Guido Sanguinetti

We present a novel inference framework for bi-stable dynamical systems whose behaviour is described by a system of non-linear
differential equations driven by a latent stochastic process. We assume our stochastic process to be a two state continuous time jump process, and devise an analytical approximate solution. We apply the framework to the modelling of transcriptional regulation of stress reaction in cells, where external stimuli force the regulatory mechanism of the cell to rapidly switch between different regimes.