Novel approach for selecting the best predictor for identifying the binding sites in DNA binding proteins
In this work, We evaluated the performance of 11 different DNA binding residues prediction methods with unbiased, stringent and diverse datasets for DNA binding proteins based on various aspects: (i) 7 structural classes, (ii) 86 folds, (iii) 106 superfamilies, (iv) 194 families, (v) 15 binding motifs, (vi) single/double stranded DNA, (vii) DNA conformation (A, B, Z etc.) and (viii) three functions. Further, the best performances of different methods in different datasets have been revealed. The information gained in this work would be helpful as well as necessary for biologists to choose the best method for designing experiments.
Please select a protein/DNA information from the provided options to identify the best predictor
Choose:
--select--
Class
Fold
Superfamily
Family
DNA Strand
DNA Conformation
Motif
Enzyme
Regulatory Proteins
Structural Proteins
To access the benchmarking data sets click
here
Reference: Novel approach for selecting the best predictor for identifying the binding sites in DNA binding proteins
Nagarajan, R., Shandar Ahmad. and Gromiha, M. M.
Nucleic Acids Research (2013), 41 (16), 7606-7614.
Comments and Feedbacks to : gromiha@iitm.ac.in.