The nature of statistical learning theory
The nature of statistical learning theory
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Hi-index | 0.00 |
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.