This article is part of the supplement: Selected articles from the Tenth Asia Pacific Bioinformatics Conference (APBC 2012)
Learning generative models of molecular dynamics
1 Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
2 Department of Biochemistry, University of Washington, Seattle, WA 98195, USA
3 Computer Science Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA
4 Lane Center for Computational Biology, Carnegie Mellon University, Pittsburgh, PA 15213, USA
BMC Genomics 2012, 13(Suppl 1):S5 doi:10.1186/1471-2164-13-S1-S5Published: 17 January 2012
We introduce three algorithms for learning generative models of molecular structures from molecular dynamics simulations. The first algorithm learns a Bayesian-optimal undirected probabilistic model over user-specified covariates (e.g., fluctuations, distances, angles, etc). L1 reg-ularization is used to ensure sparse models and thus reduce the risk of over-fitting the data. The topology of the resulting model reveals important couplings between different parts of the protein, thus aiding in the analysis of molecular motions. The generative nature of the model makes it well-suited to making predictions about the global effects of local structural changes (e.g., the binding of an allosteric regulator). Additionally, the model can be used to sample new conformations. The second algorithm learns a time-varying graphical model where the topology and parameters change smoothly along the trajectory, revealing the conformational sub-states. The last algorithm learns a Markov Chain over undirected graphical models which can be used to study and simulate kinetics. We demonstrate our algorithms on multiple molecular dynamics trajectories.