Prediction of Formylation Sites by Incorporating Sequence Coupling into General PseAAC

Post-translational modification (PTM) introduces to the biochemical mechanisms in active organisms, which has been observed in increasing functional plurality of proteins as well as operating cellular processes. Lysine formylation is such a PTM site newly invented that has gained much appreciation but a poorly destined role in chromatin composition measurement and gene expression. Our motive is to identify the annotated formyllysine sites more accurately reducing the time complexity. In this study, a novel computational tool, termed as Formyl_Pred, has been developed to predict formyllysine sites. This technique has practically implemented the sequence-coupling information surrounding amino acids of lysine residues along with optimizing slantwise training formyllysine dataset for prediction characteristics enhancement. The performance of Formyl_Pred has been measured from the average of exact 10 runs of the 10-fold cross-validation test obeying the existing methods. After implementation, Formyl_Pred has acquired an accuracy of 99.57% with an area under curve (AUC) of 0.9949. These performances indicate that Formyl_Pred remarkably outperforms the current existing prediction tool.