Computational Identification of Protein Methylation Sites through Bi-Profile Bayes Feature Extraction

Abstract

Protein methylation is one type of reversible post-translational modifications (PTMs), which plays vital roles in many cellular processes such as transcription activity, DNA repair. Experimental identification of methylation sites on proteins without prior knowledge is costly and time-consuming. In silico prediction of methylation sites might not only provide researches with information on the candidate sites for further determination, but also facilitate to perform downstream characterizations and site-specific investigations. In the present study, a novel approach based on Bi-profile Bayes feature extraction combined with support vector machines (SVMs) was employed to develop the model for Prediction of Protein Methylation Sites (BPB-PPMS) from primary sequence. Methylation can occur at many residues including arginine, lysine, histidine, glutamine, and proline. For the present, BPB-PPMS is only designed to predict the methylation status for lysine and arginine residues on polypeptides due to the absence of enough experimentally verified data to build and train prediction models for other residues. The performance of BPB-PPMS is measured with a sensitivity of 74.71%, a specificity of 94.32% and an accuracy of 87.98% for arginine as well as a sensitivity of 70.05%, a specificity of 77.08% and an accuracy of 75.51% for lysine in 5-fold cross validation experiments. Results obtained from cross-validation experiments and test on independent data sets suggest that BPB-PPMS presented here might facilitate the identification and annotation of protein methylation. Besides, BPB-PPMS can be extended to build predictors for other types of PTM sites with ease. For public access, BPB-PPMS is available at http://www.bioinfo.bio.cuhk.edu.hk/bpbppms.

The Lysine Residues within the Human Ribosomal Protein S17 Sequence Naturally Inserted into the Viral Nonstructural Protein of a Unique Strain of Hepatitis E Virus Are Important for Enhanced Virus Replication

“…Both RPS19 and RPS17 are Table showing predicted common posttranslational modifications of lysines within the sequences inserted into the HEV P6 HVR. The insert is listed in the left column, followed by acetylation prediction using PAIL (44), SUMOylation prediction using SUMOplot (Abgent), ubiquitination prediction using UBpred (38), and methylation prediction using BPB-PPMS (39). ND, none detected.…”

“…The amino acid sequences from the RPS17 insertion in the Kernow C-1 P6 HEV infectious clone or the heterologous sequences from the RSV NC, yeast poly(A) binding protein, and RibL3 protein insertions were analyzed using in silico methods to determine the likelihood of posttranslational modifications via sequence information. Acetylation prediction was performed using prediction of acetylation on internal lysines (PAIL), SUMOylation prediction was performed using SUMOplot (Abgent), ubiquitination prediction was performed using UBpred (38), and methylation prediction was performed using BPB-PPMS (39).…”

“…Methylation can act epigenetically to repress or activate gene expression. We used computational identification of protein methylation sites through biprofile Bayes feature extraction (BPB-PPMS) (39). Lysine 775 from the HEV P6 insertion and lysine 800 from the RibL3 protein were predicted to be methylated (scores of 0.5 and 0.51, respectively) (Fig.…”

Predicting protein-ATP binding sites from primary sequence through fusing bi-profile sampling of multi-view features

“…Bi-profile sampling method was firstly introduced by Shao et al [41] in predicting methylation sites in proteins. This approach assumes that peptide chains from positive dataset should exhibit some difference in the level of amino acid characteristics compared to the amino acid of peptide chains from negative dataset.…”

The importance of physicochemical characteristics and nonlinear classifiers in determining HIV-1 protease specificity

“…This ratio was selected as it had previously been used successfully in the construction of the PROSPER web server 31 as well as other similar projects. 64,65 The generalization set remained unchanged. Therefore, each training set comprised 681 case and 2043 control exemplars, and each corresponding …”