Function to test the significance of communities within a graph


dCommSignif is supposed to test the significance of communities within a graph. For a community of the graph, it first calculates two types of degrees for each node: degrees based on parters only within the community itself, and the degrees based on its parters NOT in the community but in the graph. Then, it performs two-sample Wilcoxon tests on these two types of degrees to produce the signficance level (p-value)


dCommSignif(g, comm)


an object of class "igraph" or "graphNEL"
an object of class "communities". Details on this class can be found at


  • significance: a vector of p-values (significance)




# 1) generate an vector consisting of random values from beta distribution x <- rbeta(1000, shape1=0.5, shape2=1) # 2) fit a p-value distribution under beta-uniform mixture model fit <- dBUMfit(x, ntry=1, hist.bum=FALSE, contour.bum=FALSE)
A total of p-values: 1000 Maximum Log-Likelihood: 296.6 Mixture parameter (lambda): 0.027 Shape parameter (a): 0.498
# 3) calculate the scores according to the fitted BUM and fdr=0.01 # using "pdf" method scores <- dBUMscore(fit, method="pdf", fdr=0.05, scatter.bum=FALSE) names(scores) <- as.character(1:length(scores)) # 4) generate a random graph according to the ER model g <-, 1/100) # 5) produce the induced subgraph only based on the nodes in query subg <- dNetInduce(g, V(g), knn=0) # 6) find the module with the maximum score module <- dNetFind(subg, scores) # 7) find the module and test its signficance comm <-, modularity=TRUE) significance <- dCommSignif(module, comm)

Source code


Source man

dCommSignif.Rd dCommSignif.pdf

See also