PG1cS: Prediction of protein O-GlcNAcylation sites with multiple features and analysis

As a widespread type of protein post-translational modification, O-GIcNAcylation plays crucial regulatory roles in almost all cellular processes and is related to some diseases. To deeply understand O-GlcNAcylated mechanisms, identification of substrates and specific O-GlcNAcylated sites is crucial. Experimental identification is expensive and time-consuming, so computational prediction of O-GIcNAcylated sites has considerable value. In this work, we developed a novel O-GIcNAcylated sites predictor called PGIcS (Prediction of O-GlcNAcylated Sites) by using k-means cluster to obtain informative and reliable negative samples, and support vector machines classifier combined with a two-step feature selection. The performance of PGIcS was evaluated using an independent testing dataset resulting in a sensitivity of 64.62%, a specificity of 68.4%, an accuracy of 68.37%, and a Matthew's correlation coefficient of 0.0697, which demonstrated PGlcS was very promising for predicting O-GlcNAcylated sites. The datasets and source code were available in Supplementary information. (C) 2015 Elsevier Ltd. All rights reserved.