In GranderLab/ClusterSignificanceExtras: A package allowing re-creation of all figures in the publication associated with the ClusterSignificance package

Read Me

This data is used to as an easy example to understand the purpose of ClusterSignificance. It is set up so that the results can easily be anticipated before ClusterSignificance is run. The permutation results are currently saved in the package (to save time) but, if you desire to re-run the analysis you can follow the typical ClusterSignificance pipeline using the pcpMatrix dataset in the ClusterSignificance package.

library(ClusterSignificanceExtras)

#load data
mat <- pcpMatrix
groups <- rownames(pcpMatrix)

#run ClusterSignificance projection and change colors
prj <- pcp(mat, groups)
group.color <- getData(prj, "group.color")
group.color[1,] <- c(68, 221, 136)
group.color[2,] <- c(170, 204, 34)
group.color[3,] <- c(153, 119, 85)
[e-mail] <- group.color

#run CLusterSignificance classification
cl <- classify(prj)

#run ClusterSignificance permutation
set.seed(3)
#pe <- permute(mat, groups, "pcp", 10000)
pe <- pcpPermutations

Re-create Figure 1.

Projection

plot(prj, steps=3, alpha=0.75, cex.lab = 2, cex.axis = 2, cex.symbols = 3, cex.legend=2, pt.cex.legend=3)

Classification

plot(cl, cex.points=3, cex.main=2, cex.lab=2, cex.axis=2)

Permutation

plot(pe, cex.main=2, cex.lab=1.5, cex.axis=2, abline.lwd=1.5)

P-values

pvalue(pe)

GranderLab/ClusterSignificanceExtras documentation built on May 6, 2019, 6:30 p.m.