1 - 9 of 9 results


Identifies human ubiquitination sites. The main concept of this ESA follows the principle of natural selection, i.e. survival of the fittest in a changing environment. The identification of putative human ubiquitination sites also helps to unveil the mechanisms of ubiquitination-related biological processes. ESA-UbiSite can help identify post-translational modification (PTM) sites by evolutionarily selecting effective negatives for use in designing a more accurate prediction model, which can also improve other PTM prediction methods.


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 human-specific ubiquitination site predictor through the integration of multiple complementary classifiers. Firstly, a Support Vector Machine (SVM) classier was constructed based on the composition of k-spaced amino acid pairs (CKSAAP) encoding, which has been utilized in our previous yeast ubiquitination site predictor. To further exploit the pattern and properties of the ubiquitination sites and their flanking residues, three additional SVM classifiers were constructed using the binary amino acid encoding, the AAindex physicochemical property encoding and the protein aggregation propensity encoding, respectively. Through an integration that relied on logistic regression, the resulting predictor termed hCKSAAP_UbSite achieved an area under ROC curve (AUC) of 0.770 in 5-fold cross-validation test on a class-balanced training dataset.