Abstract: Systems and methods are disclosed for Knowledge-Driven Sparse Learning to Identify Interpretable High-Order Feature Interactions. This is done by generating one or more functional groups from gene features and gene and protein interaction grouping; selecting informative genes and functional interactions that exhibit differential patterns for the target disease and to generate a reduced feature space; and searching exhaustively on the reduced feature space by examining all possible pairs of interacting features (and possibly higher-order feature interactions) to identify combination of markers and complex patterns of feature interactions that are informative about the phenotypes in a sparse learning framework to select informative interactions and genes.

Abstract: Systems and methods of selecting combinatorial coordinately dysregulated biomarker subnetworks are provided. In one embodiment, a method comprises comparing the normalized gene expression data to a predetermined threshold to provide binary gene expression data associated with phenotype samples and control samples, analyzing subnetwork states of the binary gene expression data associated with phenotype samples and control samples to identify gene expression patterns that occur in phenotype samples and do not occur in control samples and identifying a subnetwork that provides gene expression patterns indicative of a sample being a phenotype sample.