SUMOylation Sites Prediction by Machine Learning Approaches

Post-translational modification (PTM) influence still does not considered by current sumoylation prediction tools. Therefore, this study developed a sumoylation prediction system based on machine learning approach employing SVM (support vector machine) and related information. In the feature coding, we encoded binary code and protein properties based on amino acid sequence. Besides, we encoded other PTM distribution as functional feature and secondary information as structure feature. In addition, we analyzed the number of the post-modification distributions under the central lysine and window size 21 rules, and we provided some of our findings and recommended post-modification types that could be considered. Finally, this study developed a new sumoylation prediction algorithm called SUMOdig. The prediction system of Matthew's correlation coefficient achieves to 0.504.