Support vector machine for prediction of DNA-binding domains in protein-DNA complexes

Authors:
Jiansheng Wu;Hongtao Wu;Hongde Liu;Haoyan Zhou;Xiao Sun
Affiliations:
State Key Laboratory of Bioelectronics Southeast University, Nanjing, China;State Key Laboratory of Bioelectronics Southeast University, Nanjing, China;State Key Laboratory of Bioelectronics Southeast University, Nanjing, China;State Key Laboratory of Bioelectronics Southeast University, Nanjing, China;State Key Laboratory of Bioelectronics Southeast University, Nanjing, China
Venue:
LSMS'07 Proceedings of the 2007 international conference on Life System Modeling and Simulation
Year:
2007

Citing 4
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Analysis and prediction of DNA-binding proteins and their binding residues based on composition, sequence and structural information

Bioinformatics
PreDs: a server for predicting dsDNA-binding site on protein molecular surfaces

Bioinformatics
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, we present a classifier which takes an amino acid sequence as input and predicts potential DNA-binding domains with support vector machines (SVMs). We got amino acid sequences with known DNA-binding domains from the Protein Data Bank (PDB), and SVM models were designed integrating with four normalized sequence features (the side chain pKa value, hydrophobicity index, molecular mass of the amino acid and the number of isolated electron pairs) and a normalized feature on evolutionary information of amino acid sequences. The results show that DNA-binding domains can be predicted at 74.28% accuracy, 68.39% sensitivity and 79.76% specificity, in addition, at 0.822 ROC AUC value and 0.549 Pearson's correlation coefficient.