|
PSFM-DBT: Identifying DNA-binding proteins by combing position specific frequency matrix and distance-bigram transformation |
The benchmark dataset 
previous constructed for identifying DNA-binding proteins by Liu and Xu. It is formed by two subsets:
(1) 
contains 525 DNA-binding proteins;
(2) 
contains 550 non-DNA-binding proteins;
The benchmark dataset can be downloaded from Supp-S1.zip.