We present a novel inference methodology to reverse engineer the dynamics of transcription factors (TFs) in hierarchical network motifs such as feed-forward loops. The approach we present is based on a continuous time representation of the system where the high level master TF is represented as a two state Markov jump process driving a system of differential equations. We present an approximate variational inference algorithm and show promising preliminary results on a realistic simulated data set.
|Title of host publication||Machine Learning in Systems Biology, Proceedings of the Fourth International Workshop of|
|Number of pages||4|
|Publication status||Published - 2010|