Machine learning models of biological decision making

Modelling biological decision making is a fundamental task with potentially great practical implications. For example, bacterial cells within a human host can seemingly randomly switch from harmless to pathogenic as a result of environmental fluctuations. Understanding how these environmental fluctuations are processed by the cellular chemical machinery is critical in shaping possible interventions to combat the infection.
At a mathematical level, the question can be conveniently addressed in the formalism of stochastic processes: both the environment and the cellular processes are modelled as random variables which evolve in time. High quality data elucidating some aspects of cellular decision making are increasingly becoming available; however, there is a significant need for modelling, in particular for statistical modelling tools that can automatically account for the uncertainties inherent in the system. The goal of this project is to develop statistical machine learning techniques to model cellular decision making. The project will be highly interdisciplinary and the successful applicant will collaborate with biological researchers in the Swain lab at SynthSys, the University of Edinburgh's world leading centre for Systems and Synthetic Biology.

This is an exciting opportunity to pursue interdisciplinary studies at two world leading centres in both Informatics and Systems Biology. The project is suitable for a student with a strong mathematical background, ideally a first class degree in a quantitative science (Physics, Mathematics, Computer Science) or Engineering. Some knowledge of machine learning or stochastic processes would be desirable. It is recommended that applicants contact informally the supervisor, Dr Guido Sanguinetti, prior to application; please attach a CV and a brief description of your research interests.