Prediction of protein Kbhb sites based on learnable feature embedding_Journal of Biomedical Engineering

Authors：

 WEI Zhisen ¹ , WANG Zhiwei ¹ , YU Jinyao ² , DENG Cheng ¹ , YU Dongjun ³

1. School of Computer Science, Minnan Normal University, Zhangzhou, Fujian 363000, P. R. China;
2. School of Information Science and Engineering, Ningbo University, Ningbo, Zhejiang 315211, P. R. China;
3. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, P. R. China;

Corresponding author：

WEI Zhisen, Email: zs.wei@foxmail.com

Keywords：

Lysine β-hydroxybutyrylation; Protein post-translational modification; Feature embedding; Transformer encoder; Bi-directional long short-term memory

DOI：

10.7507/1001-5515.202401005

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Protein lysine β-hydroxybutyrylation (Kbhb) is a newly discovered post-translational modification associated with a wide range of biological processes. Identifying Kbhb sites is critical to better understanding its mechanism of action. However, biochemical experimental methods for probing Kbhb sites are costly and have a long cycle. Therefore, a feature embedding learning method based on the Transformer encoder was proposed to predict Kbhb sites. In this method, amino acid residues were mapped into numerical vectors according to their amino acid class and position in a learnable feature embedding method, and then the Transformer encoder was used to extract discriminating features, and the bidirectional long short-term memory network (BiLSTM) was used to capture the correlation between different features. In this paper, a benchmark dataset was constructed, and a Kbhb site predictor, AutoTF-Kbhb, was implemented based on the proposed method. Experimental results showed that the proposed feature embedding learning method could extract effective features. AutoTF-Kbhb achieved an area under curve (AUC) of 0.87 and a Matthews correlation coefficient (MCC) of 0.37 on the independent test set, significantly outperforming other methods in comparison. Therefore, AutoTF-Kbhb can be used as an auxiliary means to identify Kbhb sites.

1.	Soffer R L. Post-translational modification of proteins catalyzed by aminoacyl-tRNA-protein transferases. Mol Cell Biochem, 1973, 2(1): 3-14.
2.	Wold F. In vivo chemical modification of proteins (post-translational modification). Annu Rev Biochem, 1981, 50(1): 783-814.
3.	Fu J, Wu M, Liu X. Proteomic approaches beyond expression profiling and PTM analysis. Anal Bioanal Chem, 2018, 410(17): 4051-4060.
4.	Huang H, Sabari B R, Garcia B A, et al. SnapShot: histone modifications. Cell, 2014, 159(2): 458-458.e1.
5.	Wang Y, Jin J, Chung M W H, et al. Identification of the YEATS domain of GAS41 as a pH-dependent reader of histone succinylation. P Natl Acad Sci USA, 2018, 115(10): 2365-2370.
6.	Luo F, Wang M, Liu Y, et al. DeepPhos: prediction of protein phosphorylation sites with deep learning. Bioinformatics, 2019, 35(16): 2766-2773.
7.	陈焕超, 魏志森, 於东军, 等. 基于LightGBM的蛋白质类泛素化修饰位点预测. 南京理工大学学报, 2022, 46(2): 156-163.
8.	Tan M, Luo H, Lee S, et al. Identification of 67 histone marks and histone lysine crotonylation as a new type of histone modification. Cell, 2011, 146(6): 1016-1028.
9.	颜志良, 丰智鹏, 刘丹, 等. 一种混合深度神经网络的赖氨酸乙酰化位点预测方法. 南京大学学报(自然科学版), 57(4): 627-640.
10.	Huang H, Zhang D, Wang Y, et al. Lysine benzoylation is a histone mark regulated by SIRT2. Nat Commu, 2018, 9(1): 3374.
11.	Ramazi S, Allahverdi A, Zahiri J. Evaluation of post-translational modifications in histone proteins: a review on histone modification defects in developmental and neurological disorders. J Biosciences, 2020, 45(1): 135.
12.	Carubbi F, Alunno A, Gerli R, et al. Post-translational modifications of proteins: novel insights in the autoimmune response in rheumatoid arthritis. Cells, 2019, 8(7): 657.
13.	Lee T Y, Huang H D, Hung J H, et al. dbPTM: an information repository of protein post-translational modification. Nucleic Acids Res, 2006, 34(Database issue): D622-627.
14.	Zhang D, Tang Z, Huang H, et al. Metabolic regulation of gene expression by histone lactylation. Nature, 2019, 574(7779): 575-580.
15.	Koronowski K B, Greco C M, Huang H, et al. Ketogenesis impact on liver metabolism revealed by proteomics of lysine β-hydroxybutyrylation. Cell Rep, 2021, 36(5): 109487.
16.	Luo W, He M, Luo Q, et al. Proteome-wide analysis of lysine β-hydroxybutyrylation in the myocardium of diabetic rat model with cardiomyopathy. Front Cardiovasc Med, 2022, 9: 1066822.
17.	范成斌. 蛋白质三羟基丁酰化位点预测的分类模型研究. 漳州: 闽南师范大学, 2023.
18.	Zhao S, Zhang X, Li H. Beyond histone acetylation—writing and erasing histone acylations. Curr Opin Struc Biol, 2018, 53: 169-177.
19.	Qiu W R, Sun B Q, Tang H, et al. Identify and analysis crotonylation sites in histone by using support vector machines. Artif Intell Med, 2017, 83: 75-81.
20.	Ju Z, He J J. Prediction of lysine crotonylation sites by incorporating the composition of k-spaced amino acid pairs into Chou’s general PseAAC. J Mol Graph Model, 2017, 77: 200-204.
21.	Qiu W R, Sun B Q, Xiao X, et al. iKcr-PseEns: Identify lysine crotonylation sites in histone proteins with pseudo components and ensemble classifier. Genomics, 2018, 110(5): 239-246.
22.	Malebary S J, Rehman M S ur, Khan Y D. iCrotoK-PseAAC: identify lysine crotonylation sites by blending position relative statistical features according to the Chou’s 5-step rule. Plos One, 2019, 14(11): e0223993.
23.	Liu Y, Yu Z, Chen C, et al. Prediction of protein crotonylation sites through LightGBM classifier based on SMOTE and elastic net. Anal Biochem, 2020, 609: 113903.
24.	Lv H, Dao F Y, Guan Z X, et al. Deep-Kcr: accurate detection of lysine crotonylation sites using deep learning method. Brief Bioinform, 2021, 22(4): bbaa255.
25.	Tng S S, Le N Q K, Yeh H Y, et al. Improved prediction model of protein lysine crotonylation sites using bidirectional recurrent neural networks. J Proteome Res, 2022, 21(1): 265-273.
26.	Shen L C, Liu Y, Song J, et al. SAResNet: self-attention residual network for predicting DNA-protein binding. Brief Bioinform, 2021, 22(5): bbab101.
27.	Zhang Y, Liu Y, Xu J, et al. Leveraging the attention mechanism to improve the identification of DNA N6-methyladenine sites. Brief Bioinform, 2021, 22(6): bbab351.
28.	Han K, Shen L C, Zhu Y H, et al. MAResNet: predicting transcription factor binding sites by combining multi-scale bottom-up and top-down attention and residual network. Brief Bioinform, 2022, 23(1): bbab445.
29.	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010.
30.	Greff K, Srivastava R K, Koutnik J, et al. LSTM: a search space odyssey. IEEE T Neur Net Lear, 2017, 28(10): 2222-2232.
31.	Berman H M, Burley S K. Protein Data Bank (PDB): Fifty-three years young and having a transformative impact on science and society. Q Rev Biophys, 2025, 58: e9.
32.	Chen Z, Zhao P, Li F, et al. iFeature: a Python package and web server for features extraction and selection from protein and peptide sequences. Bioinformatics, 2018, 34(14): 2499-2502.

1. Soffer R L. Post-translational modification of proteins catalyzed by aminoacyl-tRNA-protein transferases. Mol Cell Biochem, 1973, 2(1): 3-14.
2. Wold F. In vivo chemical modification of proteins (post-translational modification). Annu Rev Biochem, 1981, 50(1): 783-814.
3. Fu J, Wu M, Liu X. Proteomic approaches beyond expression profiling and PTM analysis. Anal Bioanal Chem, 2018, 410(17): 4051-4060.
4. Huang H, Sabari B R, Garcia B A, et al. SnapShot: histone modifications. Cell, 2014, 159(2): 458-458.e1.
5. Wang Y, Jin J, Chung M W H, et al. Identification of the YEATS domain of GAS41 as a pH-dependent reader of histone succinylation. P Natl Acad Sci USA, 2018, 115(10): 2365-2370.
6. Luo F, Wang M, Liu Y, et al. DeepPhos: prediction of protein phosphorylation sites with deep learning. Bioinformatics, 2019, 35(16): 2766-2773.
7. 陈焕超, 魏志森, 於东军, 等. 基于LightGBM的蛋白质类泛素化修饰位点预测. 南京理工大学学报, 2022, 46(2): 156-163.
8. Tan M, Luo H, Lee S, et al. Identification of 67 histone marks and histone lysine crotonylation as a new type of histone modification. Cell, 2011, 146(6): 1016-1028.
9. 颜志良, 丰智鹏, 刘丹, 等. 一种混合深度神经网络的赖氨酸乙酰化位点预测方法. 南京大学学报(自然科学版), 57(4): 627-640.
10. Huang H, Zhang D, Wang Y, et al. Lysine benzoylation is a histone mark regulated by SIRT2. Nat Commu, 2018, 9(1): 3374.
11. Ramazi S, Allahverdi A, Zahiri J. Evaluation of post-translational modifications in histone proteins: a review on histone modification defects in developmental and neurological disorders. J Biosciences, 2020, 45(1): 135.
12. Carubbi F, Alunno A, Gerli R, et al. Post-translational modifications of proteins: novel insights in the autoimmune response in rheumatoid arthritis. Cells, 2019, 8(7): 657.
13. Lee T Y, Huang H D, Hung J H, et al. dbPTM: an information repository of protein post-translational modification. Nucleic Acids Res, 2006, 34(Database issue): D622-627.
14. Zhang D, Tang Z, Huang H, et al. Metabolic regulation of gene expression by histone lactylation. Nature, 2019, 574(7779): 575-580.
15. Koronowski K B, Greco C M, Huang H, et al. Ketogenesis impact on liver metabolism revealed by proteomics of lysine β-hydroxybutyrylation. Cell Rep, 2021, 36(5): 109487.
16. Luo W, He M, Luo Q, et al. Proteome-wide analysis of lysine β-hydroxybutyrylation in the myocardium of diabetic rat model with cardiomyopathy. Front Cardiovasc Med, 2022, 9: 1066822.
17. 范成斌. 蛋白质三羟基丁酰化位点预测的分类模型研究. 漳州: 闽南师范大学, 2023.
18. Zhao S, Zhang X, Li H. Beyond histone acetylation—writing and erasing histone acylations. Curr Opin Struc Biol, 2018, 53: 169-177.
19. Qiu W R, Sun B Q, Tang H, et al. Identify and analysis crotonylation sites in histone by using support vector machines. Artif Intell Med, 2017, 83: 75-81.
20. Ju Z, He J J. Prediction of lysine crotonylation sites by incorporating the composition of k-spaced amino acid pairs into Chou’s general PseAAC. J Mol Graph Model, 2017, 77: 200-204.
21. Qiu W R, Sun B Q, Xiao X, et al. iKcr-PseEns: Identify lysine crotonylation sites in histone proteins with pseudo components and ensemble classifier. Genomics, 2018, 110(5): 239-246.
22. Malebary S J, Rehman M S ur, Khan Y D. iCrotoK-PseAAC: identify lysine crotonylation sites by blending position relative statistical features according to the Chou’s 5-step rule. Plos One, 2019, 14(11): e0223993.
23. Liu Y, Yu Z, Chen C, et al. Prediction of protein crotonylation sites through LightGBM classifier based on SMOTE and elastic net. Anal Biochem, 2020, 609: 113903.
24. Lv H, Dao F Y, Guan Z X, et al. Deep-Kcr: accurate detection of lysine crotonylation sites using deep learning method. Brief Bioinform, 2021, 22(4): bbaa255.
25. Tng S S, Le N Q K, Yeh H Y, et al. Improved prediction model of protein lysine crotonylation sites using bidirectional recurrent neural networks. J Proteome Res, 2022, 21(1): 265-273.
26. Shen L C, Liu Y, Song J, et al. SAResNet: self-attention residual network for predicting DNA-protein binding. Brief Bioinform, 2021, 22(5): bbab101.
27. Zhang Y, Liu Y, Xu J, et al. Leveraging the attention mechanism to improve the identification of DNA N6-methyladenine sites. Brief Bioinform, 2021, 22(6): bbab351.
28. Han K, Shen L C, Zhu Y H, et al. MAResNet: predicting transcription factor binding sites by combining multi-scale bottom-up and top-down attention and residual network. Brief Bioinform, 2022, 23(1): bbab445.
29. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010.
30. Greff K, Srivastava R K, Koutnik J, et al. LSTM: a search space odyssey. IEEE T Neur Net Lear, 2017, 28(10): 2222-2232.
31. Berman H M, Burley S K. Protein Data Bank (PDB): Fifty-three years young and having a transformative impact on science and society. Q Rev Biophys, 2025, 58: e9.
32. Chen Z, Zhao P, Li F, et al. iFeature: a Python package and web server for features extraction and selection from protein and peptide sequences. Bioinformatics, 2018, 34(14): 2499-2502.

Journal of Biomedical Engineering

Latest ArticlesPrediction of protein Kbhb sites based on learnable feature embedding

Abstract Full text Figures/Tables Video References Cited by

Format

Content