siGGM: Structurally Informed Gaussian Graphical Models

Description Details Author(s) References See Also


siGGM is a collection of functions for estimating functional brain networks which are influenced by anatomical connectivity information. The two primary functions in this package are SCFC and SCFCpath. SCFC will estimate one functional network structure when the user supplies a sparsity tuning parameter. SCFCpath will provide estimates along a grid of sparsity parameters. This package also includes three functions for simulating precision matrices that retain small world, scale free, or Erdos-Renyi network properties. For each, the user can control the density and network size.

The approach relies on lasso (L1) penalty terms to impose sparsity on the network estimates, using either the approach of Friedman, Hastie and Tibshirani (2007) or Hsieh et al. (2011).


The following functions are included:

SCFC, SCFCpath, SmallWorld, ScaleFree, ErdosRenyi


Ixavier A Higgins, Suprateek Kundu, Ying Guo

Maintainer: Ixavier A Higgins <>


Higgins, Ixavier A., Suprateek Kundu, and Ying Guo. Integrative Bayesian Analysis of Brain Functional Networks Incorporating Anatomical Knowledge. arXiv preprint arXiv:1803.00513 (2018).

Jerome Friedman, Trevor Hastie and Robert Tibshirani (2007). Sparse inverse covariance estimation with the lasso. Biostatistics 2007.

Cho-Jui Hsieh, Matyas A. Sustik, Inderjit S. Dhillon, Pradeep Ravikumar. Sparse Inverse Covariance Matrix Estimation Using Quadratic Approximation. Advances in Neural Information Processing Systems, vol. 24, 2011, p. 2330<e2><80><93>2338.

Csardi G, Nepusz T: The igraph software package for complex network research, InterJournal, Complex Systems 1695. 2006.

See Also


IxavierHiggins/siGGMrepo documentation built on May 21, 2019, 9:39 a.m.