Design And Implementation Of Predicting Lysine Succinylation In Proteins By GBM

Lysine succinylation is an extremely important protein posttranslational modification that plays a fundamental role in regulating various biological reactions,and dysfunction of this process is associated with a number of diseases.Thus,determining which Lys residues in an uncharacterized protein sequence is are succinylated underpins both basic research and drug development endeavors.If we use biological experiments to solve this problem,all the sites in the protein sequence need to be tested and require a lot of experimentation,which will waste a lot of time.To solve this problem,a predictor called pSuc-PseRat was developed in this paper to provide experimental reference and improve experimental efficiency.The features of pSuc-PseRat predictor has two key characteristicsare derived from two aspects:(i)it was developed by the binary encoding from succinylated sites and non-succinylated sites;and(ii)it was developed by the sequence-coupling effects between succinylated sites and non-succinylated sites.Eleven gradient boosting machine classifiers were then trained with these featurescharacteristics to build the predictor.The pSuc-PseRat predictor achieved an average AUC score of 0.805 in the 5-fold cross-validation set and performed better than existing predictors on two comprehensive independent test sets.The pSuc-PseRat provides a free and useful website for forecasting services at http://ccsipb.lnu.edu.cn/pred/succ_prediction/.