A New Scheme to Characterize and Identify Protein Ubiquitination Sites

Abstract

Protein ubiquitination, involving the conjugation of ubiquitin on lysine residue, serves as an important modulator of many cellular functions in eukaryotes. Recent advancements in proteomic technology have stimulated increasing interest in identifying ubiquitination sites. However, most computational tools for predicting ubiquitination sites are focused on small-scale data. With an increasing number of experimentally verified ubiquitination sites, we were motivated to design a predictive model for identifying lysine ubiquitination sites for large-scale proteome dataset. This work assessed not only single features, such as amino acid composition (AAC), amino acid pair composition (AAPC) and evolutionary information, but also the effectiveness of incorporating two or more features into a hybrid approach to model construction. The support vector machine (SVM) was applied to generate the prediction models for ubiquitination site identification. Evaluation by five-fold cross-validation showed that the SVM models learned from the combination of hybrid features delivered a better prediction performance. Additionally, a motif discovery tool, MDDLogo, was adopted to characterize the potential substrate motifs of ubiquitination sites. The SVM models integrating the MDDLogo-identified substrate motifs could yield an average accuracy of 68.70 percent. Furthermore, the independent testing result showed that the MDDLogo-clustered SVM models could provide a promising accuracy (78.50 percent) and perform better than other prediction tools. Two cases have demonstrated the effective prediction of ubiquitination sites with corresponding substrate motifs.

Prediction of Ubiquitination Sites Using UbiNets

“…(3) 2011 Prediction of ubiquitination sites by using the composition of -spaced amino acid pairs [13] Authors used SVM as classification model and obtained accuracy of 73.40% (4) 2013hCKSAAP UbSite: improved prediction of human ubiquitination sites by exploiting amino acid pattern and properties [14] Authors used SVM as classification model based on the composition of -spaced amino acid pairs and obtained accuracy of 75.7% (5) 2014RUBI: rapid proteomic-scale prediction of lysine ubiquitination and factors influencing predictor performance [15] Authors proposed Rapid UBIquitination (RUBI), a sequence-based ubiquitination predictor, and obtained 86.8% accuracy (6) 2014 Transient protein-protein interface prediction: datasets, features, algorithms, and the RAD-T predictor [16] Authors proposed RA-T prediction model and obtained 44% improvement across multiple machine learning algorithm (7) 2016 Prediction of ubiquitination sites with feature weighting scheme and naive Bayes vectorizer [17] Category based feature weighting scheme is used and prediction model. Proposed technique performed better than SVM (8) 2016ESA-UbiSite: accurate prediction of human ubiquitination sites by identifying a set of effective negatives [18] Authors used evolutionary screening algorithm and obtained testing accuracy 92% and Matthews' correlation 0.48 (9) 2016Noncanonical pathway network modelling and ubiquitination site prediction through homology modelling of NF-B [19] Authors used loop model and asses dope functions and enhanced understanding of cofactors involved and ubiquitination sites employed during the activation process (10) 2016Computational methods for ubiquitination site prediction using physicochemical properties of protein sequences [20] Authors used various techniques like SVM and naive Bayes for predictionm and obtained AUC value greater than or equal to 0.6 (11) 2017 A new scheme to characterize and identify protein ubiquitination sites [21] Authors used SVM as prediction model and obtained 68.70% average accuracy dataset 2, and dataset 3, respectively. Dense residual v2 generated best accuracy for dataset 1, dataset 2, and dataset 3.…”

“…This study predicted the crucial cofactors in the alternate pathway of NF-kB activation. Nguyen et al [21] used support vector machine to design classification model of ubiquitination site prediction and fivefold cross validation is used. In addition a motif identification tool is taken to find out the motifs of ubiquitination sites.…”

DeepUbi: a deep learning framework for prediction of ubiquitination sites in proteins

“…Wang [23] designed a tool, ESA-UbiSite, using an evolutionary algorithm (ESA). In addition, there are many other predictors such as UbiSite [24], UbiBrowser [25], RUBI [26], the WPAAN classifier [27], MDDLogoclustered SVM models [28] and the non-canonical pathway network [29]. Although various ubiquitination site predictors have been developed, there are still limitations.…”

Large-scale prediction of protein ubiquitination sites using a multimodal deep architecture

“…Huang et al [ 8 ] developed a predictor called UbiSite, which fused multiple features such as amino acid composition (AAC), positional weighted matrix (PWM), position-specific scoring matrix (PSSM), solvent-accessible surface area (SASA) and MDDLogo-identified substrate motifs into a two-layer Support Vector Machine (SVM) model to predict protein ubiquitination sites. Nguyen et al [ 9 ] also applied SVM to build the prediction model, using three features including amino acid composition, evolutionary information and amino acid pair composition. Additionally, the motif discovery tool, MDDLogo, was also used in their predictor.…”