As post-genomic biology becomes more predictive, the inference of rate parameters that feature in both genetic and biochemical networks becomes increasingly important. Here we present a novel methodology for inference of such parameters in the case of stochastic networks, based on concepts from the area of computer models combined with Bayes Linear variance learning methodology. We apply these techniques to a simple, analytically tractable Birth-Death pro- cess model, followed by a more complex stochastic Prokaryotic Auto-regulatory Gene Network.
Vernon, I. R., & Goldstein, M. (2010). A Bayes Linear Approach to Systems Biology. MUCM