Entering edit mode
7.6 years ago
mms140130
▴
60
Hello
I have performed a PCA analysis on gene expression data 1096 patients and 20248 genes and plotted the pc1 vs. pc2 then using hclust i defined two groups,
I want to color the 2 groups defined in hclust on the PCA plot
i.e to see where are the 2 groups on the plot
I used the following codes
library(ggplot2)
model2=prcomp(tmydf1,scale.=T) # tmydf1 has patients as rows and gene as column
scores <- as.data.frame(model2$x)
qplot(x = PC1, y = PC2, data = scores, geom = "point", col = racetum$V1)
#hcluster
fit <- hclust(dist(tmydf1), method="complete")
groups <- cutree(fit, k=2)
> group.2= cutree(fit,2)
> table(group.2)
group.2
1 2
1074 22
You'll have to add the group.2 to your original data frame as a new column.
Then use this column for plotting with different colors.