Prediction Of Sumoylation Sites Research Articles

GPS-SUMO 2.0: an updated online service for the prediction of SUMOylation sites and SUMO-interacting motifs.

Small ubiquitin-like modifiers (SUMOs) are tiny but important protein regulators involved in orchestrating a broad spectrum of biological processes, either by covalently modifying protein substrates or by noncovalently interacting with other proteins. Here, we report an updated server, GPS-SUMO 2.0, for the prediction of SUMOylation sites and SUMO-interacting motifs (SIMs). For predictor training, we adopted three machine learning algorithms, penalized logistic regression (PLR), a deep neural network (DNN), and a transformer, and used 52404 nonredundant SUMOylation sites in 8262 proteins and 163 SIMs in 102 proteins. To further increase the accuracy of predicting SUMOylation sites, a pretraining model was first constructed using 145545 protein lysine modification sites, followed by transfer learning to fine-tune the model. GPS-SUMO 2.0 exhibited greater accuracy in predicting SUMOylation sites than did other existing tools. For users, one or multiple protein sequences or identifiers can be input, and the prediction results are shown in a tabular list. In addition to the basic statistics, we integrated knowledge from 35 public resources to annotate SUMOylation sites or SIMs. The GPS-SUMO 2.0 server is freely available at https://sumo.biocuckoo.cn/. We believe that GPS-SUMO 2.0 can serve as a useful tool for further analysis of SUMOylation and SUMO interactions.

An application of topological data analysis in predicting sumoylation sites.

Sumoylation is a reversible post-translational modification that regulates certain significant biochemical functions in proteins. The protein alterations caused by sumoylation are associated with the incidence of some human diseases. Therefore, identifying the sites of sumoylation in proteins may provide a direction for mechanistic research and drug development. Here, we propose a new computational approach for identifying sumoylation sites using an encoding method based on topological data analysis. The features of our model captured the key physical and biological properties of proteins at multiple scales. In a 10-fold cross validation, the outcomes of our model showed 96.45% of sensitivity (Sn), 94.65% of accuracy (Acc), 0.8946 of Matthew's correlation coefficient (MCC), and 0.99 of area under curve (AUC). The proposed predictor with only topological features achieves the best MCC and AUC in comparison to the other released methods. Our results suggest that topological information is an additional parameter that can assist in the prediction of sumoylation sites and provide a novel perspective for further research in protein sumoylation.

Bioinformatic Tools for Exploring the SUMO Gene Network: An Update.

Plant sumoylation research has seen significant advances in recent years, particularly since high-throughput proteomic strategies have enabled the discovery of more than one thousand SUMO targets. In the present chapter, we update the previously reported SUMO (small ubiquitin-related modifier) gene network (SGN) to its v4 iteration. SGN is a curated assembly of Arabidopsis thaliana genes that have been functionally associated with sumoylation, from SUMO pathway components to targets and interactors. The enclosed tutorial helps interpret and manage these datasets and details bioinformatic tools that can be used for in silico-based hypothesis generation. The latter include tools for sumoylation site prediction, comparative genomics, and gene network analysis.

ResSUMO: A Deep Learning Architecture Based on Residual Structure for Prediction of Lysine SUMOylation Sites.

Lysine SUMOylation plays an essential role in various biological functions. Several approaches integrating various algorithms have been developed for predicting SUMOylation sites based on a limited dataset. Recently, the number of identified SUMOylation sites has significantly increased due to investigation at the proteomics scale. We collected modification data and found the reported approaches had poor performance using our collected data. Therefore, it is essential to explore the characteristics of this modification and construct prediction models with improved performance based on an enlarged dataset. In this study, we constructed and compared 16 classifiers by integrating four different algorithms and four encoding features selected from 11 sequence-based or physicochemical features. We found that the convolution neural network (CNN) model integrated with residue structure, dubbed ResSUMO, performed favorably when compared with the traditional machine learning and CNN models in both cross-validation and independent tests. The area under the receiver operating characteristic (ROC) curve for ResSUMO was around 0.80, superior to that of the reported predictors. We also found that increasing the depth of neural networks in the CNN models did not improve prediction performance due to the degradation problem, but the residual structure could be included to optimize the neural networks and improve performance. This indicates that residual neural networks have the potential to be broadly applied in the prediction of other types of modification sites with great effectiveness and robustness. Furthermore, the online ResSUMO service is freely accessible.

Importation of chloroplast proteins under heat stress is facilitated by their SUMO conjugations.

Chloroplasts are hypersensitive to heat stress (HS). SUMOylation, a critical post-translational modification, is conservatively involved in HS responses. However, the functional connection between SUMOylation and chloroplasts under HS remains to be studied. The bioinformatics, biochemistry, and cell biology analyses were used to detect the SUMOylation statuses of Arabidopsis nuclear-encoded chloroplast proteins and the effect of SUMOylation on subcellular localization of these proteins under HS. PSBR, a subunit of photosystem II, was used as an example for a detailed investigation of functional mechanisms. After a global SUMOylation site prediction of nuclear-encoded chloroplast proteins, biochemical data showed that most of the selected candidates are modified by SUMO3 in the cytoplasm. The chloroplast localization of these SUMOylation targets under long-term HS is partially maintained by the SUMO ligase AtSIZ1. The HS-induced SUMOylation on PSBR contributes to the maintenance of its chloroplast localization, which is dependent on its chloroplast importation efficiency correlated to phosphorylation. The complementation analysis provided evidence that SUMOylation is essential for the physiological function of PSBR under HS. Our study illustrated a general regulatory mechanism of SUMOylation in maintaining the chloroplast protein importation during HS and provided hints for further investigation on protein modifications associated with plant organelles under stress conditions.

Recent Development of Machine Learning Methods in Sumoylation Sites Prediction.

Sumoylation of proteins is an important reversible post-translational modification of proteins and mediates a variety of cellular processes. Sumo-modified proteins can change their subcellular localization, activity, and stability. In addition, it also plays an important role in various cellular processes such as transcriptional regulation and signal transduction. The abnormal sumoylation is involved in many diseases, including neurodegeneration and immune-related diseases, as well as the development of cancer. Therefore, identification of the sumoylation site (SUMO site) is fundamental to understanding their molecular mechanisms and regulatory roles. In contrast to labor-intensive and costly experimental approaches, computational prediction of sumoylation sites in silico has also attracted much attention for its accuracy, convenience, and speed. At present, many computational prediction models have been used to identify SUMO sites, but their contents have not been comprehensively summarized and reviewed. Therefore, the research progress of relevant models is summarized and discussed in this paper. We have briefly summarized the development of bioinformatics methods for sumoylation site prediction by mainly focusing on the benchmark dataset construction, feature extraction, machine learning method, published results, and online tools. We hope that this review will provide more help for wet-experimental scholars.

An Ensemble Deep Learning based Predictor for Simultaneously Identifying Protein Ubiquitylation and SUMOylation Sites

BackgroundSeveral computational tools for predicting protein Ubiquitylation and SUMOylation sites have been proposed to study their regulatory roles in gene location, gene expression, and genome replication. However, existing methods generally rely on feature engineering, and ignore the natural similarity between the two types of protein translational modification. This study is the first all-in-one deep network to predict protein Ubiquitylation and SUMOylation sites from protein sequences as well as their crosstalk sites simultaneously. Our deep learning architecture integrates several meta classifiers that apply deep neural networks to protein sequence information and physico-chemical properties, which were trained on multi-label classification mode for simultaneously identifying protein Ubiquitylation and SUMOylation as well as their crosstalk sites.ResultsThe promising AUCs of our method on Ubiquitylation, SUMOylation and crosstalk sites achieved 0.838, 0.888, and 0.862 respectively on tenfold cross-validation. The corresponding APs reached 0.683, 0.804 and 0.552, which also validated our effectiveness.ConclusionsThe proposed architecture managed to classify ubiquitylated and SUMOylated lysine residues along with their crosstalk sites, and outperformed other well-known Ubiquitylation and SUMOylation site prediction tools.

ISUMOK-PseAAC: prediction of lysine sumoylation sites using statistical moments and Chou's PseAAC.

Sumoylation is the post-translational modification that is involved in the adaption of the cells and the functional properties of a large number of proteins. Sumoylation has key importance in subcellular concentration, transcriptional synchronization, chromatin remodeling, response to stress, and regulation of mitosis. Sumoylation is associated with developmental defects in many human diseases such as cancer, Huntington’s, Alzheimer’s, Parkinson’s, Spin cerebellar ataxia 1, and amyotrophic lateral sclerosis. The covalent bonding of Sumoylation is essential to inheriting part of the operative characteristics of some other proteins. For that reason, the prediction of the Sumoylation site has significance in the scientific community. A novel and efficient technique is proposed to predict the Sumoylation sites in proteins by incorporating Chou’s Pseudo Amino Acid Composition (PseAAC) with statistical moments-based features. The outcomes from the proposed system using 10 fold cross-validation testing are 94.51%, 94.24%, 94.79% and 0.8903% accuracy, sensitivity, specificity and MCC, respectively. The performance of the proposed system is so far the best in comparison to the other state-of-the-art methods. The codes for the current study are available on the GitHub repository using the link: https://github.com/csbioinfopk/iSumoK-PseAAC.

ORCA/LRWD1 Regulates Homologous Recombination at ALT-Telomeres by Modulating Heterochromatin Organization.

SummaryTelomeres are maintained by telomerase or in a subset of cancer cells by a homologous recombination (HR)-based mechanism, Alternative Lengthening of Telomeres (ALT). The mechanisms regulating telomere-homeostasis in ALT cells remain unclear. We report that a replication initiator protein, Origin Recognition Complex-Associated (ORCA/LRWD1), by localizing at the ALT-telomeres, modulates HR activity. ORCA's localization to the ALT-telomeres is facilitated by its interaction to SUMOylated shelterin components. The loss of ORCA in ALT-positive cells elevates the levels of two mediators of HR, RPA and RAD51, and consistent with this, we observe increased ALT-associated promyelocytic leukemia body formation and telomere sister chromatid exchange. ORCA binds to RPA and modulates the association of RPA to telomeres. Finally, the loss of ORCA causes global chromatin decondensation, including at the telomeres. Our results demonstrate that ORCA acts as an inhibitor of HR by modulating RPA binding to ssDNA and inducing chromatin compaction.

SUMO-Forest: A Cascade Forest based method for the prediction of SUMOylation sites on imbalanced data.

• SUMOylation sites prediction on imbalanced datasets. • A new model which combines Cascade Forest and Genetic Algorithm. • A new feature based on different types of amino acids at specific positions.

HseSUMO: Sumoylation site prediction using half-sphere exposures of amino acids residues

BackgroundPost-translational modifications are viewed as an important mechanism for controlling protein function and are believed to be involved in multiple important diseases. However, their profiling using laboratory-based techniques remain challenging. Therefore, making the development of accurate computational methods to predict post-translational modifications is particularly important for making progress in this area of research.ResultsThis work explores the use of four half-sphere exposure-based features for computational prediction of sumoylation sites. Unlike most of the previously proposed approaches, which focused on patterns of amino acid co-occurrence, we were able to demonstrate that protein structural based features could be sufficiently informative to achieve good predictive performance. The evaluation of our method has demonstrated high sensitivity (0.9), accuracy (0.89) and Matthew’s correlation coefficient (0.78–0.79). We have compared these results to the recently released pSumo-CD method and were able to demonstrate better performance of our method on the same evaluation dataset.ConclusionsThe proposed predictor HseSUMO uses half-sphere exposures of amino acids to predict sumoylation sites. It has shown promising results on a benchmark dataset when compared with the state-of-the-art method.The extracted data of this study can be accessed at https://github.com/YosvanyLopez/HseSUMO.

SumSec: Accurate Prediction of Sumoylation Sites Using Predicted Secondary Structure.

Post Translational Modification (PTM) is defined as the modification of amino acids along the protein sequences after the translation process. These modifications significantly impact on the functioning of proteins. Therefore, having a comprehensive understanding of the underlying mechanism of PTMs turns out to be critical in studying the biological roles of proteins. Among a wide range of PTMs, sumoylation is one of the most important modifications due to its known cellular functions which include transcriptional regulation, protein stability, and protein subcellular localization. Despite its importance, determining sumoylation sites via experimental methods is time-consuming and costly. This has led to a great demand for the development of fast computational methods able to accurately determine sumoylation sites in proteins. In this study, we present a new machine learning-based method for predicting sumoylation sites called SumSec. To do this, we employed the predicted secondary structure of amino acids to extract two types of structural features from neighboring amino acids along the protein sequence which has never been used for this task. As a result, our proposed method is able to enhance the sumoylation site prediction task, outperforming previously proposed methods in the literature. SumSec demonstrated high sensitivity (0.91), accuracy (0.94) and MCC (0.88). The prediction accuracy achieved in this study is 21% better than those reported in previous studies. The script and extracted features are publicly available at: https://github.com/YosvanyLopez/SumSec.

SUMOgo: Prediction of sumoylation sites on lysines by motif screening models and the effects of various post-translational modifications

Most modern tools used to predict sites of small ubiquitin-like modifier (SUMO) binding (referred to as SUMOylation) use algorithms, chemical features of the protein, and consensus motifs. However, these tools rarely consider the influence of post-translational modification (PTM) information for other sites within the same protein on the accuracy of prediction results. This study applied the Random Forest machine learning method, as well as motif screening models and a feature selection combination mechanism, to develop a SUMOylation prediction system, referred to as SUMOgo. With regard to prediction method, PTM sites were coded as new functional features in addition to structural features, such as sequence-based binary coding, encoded chemical features of proteins, and encoded secondary structure information that is important for PTM. Twenty cycles of prediction were conducted with a 1:1 combination of positive test data and random negative data. Matthew’s correlation coefficient of SUMOgo reached 0.511, which is higher than that of current commonly used tools. This study further verified the important role of PTM in SUMOgo and includes a case study on CREB binding protein (CREBBP). The website for the final tool is http://predictor.nchu.edu.tw/SUMOgo.

Bioinformatics Tools for Exploring the SUMO Gene Network.

Plant sumoylation research has seen significant advances in recent years, particularly since high-throughput proteomics strategies have enabled the discovery of hundreds of potential SUMO targets and interactors of SUMO pathway components. In the present chapter, we introduce the SUMO Gene Network (SGN), a curated assembly of Arabidopsis thaliana genes that have been functionally associated with sumoylation, from SUMO pathway components to targets and interactors. The enclosed tutorial helps interpret and manage these datasets, and details bioinformatics tools that can be used for in silico-based hypothesis generation. The latter include tools for sumoylation site prediction, comparative genomics, and gene network analysis.

Prediction of sumoylation sites in proteins using linear discriminant analysis

Sumoylation is a multifunctional post-translation modification (PTM) in proteins by the small ubiquitin-related modifiers (SUMOs), which have relations to ubiquitin in molecular structure. Sumoylation has been found to be involved in some cellular processes. It is very significant to identify the exact sumoylation sites in proteins for not only basic researches but also drug developments. Comparing with time exhausting experiment methods, it is highly desired to develop computational methods for prediction of sumoylation sites as a complement to experiment in the post-genomic age. In this work, three feature constructions (AAIndex, position-specific amino acid propensity and modification of composition of k-space amino acid pairs) and five different combinations of them were used to construct features. At last, 178 features were selected as the optimal features according to the Mathew's correlation coefficient values in 10-fold cross validation based on linear discriminant analysis. In 10-fold cross-validation on the benchmark dataset, the accuracy and Mathew's correlation coefficient were 86.92% and 0.6845. Comparing with those existing predictors, SUMO_LDA showed its better performance.

JASSA: a comprehensive tool for prediction of SUMOylation sites and SIMs.

Post-translational modification by the Small Ubiquitin-like Modifier (SUMO) proteins, a process termed SUMOylation, is involved in many fundamental cellular processes. SUMO proteins are conjugated to a protein substrate, creating an interface for the recruitment of cofactors harboring SUMO-interacting motifs (SIMs). Mapping both SUMO-conjugation sites and SIMs is required to study the functional consequence of SUMOylation. To define the best candidate sites for experimental validation we designed JASSA, a Joint Analyzer of SUMOylation site and SIMs. JASSA is a predictor that uses a scoring system based on a Position Frequency Matrix derived from the alignment of experimental SUMOylation sites or SIMs. Compared with existing web-tools, JASSA displays on par or better performances. Novel features were implemented towards a better evaluation of the prediction, including identification of database hits matching the query sequence and representation of candidate sites within the secondary structural elements and/or the 3D fold of the protein of interest, retrievable from deposited PDB files. JASSA is freely accessible at http://www.jassa.fr/. Website is implemented in PHP and MySQL, with all major browsers supported. guillaume.beauclair@inserm.fr Supplementary data are available at Bioinformatics online.

Predicting sumoylation sites using support vector machines based on various sequence features, conformational flexibility and disorder.

BackgroundSumoylation, which is a reversible and dynamic post-translational modification, is one of the vital processes in a cell. Before a protein matures to perform its function, sumoylation may alter its localization, interactions, and possibly structural conformation. Abberations in protein sumoylation has been linked with a variety of disorders and developmental anomalies. Experimental approaches to identification of sumoylation sites may not be effective due to the dynamic nature of sumoylation, laborsome experiments and their cost. Therefore, computational approaches may guide experimental identification of sumoylation sites and provide insights for further understanding sumoylation mechanism.ResultsIn this paper, the effectiveness of using various sequence properties in predicting sumoylation sites was investigated with statistical analyses and machine learning approach employing support vector machines. These sequence properties were derived from windows of size 7 including position-specific amino acid composition, hydrophobicity, estimated sub-window volumes, predicted disorder, and conformational flexibility. 5-fold cross-validation results on experimentally identified sumoylation sites revealed that our method successfully predicts sumoylation sites with a Matthew's correlation coefficient, sensitivity, specificity, and accuracy equal to 0.66, 73%, 98%, and 97%, respectively. Additionally, we have showed that our method compares favorably to the existing prediction methods and basic regular expressions scanner.ConclusionsBy using support vector machines, a new, robust method for sumoylation site prediction was introduced. Besides, the possible effects of predicted conformational flexibility and disorder on sumoylation site recognition were explored computationally for the first time to our knowledge as an additional parameter that could aid in sumoylation site prediction.

GPS-SUMO: a tool for the prediction of sumoylation sites and SUMO-interaction motifs.

Small ubiquitin-like modifiers (SUMOs) regulate a variety of cellular processes through two distinct mechanisms, including covalent sumoylation and non-covalent SUMO interaction. The complexity of SUMO regulations has greatly hampered the large-scale identification of SUMO substrates or interaction partners on a proteome-wide level. In this work, we developed a new tool called GPS-SUMO for the prediction of both sumoylation sites and SUMO-interaction motifs (SIMs) in proteins. To obtain an accurate performance, a new generation group-based prediction system (GPS) algorithm integrated with Particle Swarm Optimization approach was applied. By critical evaluation and comparison, GPS-SUMO was demonstrated to be substantially superior against other existing tools and methods. With the help of GPS-SUMO, it is now possible to further investigate the relationship between sumoylation and SUMO interaction processes. A web service of GPS-SUMO was implemented in PHP + JavaScript and freely available at http://sumosp.biocuckoo.org.

Abstract 3201: PTBP1 stability is increased in ovarian and breast cancer cell lines compared to matched controls.

Abstract PTBP1 (polypyrimidine tract-binding) protein is a splicing factor that is frequently upregulated in ovarian and breast tumors. Knockdown (KD) of PTBP1 expression by shRNA impairs ovarian tumor cell growth in vivo and in vitro, as well as colony formation and invasiveness in vitro (He et al, Oncogene 26:4961-8, 2007). We have also found that PTBP1 is progressively upregulated in immortalized human mammary epithelial cells (HMECs) and human ovarian surface epithelial (HOSE) cells, correlating with their transformation state. These results prompted us to determine the factors that play a role in the upregulation of PTBP1 protein expression. We first asked whether the increased PTBP1 protein in human ovarian and breast cell lines is accompanied by proportional increases of PTBP1 mRNA. We found that there was a discordance between PTBP1 mRNA and protein levels, as measured by RT-PCR and western blot, in these cancer cell lines in relation to the control cells (finite lifespan HMEC or HOSE, respectively). Accordingly, we attempted to understand the basis for this discrepancy, and measured PTBP1 protein half-life. We treated A2780 (ovarian cancer), MCF7 (breast cancer) cells, and “finite lifespan” HMEC (184A1) with cycloheximide to terminate protein synthesis and followed the fate of PTBP1 protein over time by western blot. We found that the half-life of PTBP1 protein is ∼3-5 h in the HMECs with finite lifespan, whereas it ranges from ∼9-12h in human epithelial ovarian and breast cancer cells. These results demonstrate that PTBP1 expression is regulated in part by events that control the stability of the protein and suggest that the normal regulation of PTBP1 protein turnover is altered in cancer cell lines. Bioinformatics analysis identified one possible SUMO-binding motif site within the PTBP1 protein (SUMOsp 2.0 - SUMOylation Site Prediction, http://sumosp.biocuckoo.org/), suggesting that SUMOylation may play a role in PTBP1 stability; we are currently examining this possibility. Findings presented herein will enhance our understanding of the regulation of PTBP1 expression and the mechanisms underlying its variation in protein and mRNA levels in ovarian and breast tumors. (Support in part by NCI grants R01 CA40570 and R01 CA138762 [to WTB], by OCRF [to XH], and by UIC.) Citation Format: Ahmet Dirim Arslan, Szilard Asztalos, Martha Stampfer, Debra Tonetti, Xiaolong He, William T. Beck. PTBP1 stability is increased in ovarian and breast cancer cell lines compared to matched controls. [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 3201. doi:10.1158/1538-7445.AM2013-3201

SUMOhydro: a novel method for the prediction of sumoylation sites based on hydrophobic properties.

Sumoylation is one of the most essential mechanisms of reversible protein post-translational modifications and is a crucial biochemical process in the regulation of a variety of important biological functions. Sumoylation is also closely involved in various human diseases. The accurate computational identification of sumoylation sites in protein sequences aids in experimental design and mechanistic research in cellular biology. In this study, we introduced amino acid hydrophobicity as a parameter into a traditional binary encoding scheme and developed a novel sumoylation site prediction tool termed SUMOhydro. With the assistance of a support vector machine, the proposed method was trained and tested using a stringent non-redundant sumoylation dataset. In a leave-one-out cross-validation, the proposed method yielded an excellent performance with a correlation coefficient, specificity, sensitivity and accuracy equal to 0.690, 98.6%, 71.1% and 97.5%, respectively. In addition, SUMOhydro has been benchmarked against previously described predictors based on an independent dataset, thereby suggesting that the introduction of hydrophobicity as an additional parameter could assist in the prediction of sumoylation sites. Currently, SUMOhydro is freely accessible at http://protein.cau.edu.cn/others/SUMOhydro/.