I am working with TCGA normalised RNAseq gene counts prostate cancer data. My aim is to cluster them with various algorithms then conclude a point about the performance of the algorithms. My Pi asked me to do a method called Rand - index. However for this method I need a reference clustered genes. Is there a database which contains genes (lets say based on their functions?)
Could you please enlighten me regarding the evaluation of the algorithms performances?
Thank you very much for your time,
Forgot to mention: While discussing with my colleagues, I was suggested to pipe all the genes to the DAVID, or GSEA?