Application of Clustering-based Under-sampling in Protein-Nucleotide Binding Residues Prediction
SHI Dahong
Abstract：Protein‐nucleotide binding residues prediction is of extreme importance for both protein function research and drug design .The cost of relying solely on biological experiments to obtain binding residues is costly and time‐consuming . Therefore the predictive methods of using pattern recognition techniques are more and more important .Protein‐nucleotide binding residues prediction is a typical imbalanced learning problem .In order to keep samples balanced ,on the basis of fea‐ture extraction using sparse representation ,clustering‐based under‐sampling is used for sampling ,and then SVM is used for protein‐nucleotide binding residues prediction .Experimental results illustrate the feasibility and effectiveness of our method .
Keywords：position specific scoring matrixsparse representationunder sampling based on clusteringsupport vector machine
Publication Date：2015-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 972-975 )