This directory contains the main code used for sequence based predictions of DBPs, starting from the
binding site and amino acid composition features. 
The main code is given in 
	model-train-fsel-and-cv-sq2dbp.R
The required files are:
	dbp-annotations-profile.txt
	feature-set-all.txt


Gene expression based training is similar with the only difference in the feature-set-all.txt data.