SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites
Abstract Protein S-sulfenylation, which results from oxidation of free thiols on cysteine residues, has recently emerged as an important post-translational modification that regulates the structure and function of proteins involved in a variety of physiological and pathological processes. By alterin...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2018-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-018-29126-x |
| _version_ | 1818994374262915072 |
|---|---|
| author | Hussam J. AL-barakati Evan W. McConnell Leslie M. Hicks Leslie B. Poole Robert H. Newman Dukka B. KC |
| author_facet | Hussam J. AL-barakati Evan W. McConnell Leslie M. Hicks Leslie B. Poole Robert H. Newman Dukka B. KC |
| author_sort | Hussam J. AL-barakati |
| collection | DOAJ |
| description | Abstract Protein S-sulfenylation, which results from oxidation of free thiols on cysteine residues, has recently emerged as an important post-translational modification that regulates the structure and function of proteins involved in a variety of physiological and pathological processes. By altering the size and physiochemical properties of modified cysteine residues, sulfenylation can impact the cellular function of proteins in several different ways. Thus, the ability to rapidly and accurately identify putative sulfenylation sites in proteins will provide important insights into redox-dependent regulation of protein function in a variety of cellular contexts. Though bottom-up proteomic approaches, such as tandem mass spectrometry (MS/MS), provide a wealth of information about global changes in the sulfenylation state of proteins, MS/MS-based experiments are often labor-intensive, costly and technically challenging. Therefore, to complement existing proteomic approaches, researchers have developed a series of computational tools to identify putative sulfenylation sites on proteins. However, existing methods often suffer from low accuracy, specificity, and/or sensitivity. In this study, we developed SVM-SulfoSite, a novel sulfenylation prediction tool that uses support vector machines (SVM) to identify key determinants of sulfenylation among five feature classes: binary code, physiochemical properties, k-space amino acid pairs, amino acid composition and high-quality physiochemical indices. Using 10-fold cross-validation, SVM-SulfoSite achieved 95% sensitivity and 83% specificity, with an overall accuracy of 89% and Matthew’s correlation coefficient (MCC) of 0.79. Likewise, using an independent test set of experimentally identified sulfenylation sites, our method achieved scores of 74%, 62%, 80% and 0.42 for accuracy, sensitivity, specificity and MCC, with an area under the receiver operator characteristic (ROC) curve of 0.81. Moreover, in side-by-side comparisons, SVM-SulfoSite performed as well as or better than existing sulfenylation prediction tools. Together, these results suggest that our method represents a robust and complementary technique for advanced exploration of protein S-sulfenylation. |
| first_indexed | 2024-12-20T20:56:56Z |
| format | Article |
| id | doaj.art-a2f299fb10184e2fa23fde2539f4dae7 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-20T20:56:56Z |
| publishDate | 2018-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a2f299fb10184e2fa23fde2539f4dae72022-12-21T19:26:48ZengNature PortfolioScientific Reports2045-23222018-07-01811910.1038/s41598-018-29126-xSVM-SulfoSite: A support vector machine based predictor for sulfenylation sitesHussam J. AL-barakati0Evan W. McConnell1Leslie M. Hicks2Leslie B. Poole3Robert H. Newman4Dukka B. KC5Department of Computational Science and Engineering, North Carolina A&T State UniversityDepartment of Chemistry, University of North Carolina at Chapel HillDepartment of Chemistry, University of North Carolina at Chapel HillDepartment of Biochemistry, Wake Forest University School of MedicineDepartment of Biology, North Carolina A&T State UniversityDepartment of Computational Science and Engineering, North Carolina A&T State UniversityAbstract Protein S-sulfenylation, which results from oxidation of free thiols on cysteine residues, has recently emerged as an important post-translational modification that regulates the structure and function of proteins involved in a variety of physiological and pathological processes. By altering the size and physiochemical properties of modified cysteine residues, sulfenylation can impact the cellular function of proteins in several different ways. Thus, the ability to rapidly and accurately identify putative sulfenylation sites in proteins will provide important insights into redox-dependent regulation of protein function in a variety of cellular contexts. Though bottom-up proteomic approaches, such as tandem mass spectrometry (MS/MS), provide a wealth of information about global changes in the sulfenylation state of proteins, MS/MS-based experiments are often labor-intensive, costly and technically challenging. Therefore, to complement existing proteomic approaches, researchers have developed a series of computational tools to identify putative sulfenylation sites on proteins. However, existing methods often suffer from low accuracy, specificity, and/or sensitivity. In this study, we developed SVM-SulfoSite, a novel sulfenylation prediction tool that uses support vector machines (SVM) to identify key determinants of sulfenylation among five feature classes: binary code, physiochemical properties, k-space amino acid pairs, amino acid composition and high-quality physiochemical indices. Using 10-fold cross-validation, SVM-SulfoSite achieved 95% sensitivity and 83% specificity, with an overall accuracy of 89% and Matthew’s correlation coefficient (MCC) of 0.79. Likewise, using an independent test set of experimentally identified sulfenylation sites, our method achieved scores of 74%, 62%, 80% and 0.42 for accuracy, sensitivity, specificity and MCC, with an area under the receiver operator characteristic (ROC) curve of 0.81. Moreover, in side-by-side comparisons, SVM-SulfoSite performed as well as or better than existing sulfenylation prediction tools. Together, these results suggest that our method represents a robust and complementary technique for advanced exploration of protein S-sulfenylation.https://doi.org/10.1038/s41598-018-29126-x |
| spellingShingle | Hussam J. AL-barakati Evan W. McConnell Leslie M. Hicks Leslie B. Poole Robert H. Newman Dukka B. KC SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites Scientific Reports |
| title | SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites |
| title_full | SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites |
| title_fullStr | SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites |
| title_full_unstemmed | SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites |
| title_short | SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites |
| title_sort | svm sulfosite a support vector machine based predictor for sulfenylation sites |
| url | https://doi.org/10.1038/s41598-018-29126-x |
| work_keys_str_mv | AT hussamjalbarakati svmsulfositeasupportvectormachinebasedpredictorforsulfenylationsites AT evanwmcconnell svmsulfositeasupportvectormachinebasedpredictorforsulfenylationsites AT lesliemhicks svmsulfositeasupportvectormachinebasedpredictorforsulfenylationsites AT lesliebpoole svmsulfositeasupportvectormachinebasedpredictorforsulfenylationsites AT roberthnewman svmsulfositeasupportvectormachinebasedpredictorforsulfenylationsites AT dukkabkc svmsulfositeasupportvectormachinebasedpredictorforsulfenylationsites |