Abstract
Most modern tools used to predict sites of small ubiquitin-like modifier (SUMO) binding (referred to as SUMOylation) use algorithms, chemical features of the protein, and consensus motifs. However, these tools rarely consider the influence of post-translational modification (PTM) information for other sites within the same protein on the accuracy of prediction results. This study applied the Random Forest machine learning method, as well as motif screening models and a feature selection combination mechanism, to develop a SUMOylation prediction system, referred to as SUMOgo. With regard to prediction method, PTM sites were coded as new functional features in addition to structural features, such as sequence-based binary coding, encoded chemical features of proteins, and encoded secondary structure information that is important for PTM. Twenty cycles of prediction were conducted with a 1:1 combination of positive test data and random negative data. Matthew’s correlation coefficient of SUMOgo reached 0.511, which is higher than that of current commonly used tools. This study further verified the important role of PTM in SUMOgo and includes a case study on CREB binding protein (CREBBP). The website for the final tool is http://predictor.nchu.edu.tw/SUMOgo.
Highlights
Post-translational modification (PTM) of proteins refers to the chemical modification of proteins after their translation[1,2,3]
Our research developed a SUMOylation prediction tool, named SUMOgo, which we used to explore whether such competition can affect the accuracy of SUMOylation prediction tools and whether the rules of other post-translational modification (PTM) can be applied to SUMOylation
The results showed that the prediction accuracy of SUMOgo is greater than that of other SUMOylation site prediction tools with an average Matthews correlation coefficient (MCC) of up to 0.511
Summary
Positive and negative data sets not matching the consensus motif were named CN_P and CN_N, respectively. We refer to this procedure for motif screening models as the CNCY system. A comparison of consensus motif types and the positive and negative data set ratio (P/N ratio) is necessary prior to the construction of the prediction model. Positive and negative data sets with different proportions of CN and CY were combined into SVM learning for the calculation of the average MCC for each item after prediction and for constructing motif screening models
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
