DNA is folded in an intricate 3D structure inside the nucleus of the cell. Newly developed technologies have made it possible to probe this structure, giving rise to large amounts of data conserning the spatial arrangement of DNA. Since traditionally DNA is represented in a one-dimensional fasion with genes positioned along a line, visualisation and analysis of 3D data is challenging. Newly developed machine-learning techniques have recently been used to reduce the complexity of the data, and reveal structural features not immediately visible in the 3D data itself.
In this project, the student will apply machine-learning techniques such as Principal Component Analysis (PCA) and Dynamic Bayesian Networks (DBN) to 3D-DNA datasets, with the aim of putting together a useful set of tools for visualisation and analysis.
The student should be skilled in programming and mathematics/statistics. An interest for biology is general could be an advantage.