Bayesian inference of chemical reaction networks

6 November 2015
12:00 pm
Bayesian inference of chemical reaction networks
Nikhil Galagali
PhD Candidate
Aerospace Computational Design Laboratory
Department of Aeronautics and Astronautics

The development of chemical reaction models aids system design and optimization, along with fundamental understanding, in a number of areas such as combustion, catalysis, and biology. A systematic approach to building reaction network models uses available data not only to estimate unknown parameters, but to also learn the model structure. Bayesian inference provides a natural approach for this data-driven construction of models. The traditional Bayesian model inference methodology is based on evaluating a multidimensional integral for each model. This is often not feasible for reaction network inference, as the number of plausible models can be very large. An alternative approach based on model-space sampling can enable large-scale network inference, but its efficient implementation continues to be a challenge.

In this talk, we present some newly developed computational methods that make large-scale nonlinear network inference tractable. Firstly, we exploit the network-based interactions of species to design improved between-model proposals for Markov chain Monte Carlo (MCMC). We then introduce a sensitivity-based determination of move types which, when combined with the above network-aware proposals, yields further sampling efficiency. We also show that by recognizing network inference as a fixed-dimensional problem with point-mass priors, we can adapt existing adaptive MCMC methods for network inference. Finally, we present an approximation-based method that allows sampling over very large model spaces whose exploration could be prohibitively expensive with exact sampling methods.