-time: 35 hours per week

Fixed-term:  for 24 months (with possibility of extension)

We will consider requests for hybrid working (on a non-contractual basis) that combines a mix of remote and regular (weekly) on-campus working.  We would expect a minimum of 60% on campus working.

The Centre for Population Health Sciences at the Usher Institute within The University of Edinburgh is looking for a skilled biostatistician, informatician or data scientist to join our team and work on a project to identify biomarkers of response to treatment in people with rheumatoid arthritis, and to stratify the disease, using novel methods for analysing complex high-dimensional genetic, transcriptomic and proteomic data linked to health outcomes from large biobanks and smaller clinical cohorts.

The Opportunity:

We have recently developed a new method of statistical analysis for the problem of finding the key genes for disease, with exciting pilot results and promising drug targets for rheumatoid arthritis and other autoimmune conditions. The post holder will play a pivotal role in helping us further develop this method and take genetic discoveries forward to inform biomarker identification and validation for predicting progression and response to treatment in people with rheumatoid arthritis using available and newly generated transcriptomic and proteomic data.

This post is an important component of the work programme in Dr Spiliopoulou’s career development fellowship funded by Versus Arthritis and aiming to develop a precision medicine approach for rheumatoid arthritis. The post holder will work closely with Dr Athina Spiliopoulou, Prof Paul McKeigue, and Dr Andrii Iakovliev, and with postdoctoral researchers and students in our team. They will also interact and collaborate with academic, clinical and industry contacts from existing collaborations, including the prediction of response to treatment in rheumatoid arthritis, and with colleagues at the Diabetes Medical Informatics and Epidemiology research group at the Institute of Genetics and Cancer.

Informal enquiries may be directed to Dr Athina Spiliopoulou (A.Spiliopoulou@ed.ac.uk).

Your skills and attributes for success:  

• PhD in machine learning, genetic epidemiology or a numerate discipline OR equivalent experience.
• Broad knowledge of probabilistic models, Bayesian inference and machine learning methods.
• Good knowledge of R, Python or both (links to project source code are encouraged as part of the application).
• Experience working with Unix-based operating systems, and tools for reproducible research (e.g. GitHub, Rmarkdown).
• Good communication skills and ability to work within a team.
• Ability to manage time and work plans to achieve the objectives of a project

Apply Before: 01/07/2025, 23:59

Advert information