A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites
Abstract Protein phosphorylation, which is one of the most important post-translational modifications (PTMs), is involved in regulating myriad cellular processes. Herein, we present a novel deep learning based approach for organism-specific protein phosphorylation site prediction in Chlamydomonas re...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-91840-w |
| _version_ | 1819122470797443072 |
|---|---|
| author | Niraj Thapa Meenal Chaudhari Anthony A. Iannetta Clarence White Kaushik Roy Robert H. Newman Leslie M. Hicks Dukka B. KC |
| author_facet | Niraj Thapa Meenal Chaudhari Anthony A. Iannetta Clarence White Kaushik Roy Robert H. Newman Leslie M. Hicks Dukka B. KC |
| author_sort | Niraj Thapa |
| collection | DOAJ |
| description | Abstract Protein phosphorylation, which is one of the most important post-translational modifications (PTMs), is involved in regulating myriad cellular processes. Herein, we present a novel deep learning based approach for organism-specific protein phosphorylation site prediction in Chlamydomonas reinhardtii, a model algal phototroph. An ensemble model combining convolutional neural networks and long short-term memory (LSTM) achieves the best performance in predicting phosphorylation sites in C. reinhardtii. Deemed Chlamy-EnPhosSite, the measured best AUC and MCC are 0.90 and 0.64 respectively for a combined dataset of serine (S) and threonine (T) in independent testing higher than those measures for other predictors. When applied to the entire C. reinhardtii proteome (totaling 1,809,304 S and T sites), Chlamy-EnPhosSite yielded 499,411 phosphorylated sites with a cut-off value of 0.5 and 237,949 phosphorylated sites with a cut-off value of 0.7. These predictions were compared to an experimental dataset of phosphosites identified by liquid chromatography-tandem mass spectrometry (LC–MS/MS) in a blinded study and approximately 89.69% of 2,663 C. reinhardtii S and T phosphorylation sites were successfully predicted by Chlamy-EnPhosSite at a probability cut-off of 0.5 and 76.83% of sites were successfully identified at a more stringent 0.7 cut-off. Interestingly, Chlamy-EnPhosSite also successfully predicted experimentally confirmed phosphorylation sites in a protein sequence (e.g., RPS6 S245) which did not appear in the training dataset, highlighting prediction accuracy and the power of leveraging predictions to identify biologically relevant PTM sites. These results demonstrate that our method represents a robust and complementary technique for high-throughput phosphorylation site prediction in C. reinhardtii. It has potential to serve as a useful tool to the community. Chlamy-EnPhosSite will contribute to the understanding of how protein phosphorylation influences various biological processes in this important model microalga. |
| first_indexed | 2024-12-22T06:52:58Z |
| format | Article |
| id | doaj.art-763a7ff34700418ebf40a11c4465bd6e |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-22T06:52:58Z |
| publishDate | 2021-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-763a7ff34700418ebf40a11c4465bd6e2022-12-21T18:35:04ZengNature PortfolioScientific Reports2045-23222021-06-0111111210.1038/s41598-021-91840-wA deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sitesNiraj Thapa0Meenal Chaudhari1Anthony A. Iannetta2Clarence White3Kaushik Roy4Robert H. Newman5Leslie M. Hicks6Dukka B. KC7Department of Computational Data Science and Engineering, North Carolina A&T State UniversityDepartment of Computational Data Science and Engineering, North Carolina A&T State UniversityDepartment of Chemistry, University of North Carolina at Chapel HillDepartment of Computational Data Science and Engineering, North Carolina A&T State UniversityDepartment of Computer Science, North Carolina A&T State UniversityDepartment of Biology, North Carolina A&T State UniversityDepartment of Chemistry, University of North Carolina at Chapel HillElectrical Engineering and Computer Science Department, Wichita State UniversityAbstract Protein phosphorylation, which is one of the most important post-translational modifications (PTMs), is involved in regulating myriad cellular processes. Herein, we present a novel deep learning based approach for organism-specific protein phosphorylation site prediction in Chlamydomonas reinhardtii, a model algal phototroph. An ensemble model combining convolutional neural networks and long short-term memory (LSTM) achieves the best performance in predicting phosphorylation sites in C. reinhardtii. Deemed Chlamy-EnPhosSite, the measured best AUC and MCC are 0.90 and 0.64 respectively for a combined dataset of serine (S) and threonine (T) in independent testing higher than those measures for other predictors. When applied to the entire C. reinhardtii proteome (totaling 1,809,304 S and T sites), Chlamy-EnPhosSite yielded 499,411 phosphorylated sites with a cut-off value of 0.5 and 237,949 phosphorylated sites with a cut-off value of 0.7. These predictions were compared to an experimental dataset of phosphosites identified by liquid chromatography-tandem mass spectrometry (LC–MS/MS) in a blinded study and approximately 89.69% of 2,663 C. reinhardtii S and T phosphorylation sites were successfully predicted by Chlamy-EnPhosSite at a probability cut-off of 0.5 and 76.83% of sites were successfully identified at a more stringent 0.7 cut-off. Interestingly, Chlamy-EnPhosSite also successfully predicted experimentally confirmed phosphorylation sites in a protein sequence (e.g., RPS6 S245) which did not appear in the training dataset, highlighting prediction accuracy and the power of leveraging predictions to identify biologically relevant PTM sites. These results demonstrate that our method represents a robust and complementary technique for high-throughput phosphorylation site prediction in C. reinhardtii. It has potential to serve as a useful tool to the community. Chlamy-EnPhosSite will contribute to the understanding of how protein phosphorylation influences various biological processes in this important model microalga.https://doi.org/10.1038/s41598-021-91840-w |
| spellingShingle | Niraj Thapa Meenal Chaudhari Anthony A. Iannetta Clarence White Kaushik Roy Robert H. Newman Leslie M. Hicks Dukka B. KC A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites Scientific Reports |
| title | A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites |
| title_full | A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites |
| title_fullStr | A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites |
| title_full_unstemmed | A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites |
| title_short | A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites |
| title_sort | deep learning based approach for prediction of chlamydomonas reinhardtii phosphorylation sites |
| url | https://doi.org/10.1038/s41598-021-91840-w |
| work_keys_str_mv | AT nirajthapa adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT meenalchaudhari adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT anthonyaiannetta adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT clarencewhite adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT kaushikroy adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT roberthnewman adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT lesliemhicks adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT dukkabkc adeeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT nirajthapa deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT meenalchaudhari deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT anthonyaiannetta deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT clarencewhite deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT kaushikroy deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT roberthnewman deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT lesliemhicks deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites AT dukkabkc deeplearningbasedapproachforpredictionofchlamydomonasreinhardtiiphosphorylationsites |