Figure 3
From: A Bayesian variable selection procedure to rank overlapping gene sets
Heat-map showing the dendrogram from the overlaps among all KEGG pathways; the points represent posterior Pearson correlations between the indicator variables, generated by Gibbs sampling, corresponding to all the KEGG pathways. The latent variables could be either one or zero, indicating that a particular KEGG pathway is included in or excluded from the model, respectively. A positive posterior correlation would indicate pathways that are selected together in the model; and a negative correlation would indicate pathways that tend to be included in the model alternately. Ending to only select one of them at the time but not the other one or select the second one but not the first one.