hi. I read most questions, but I'm not sure of my understanding..
Assume the method consists of two steps,
1. Gene selection step (20/40/60)
2. Predict location step using only 20/40/60 selected genes.
My question is,
During gene selection step, can I use All 84 genes in situ information? (Because this step is not the prediction step)
Or should I also use 20/40/60 genes during this step?
thank you.
Created by happicukki Just to be clear, you cannot extract features from the 84 in situs in an exhaustive way, you have to pre-select the 20,40 or 60 genes and consider as if the rest did not exist. Exactly! Thanks for reply and sorry for duplicate question.
So, 20/40/60 genes should be randomly or using biological knowledge without using in situ data, right? Hi, this question was already asked but basically NO you cannot because then you would be using information from the 84 in situs. You have to imagine as if some of the gene information just did not exist, what would you do then?
thanks
Pablo