Position-Specific Analysis and Prediction for Protein Lysine Acetylation Based on Multiple Features

摘要: Protein lysine acetylation is a type of reversible post-translational modification that plays vital role in many cellular processes, such as transcriptional regulation, apoptosis and cytokine signaling. To fully decipher the molecular mechanisms acetylation-related biological an initial but crucial step recognition acetylated substrates corresponding sites. In this study, we developed position-specific method named PSKAcePred for prediction based on support vector machines. The residues around sites were selected or excluded their entropy values. We incorporated features amino acid composition information, evolutionary similarity physicochemical properties to predict model achieved accuracy 79.84% Matthews correlation coefficient 59.72% using 10-fold cross-validation balanced positive negative samples. A feature analysis showed all applied contributed process. derived from critical neighboring profoundly site determination. detailed paper can help us understand more mechanism provide guidance related experimental validation.