My current research work focuses on these main areas: Predicting the native structure of a protein from its amino acid sequence remains a highly challenging problem in the biological sciences. A significant bottleneck of computational prediction is the lack of efficient sampling algorithms to explore the configuration space of a protein. We are developing approaches to improve sampling, beginning at the fragment level of proteins. Efficiency is gained by sequentially guiding the sampling distributions of each amino acid to respect the geometric and energetic properties that are satisfied by real proteins. Sampling is carried out with the goal of attaining Monte Carlo optimization of a protein's free energy. Dynamic models, which are usually described by coupled differential equations, are widely used in modeling diverse behaviors in science. Examples of these include the modeling of mRNA and protein levels in cultured cells, and gene regulatory networks with feedback loops. Methods of parametric estimation for dynamic models from noisy data are computationally intensive due to the need to repeatedly solve ordinary differential equations numerically. We are working on interpolation methods and approximate inference via emulated Gaussian systems to provide fast convergence while still retaining estimation accuracy. The aim is to provide computationally viable methods for parameter inference on the large systems often encountered in systems biology, which may involve dozens of components. The lumber industry is enormous -- Statistics Canada estimates the value of the lumber industry's manufacturing shipments in 2009 at about $12B in Canada alone. The product has a myriad of applications and it is also seen as increasingly important due to its sustainability. Along with that rise in interest comes concern about the effects of climate change on the growth of trees and consequently the mechanical properties of the wood products derived from these trees. This concern and new approaches to processing the resource have led to a need to detect changes in the engineering properties of lumber. That in turn has led a renewed interest in ways of assessing lumber properties, including innovative analytical approaches that exploit modern statistical theory.