Prediction of 2-hydroxyisobutyrylation sites by integrating multiple sequence features with ensemble support vector machine

Lysine 2-hydroxyisobutyrylation (K_hib) is a new type of histone mark, which has been found to affect the association between histone and DNA. To better understand the molecular mechanism of K_hib, it is important to identify 2-hydroxyisobutyrylated substrates and their corresponding K_hib sites accurately. In this study, a novel bioinformatics tool named KhibPred is proposed to predict K_hib sites in human HeLa cells. Three kinds of effective features, the composition of k-spaced amino acid pairs, binary encoding and amino acid factors, are incorporated to encode K_hib sites. Moreover, an ensemble support vector machine is employed to overcome the imbalanced problem in the prediction. As illustrated by 10-fold cross-validation, the performance of KhibPred achieves a satisfactory performance with an area under receiver operating characteristic curve of 0.7937. Therefore, KhibPred can be a useful tool for predicting protein K_hib sites. Feature analysis shows that the polarity factor features play significant roles in the prediction of K_hib sites. The conclusions derived from this study might provide useful insights for in-depth investigation into the molecular mechanisms of K_hib.