Ju Zhe, Sun Juhe, Li Yanjie, Wang Li
College of Science, Shenyang Aerospace University, 110136, People's Republic of China.
College of Science, Shenyang Aerospace University, 110136, People's Republic of China.
Comput Biol Chem. 2017 Dec;71:98-103. doi: 10.1016/j.compbiolchem.2017.10.004. Epub 2017 Oct 12.
Glycation is a nonenzymatic post-translational modification which has been found to be involved in various biological processes and closely associated with many metabolic diseases. The accurate identification of glycation sites is important to understand the underlying molecular mechanisms of glycation. As the traditional experimental methods are often labor-intensive and time-consuming, it is desired to develop computational methods to predict glycation sites. In this study, a novel predictor named BPB_GlySite is proposed to predict lysine glycation sites by using bi-profile bayes feature extraction and support vector machine algorithm. As illustrated by 10-fold cross-validation, BPB_GlySite achieves a satisfactory performance with a Sensitivity of 63.68%, a Specificity of 72.60%, an Accuracy of 69.63% and a Matthew's correlation coefficient of 0.3499. Experimental results also indicate that BPB_GlySite significantly outperforms three existing glycation sites predictors: NetGlycate, PreGly and Gly-PseAAC. Therefore, BPB_GlySite can be a useful bioinformatics tool for the prediction of glycation sites. A user-friendly web-server for BPB_GlySite is established at 123.206.31.171/BPB_GlySite/.
糖基化是一种非酶促翻译后修饰，已发现其参与多种生物过程，并与许多代谢性疾病密切相关。准确识别糖基化位点对于理解糖基化的潜在分子机制很重要。由于传统实验方法通常劳动强度大且耗时，因此需要开发计算方法来预测糖基化位点。在本研究中，提出了一种名为BPB_GlySite的新型预测器，通过使用双轮廓贝叶斯特征提取和支持向量机算法来预测赖氨酸糖基化位点。如10折交叉验证所示，BPB_GlySite具有令人满意的性能，灵敏度为63.68%，特异性为72.60%，准确率为69.63%，马修斯相关系数为0.3499。实验结果还表明，BPB_GlySite明显优于三个现有的糖基化位点预测器：NetGlycate、PreGly和Gly-PseAAC。因此，BPB_GlySite可以成为预测糖基化位点的有用生物信息学工具。在123.206.31.171/BPB_GlySite/建立了一个用户友好的BPB_GlySite网络服务器。
