GNU R high-dimensional undirected graph estimation

 Provides a general framework for high-dimensional undirected graph
 estimation. It integrates data preprocessing, neighborhood screening,
 graph estimation, and model selection techniques into a pipeline. In
 preprocessing stage, the nonparanormal(npn) transformation is applied to
 help relax the normality assumption. In the graph estimation stage, the
 graph structure is estimated by Meinshausen-Buhlmann graph estimation or
 the graphical lasso, and both methods can be further accelerated by the
 lossy screening rule preselecting the neighborhood of each variable by
 correlation thresholding.