1 - 16 of 16 results

PSSMe / Prediction of Species-Specific Methylation sites

A tool based on information gain (IG) feature optimization method for species-specific methylation site prediction. The IG method was adopted to analyze the importance and contribution of each feature, then select the valuable dimension feature vectors to reconstitute a new orderly feature, which was applied to build the finally prediction model. Finally, PSSMe improves prediction performance of accuracy about 15% comparing with single features. Furthermore, our species-specific model significantly improves the predictive performance compare with other general methylation prediction tools.


Identifies multiple lysine post-translational modification (PTM) sites and their different types. iPTM-mLys represents the first multi-label PTM predictor ever established. The novel predictor is featured by incorporating the sequence-coupled effects into the general PseAAC, and by fusing an array of basic random forest classifiers into an ensemble system. Rigorous cross-validations via a set of multi-label metrics indicate that the first multi-label PTM predictor is very promising and encouraging.


Identifies methylation sites based on an enhanced feature encoding scheme for extracting the most informative amino acids features. PMes is an enhanced feature encoding scheme that incorporates the amino acid sequence, position information, physicochemical properties of residues with structural characteristic to improve the prediction of protein methylation sites. It was composed of sparse property coding (SPC), normalized van der Waals volume (VDWV), position weight amino acid composition (PWAA) and solvent accessible surface area (ASA).


Predicts lysine methylation and lysine acetylation only from the protein primary sequence. PLMLA is an algorithm implemented in a web app that consider not only protein sequence information but also physicochemical properties of amino acids and residue secondary structure within the lysine regions. The prediction model achieved a promising performance and outperformed other prediction tools. This resource could help to understand the lysine methylation and acetylation mechanism and guide the related experimental validation.


A homology-based pipeline that allows identification of potential modification sites for most of the proteomes lacking post-translational modifications (PTMs) data. PTMProber provides a unique functionality for constructing customized models (such as organism-specific and modification-specific models) from user-provided data sets. Cross-promotion E-value (CPE) as stringent benchmark has been used in PTMProber to evaluate homology to known modification sites. Independent-validation tests show that PTMProber achieves over 58.8% recall with high precision by CPE benchmark. Comparisons with other machine-learning tools show that PTMProber pipeline performs better on general predictions.


A plugin implemented with the commonly used visualization software PyMOL. PyTMs enables users to introduce a set of common post-translational modifications (PTMs) into protein/peptide models and can be used to address research questions related to PTMs. Ten types of modification are currently supported, including acetylation, carbamylation, citrullination, cysteine oxidation, malondialdehyde adducts, methionine oxidation, methylation, nitration, proline hydroxylation and phosphorylation.


Predicts methylation sites in proteins. With the assistance of SVM, the highlight of iMethyl-PseAAC is to employ amino acid sequence features extracted from the sequence evolution information via grey system model (Grey-PSSM). In the prediction system, a peptide sample was formulated by a 346-dimensional vector, formed by incorporating its physicochemical, sequence evolution, biochemical, and structural disorder information into the general form of pseudo amino acid composition.


An in silico online tool for identification of potential methylation sites from protein sequences. The computational methodology is based on Bi-profile Bayes combined with support vector machines (SVMs). BPB-PPMS yields, on average, 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 the case of 5-fold cross validation, together with the results of the case study, suggesting that BPB-PPMS presented here can facilitate the identification of potential methylation sites and more confident annotation of protein methylation.


Identifies lysine-methylated sites on histones and non-histone proteins. MethK is a web server that provides a user-friendly interface and predictive results. Users can submit a protein sequence and select the protein type to identify potential lysine-methylated sites. It was developed using the support vector machine (SVM) models with amino acid composition (AAC) and accessible surface area (ASA) features for the histone model, and amino acid (AA) and amino acid pair composition (AAPC) features for the non-histone model.