Plotting Correlation matrix

Question

[Zhiyi]

Hi,

I'm trying to plot a correlation matrix such that the color of each square correspond to the correlation coefficient (deeper color -> higher correlation), while the size of the square corresponds to the pval (larger square -> more significant pval).

Is there any R / python package that can plot such a correlation matrix (as shown)? (The figure is from https://www.nature.com/articles/ng.3406#Sec20)

Answer 1

[LChart]

That's corrplot: https://cran.r-project.org/web/packages/corrplot/vignettes/corrplot-intro.html

[Zhiyi]

It seems in this package the size of the square corresponds to the correlation coefficient instead of the pvalue. Is there a way to make larger squares to correpond to more significant p-values?

[Ram]

I don't think the package has that sort of customization available. It's open source, so feel free to modify the code and share your modified code when you publish the figure.