Hi group,

 I'm planning to apply machine learning techniques over SNP dataset.  

I already downloaded sanger dataset but confused which is the file I should deal with

the type of files is chiamo, PRLMM, tplink, signal intensity, oxstats and CEL.

From which file I can extract the AA, AB or BB.

If it is the signal intensity, so what is the threshold value I can use to build the genotype file 

Thanks