S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTE
BackgroundThe realization of many protein functions requires binding with ligands. As a significant protein-binding ligand, ATP plays a crucial role in various biological processes. Currently, the precise prediction of ATP binding residues remains challenging.MethodsBased on the sequence information...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2024.1513201/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558635715493888 |
|---|---|
| author | Sixi Hao Sixi Hao Cai-Yan Li Xiuzhen Hu Zhenxing Feng Gaimei Zhang Caiyun Yang Huimin Hu |
| author_facet | Sixi Hao Sixi Hao Cai-Yan Li Xiuzhen Hu Zhenxing Feng Gaimei Zhang Caiyun Yang Huimin Hu |
| author_sort | Sixi Hao |
| collection | DOAJ |
| description | BackgroundThe realization of many protein functions requires binding with ligands. As a significant protein-binding ligand, ATP plays a crucial role in various biological processes. Currently, the precise prediction of ATP binding residues remains challenging.MethodsBased on the sequence information, this paper introduces a method called S-DCNN for predicting ATP binding residues, utilizing a deep convolutional neural network (DCNN) enhanced with the synthetic minority over-sampling technique (SMOTE).ResultsThe incorporation of additional feature parameters such as dihedral angles, energy, and propensity factors into the standard parameter set resulted in a significant enhancement in prediction accuracy on the ATP-289 dataset. The S-DCNN achieved the highest Matthews correlation coefficient value of 0.5031 and an accuracy rate of 97.06% on an independent test set. Furthermore, when applied to the ATP-221 and ATP-388 datasets for validation, the S-DCNN outperformed existing methods on ATP-221 and performed comparably to other methods on ATP-388 during independent testing.ConclusionOur experimental results underscore the efficacy of the S-DCNN in accurately predicting ATP binding residues, establishing it as a potent tool in the prediction of ATP binding residues. |
| format | Article |
| id | doaj-art-57c07fa8d0e44e638ca089b86e5abf2c |
| institution | Kabale University |
| issn | 1664-8021 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj-art-57c07fa8d0e44e638ca089b86e5abf2c2025-01-06T06:59:47ZengFrontiers Media S.A.Frontiers in Genetics1664-80212025-01-011510.3389/fgene.2024.15132011513201S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTESixi Hao0Sixi Hao1Cai-Yan Li2Xiuzhen Hu3Zhenxing Feng4Gaimei Zhang5Caiyun Yang6Huimin Hu7College of Sciences, Inner Mongolia University of Technology, Hohhot, ChinaSchool of Mathematics and Statistics, Xinyang College, Xinyang, ChinaSchool of Computer Science and Technology/Baotou Medical College, Baotou, ChinaCollege of Sciences, Inner Mongolia University of Technology, Hohhot, ChinaCollege of Sciences, Inner Mongolia University of Technology, Hohhot, ChinaDepartment of Obstetrics and Gynecology, Hohhot First Hospital, Hohhot, ChinaCollege of Sciences, Inner Mongolia University of Technology, Hohhot, ChinaCollege of Sciences, Inner Mongolia University of Technology, Hohhot, ChinaBackgroundThe realization of many protein functions requires binding with ligands. As a significant protein-binding ligand, ATP plays a crucial role in various biological processes. Currently, the precise prediction of ATP binding residues remains challenging.MethodsBased on the sequence information, this paper introduces a method called S-DCNN for predicting ATP binding residues, utilizing a deep convolutional neural network (DCNN) enhanced with the synthetic minority over-sampling technique (SMOTE).ResultsThe incorporation of additional feature parameters such as dihedral angles, energy, and propensity factors into the standard parameter set resulted in a significant enhancement in prediction accuracy on the ATP-289 dataset. The S-DCNN achieved the highest Matthews correlation coefficient value of 0.5031 and an accuracy rate of 97.06% on an independent test set. Furthermore, when applied to the ATP-221 and ATP-388 datasets for validation, the S-DCNN outperformed existing methods on ATP-221 and performed comparably to other methods on ATP-388 during independent testing.ConclusionOur experimental results underscore the efficacy of the S-DCNN in accurately predicting ATP binding residues, establishing it as a potent tool in the prediction of ATP binding residues.https://www.frontiersin.org/articles/10.3389/fgene.2024.1513201/fullATP binding residuessynthetic minority over-sampling techniquedeep convolutional neural networkpropensity factorsdihedral angleenergy |
| spellingShingle | Sixi Hao Sixi Hao Cai-Yan Li Xiuzhen Hu Zhenxing Feng Gaimei Zhang Caiyun Yang Huimin Hu S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTE Frontiers in Genetics ATP binding residues synthetic minority over-sampling technique deep convolutional neural network propensity factors dihedral angle energy |
| title | S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTE |
| title_full | S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTE |
| title_fullStr | S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTE |
| title_full_unstemmed | S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTE |
| title_short | S-DCNN: prediction of ATP binding residues by deep convolutional neural network based on SMOTE |
| title_sort | s dcnn prediction of atp binding residues by deep convolutional neural network based on smote |
| topic | ATP binding residues synthetic minority over-sampling technique deep convolutional neural network propensity factors dihedral angle energy |
| url | https://www.frontiersin.org/articles/10.3389/fgene.2024.1513201/full |
| work_keys_str_mv | AT sixihao sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote AT sixihao sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote AT caiyanli sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote AT xiuzhenhu sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote AT zhenxingfeng sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote AT gaimeizhang sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote AT caiyunyang sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote AT huiminhu sdcnnpredictionofatpbindingresiduesbydeepconvolutionalneuralnetworkbasedonsmote |