Prediction of citrullination sites by incorporating k-spaced amino acid pairs into Chou's general pseudo amino acid composition

• Published in: Gene Vol. 664; pp. 78 - 83
• Main Authors: Ju, Zhe, Wang, Shi-Yun
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 20.07.2018
• Subjects: Algorithms; Arginine - metabolism; Citrullination; Computational Biology - methods; Genetic Testing; Humans; K-spaced amino acid pair; Models, Biological; Post-translational modification; Proteomics - methods; Support vector machine; Post-translational modification; Citrullination; ACC; PTM; SVM; Support vector machine; MCC; AUC; K-spaced amino acid pair; RBF; CKSAAP; Sn; Sp
• ISSN: 0378-1119; 1879-0038; 1879-0038
• DOI: 10.1016/j.gene.2018.04.055

As one of the most important and common protein post-translational modifications, citrullination plays a key role in regulating various biological processes and is associated with several human diseases. The accurate identification of citrullination sites is crucial for elucidating the underlying molecular mechanisms of citrullination and designing drugs for related human diseases. In this study, a novel bioinformatics tool named CKSAAP_CitrSite is developed for the prediction of citrullination sites. With the assistance of support vector machine algorithm, the highlight of CKSAAP_CitrSite is to adopt the composition of k-spaced amino acid pairs surrounding a query site as input. As illustrated by 10-fold cross-validation, CKSAAP_CitrSite achieves a satisfactory performance with a Sensitivity of 77.59%, a Specificity of 95.26%, an Accuracy of 89.37% and a Matthew's correlation coefficient of 0.7566, which is much better than those of the existing prediction method. Feature analysis shows that the N-terminal space containing pairs may play an important role in the prediction of citrullination sites, and the arginines close to N-terminus tend to be citrullinated. The conclusions derived from this study could offer useful information for elucidating the molecular mechanisms of citrullination and related experimental validations. A user-friendly web-server for CKSAAP_CitrSite is available at 123.206.31.171/CKSAAP_CitrSite/. [Display omitted] •A novel predictor is developed to predict citrullination sites.•The CKSAAP encoding is used to predict and analyze citrullination sites.•F-score feature selection method is adopted to remove the redundant features.•A free online service is available for prediction.