Want to use deep learning and automated microscopy to reverse engineer the rules of a cellular game? We have a fully funded #AI PhD project available.
The aim of this project is to use state-of-the-art computer vision, machine learning and automated time-lapse microscopy to determine the underlying rules governing cell competition.
Cell competition is a biological phenomenon that results in the elimination of less fit cells from a tissue – a critical process in development, homeostasis and disease. The viability of loser cells depends strongly on context: when they are cultured alone, they thrive, but when in a mixed population, they are eliminated by cells with greater fitness.
Despite its physiological relevance, cell competition remains poorly understood -- we do not know the “rules” of how cells interact, or how their biochemical and mechanical environment affects fate. To address this challenge, we recently built the first deep learning and automated single-cell microscopy system to analyse cell competition (Bove et al. Mol. Biol. Cell 2017). We used deep convolutional neural networks to analyse the state and fate of millions of single cells in mechanical competition, including cell division and death. Remarkably, this revealed that tissue-scale population shifts are strongly affected by cellular-scale tissue organisation.
In this project, we will develop new deep neural network architectures to identify the features of a single-cell’s microenvironment over time which predict its eventual fate. We will use this information to gain insight into and model the outcome of competition between two cell types in a co-culture. We will use the full scope of time-series information to determine a basic set of ‘rules’ of cell competition with relevance to development, disease and stem cell biology.