O-glycosylation is one of the main types of the mammalian protein glycosylation; it occurs on the particular site of serine (S) or threonine (T). Several O-glycosylation site predictors have been developed. However, a need to get even better prediction tools remains. One challenge in training the classifiers is that the available datasets are highly imbalanced, which makes the classification accuracy for the minority class to become unsatisfactory. In our previous work, we have proposed a new classification approach, which is based on particle swarm optimization (PSO) and random forest (RF); this approach has considered the imbalanced dataset problem. The PSO parameters setting in the training process impacts the classification accuracy. Thus, in this paper, we perform parameters optimization for the PSO algorithm, based on genetic algorithm, in order to increase the classification accuracy. Our proposed genetic algorithm-based approach has shown better performance in terms of area under the receiver operating characteristic curve against existing predictors. In addition, we implemented a glycosylation predictor tool based on that approach, and we demonstrated that this tool could successfully identify candidate glycosylation sites in case study protein.

O-glycosylation of mammalian proteins is one of the most important post-translational modifications (PTMs). Hence, there is significant interest in the development of computational methods for reliable prediction of O-Glycosylation sites from amino acid sequences. One particular challenge in training the classifiers comes from the fact that the available dataset is highly imbalanced, which makes the classification performance for the minority class becomes unsatisfactory. Traditional sampling approaches generally rely on random re-sampling from a given dataset. However, these methods cannot utilize all the information available in the training set and it increases the false positive rate. This paper proposes a new approach for predicting the O-glycosylation sites which is based on Particle Swarm optimization (PSO) and Random Forest (RF). PSO is used as evolutionary under-sampling technique for balancing the dataset, and Random Forest is used as a classifier. The results obtained from the proposed approach and other related researches, demonstrate that the proposed approach outperforms the performance of other approaches for the experimented dataset.