ProTstab – predictor for cellular protein stability
Abstract Background Stability is one of the most fundamental intrinsic characteristics of proteins and can be determined with various methods. Characterization of protein properties does not keep pace with increase in new sequence data and therefore even basic properties are not known for far majori...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-11-01
|
| Series: | BMC Genomics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12864-019-6138-7 |
| _version_ | 1831735032447762432 |
|---|---|
| author | Yang Yang Xuesong Ding Guanchen Zhu Abhishek Niroula Qiang Lv Mauno Vihinen |
| author_facet | Yang Yang Xuesong Ding Guanchen Zhu Abhishek Niroula Qiang Lv Mauno Vihinen |
| author_sort | Yang Yang |
| collection | DOAJ |
| description | Abstract Background Stability is one of the most fundamental intrinsic characteristics of proteins and can be determined with various methods. Characterization of protein properties does not keep pace with increase in new sequence data and therefore even basic properties are not known for far majority of identified proteins. There have been some attempts to develop predictors for protein stabilities; however, they have suffered from small numbers of known examples. Results We took benefit of results from a recently developed cellular stability method, which is based on limited proteolysis and mass spectrometry, and developed a machine learning method using gradient boosting of regression trees. ProTstab method has high performance and is well suited for large scale prediction of protein stabilities. Conclusions The Pearson’s correlation coefficient was 0.793 in 10-fold cross validation and 0.763 in independent blind test. The corresponding values for mean absolute error are 0.024 and 0.036, respectively. Comparison with a previously published method indicated ProTstab to have superior performance. We used the method to predict stabilities of all the remaining proteins in the entire human proteome and then correlated the predicted stabilities to protein chain lengths of isoforms and to localizations of proteins. |
| first_indexed | 2024-12-21T12:18:59Z |
| format | Article |
| id | doaj.art-08bdaf0b77f144ccb3b61f5177ca011e |
| institution | Directory Open Access Journal |
| issn | 1471-2164 |
| language | English |
| last_indexed | 2024-12-21T12:18:59Z |
| publishDate | 2019-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genomics |
| spelling | doaj.art-08bdaf0b77f144ccb3b61f5177ca011e2022-12-21T19:04:21ZengBMCBMC Genomics1471-21642019-11-012011910.1186/s12864-019-6138-7ProTstab – predictor for cellular protein stabilityYang Yang0Xuesong Ding1Guanchen Zhu2Abhishek Niroula3Qiang Lv4Mauno Vihinen5School of Computer Science and Technology, Soochow UniversitySchool of Computer Science and Technology, Soochow UniversitySchool of Computer Science and Technology, Soochow UniversityDepartment of Experimental Medical Science, BMC B13, Lund UniversitySchool of Computer Science and Technology, Soochow UniversityDepartment of Experimental Medical Science, BMC B13, Lund UniversityAbstract Background Stability is one of the most fundamental intrinsic characteristics of proteins and can be determined with various methods. Characterization of protein properties does not keep pace with increase in new sequence data and therefore even basic properties are not known for far majority of identified proteins. There have been some attempts to develop predictors for protein stabilities; however, they have suffered from small numbers of known examples. Results We took benefit of results from a recently developed cellular stability method, which is based on limited proteolysis and mass spectrometry, and developed a machine learning method using gradient boosting of regression trees. ProTstab method has high performance and is well suited for large scale prediction of protein stabilities. Conclusions The Pearson’s correlation coefficient was 0.793 in 10-fold cross validation and 0.763 in independent blind test. The corresponding values for mean absolute error are 0.024 and 0.036, respectively. Comparison with a previously published method indicated ProTstab to have superior performance. We used the method to predict stabilities of all the remaining proteins in the entire human proteome and then correlated the predicted stabilities to protein chain lengths of isoforms and to localizations of proteins.http://link.springer.com/article/10.1186/s12864-019-6138-7Protein stabilityPredictionMachine learningProteome properties |
| spellingShingle | Yang Yang Xuesong Ding Guanchen Zhu Abhishek Niroula Qiang Lv Mauno Vihinen ProTstab – predictor for cellular protein stability BMC Genomics Protein stability Prediction Machine learning Proteome properties |
| title | ProTstab – predictor for cellular protein stability |
| title_full | ProTstab – predictor for cellular protein stability |
| title_fullStr | ProTstab – predictor for cellular protein stability |
| title_full_unstemmed | ProTstab – predictor for cellular protein stability |
| title_short | ProTstab – predictor for cellular protein stability |
| title_sort | protstab predictor for cellular protein stability |
| topic | Protein stability Prediction Machine learning Proteome properties |
| url | http://link.springer.com/article/10.1186/s12864-019-6138-7 |
| work_keys_str_mv | AT yangyang protstabpredictorforcellularproteinstability AT xuesongding protstabpredictorforcellularproteinstability AT guanchenzhu protstabpredictorforcellularproteinstability AT abhishekniroula protstabpredictorforcellularproteinstability AT qianglv protstabpredictorforcellularproteinstability AT maunovihinen protstabpredictorforcellularproteinstability |