Datasets used for the 10-fold cross-validation tests.
Benign variants have been randomly selected to match 
the number of Pathogenic variants in coding and noncoding
regiones.

SET = Cross-validation subset
CHR = Chromosome     
POS = Position of hg38 reference genome    
MUT = Reference, Alterantive alleles    
REG = coding/noncoding    
EFF = Annotation    
PRED = Prediction   
PROB = Probability of pathogenicity 
