The web-server predCar-Site used to predict the carbonylation sites in protein.The carbonylation is found as an irreversible post-translational modification (PTM) and considered a biomarker of oxidative stress. In protein carbonylation sites, most carbonyl groups are formed from lysine (K), proline (P), arginine (R), and threonine (T) residues. It plays major role not only in orchestrating various biological processes but also associated with some diseases. As a result, it requires an easiest way to detect carbonylation modification in proteins. However, since the experimental technologies are costly and time-consuming, so itís quite hard to detect the carbonylation modification timely at lost to face the explosive growth of protein sequences in postgenomic age. In this context, an accurate computational method for predicting carbonylation sites is an urgent issue which can be useful for drug development. In this study, a novel computational tool termed predCar-Site has been developed to predict protein carbonylation sites by (1) incorporating the sequence-coupled information in to the general pseudo amino acid composition, (2) balancing the effect of skewed training dataset by Different Error Costs (DEC) method, and (3) constructing a predictor using support vector machine as classifier. This predCar-Site predictor achieves an average AUC (area under curve) score of 0.9959, 0.9999, 1, and 0.9997 in predicting the carbonylation sites of K, P, R, and T, respectively. All of the experimental results along with AUC are found from the average of 5 times complete run of 5-fold cross-validation set and indicate the significantly better performance than existing predictors.