Note: this question has also been asked on Biostars
I am currently trying to complete a Breast Cancer Classification task using Neural Networks. I have experimented with using my full dataset of gene expressions(1000+) and managed to improve my results by using only the PAM50 genes. I was wondering though what other genes I could add to the list to even better improve my results.
I have tried looking for papers about extending the PAM50, but could not find anything. I would greatly appreciate any advice.