A Graphical Model Approach to Identify Primary Genes in Perturbed Biological Pathways

The algorithm pursues the identification of the set of variables driving the differences in two different experimental conditions (i.e., the primary genes) within a graphical model context. It uses the idea of simultaneously looking for the differences between two multivariate normal distributions in all marginal and conditional distributions associated with a decomposable graph, which represents the pathway under exam. The implementation accommodates genomics specific issues (low sample size and multiple testing issues) and provides a number of functions offering numerical and visual summaries to help the user interpret the obtained results. In order to use the (optional) 'Cytoscape' functionalities, the suggested 'r2cytoscape' package must be installed from the 'GitHub' repository ('devtools::install_github('cytoscape/r2cytoscape')').


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.1.3 by Elisa Salviato, 2 years ago

Browse source code at https://github.com/cran/SourceSet

Authors: Elisa Salviato [aut, cre] , Vera Djordjilovic [aut] , Chiara Romualdi [aut] , Monica Chiogna [aut]

Documentation:   PDF Manual  

AGPL-3 license

Imports gRbase, progress, reshape2, graph, igraph, gtools, methods, plyr, scales

Suggests networkD3, ggplot2, grDevices, Rgraphviz, knitr, rmarkdown, r2cytoscape, BiocStyle, Biobase, graphite, hgu95av2.db, ALL, mvtnorm, org.Hs.eg.db

See at CRAN