Research on prediction model of protein thermostability integrating graph embedding and network topology features_Journal of Biomedical Engineering

Authors：

PAN Shuyi , XIANG Xiaoyang , YAN Qunfang ,  DING Yanrui

School of Science, Jiangnan University, Wuxi, Jiangsu 214122, P. R. China;

Corresponding author：

DING Yanrui, Email: yr_ding@jiangnan.edu.cn

Keywords：

Residue interaction networks; Graph embedding; Feature fusion; Deep learning; Protein heat tolerance

DOI：

10.7507/1001-5515.202501045

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Protein structure determines function, and structural information is critical for predicting protein thermostability. This study proposes a novel method for protein thermostability prediction by integrating graph embedding features and network topological features. By constructing residue interaction networks (RINs) to characterize protein structures, we calculated network topological features and utilize deep neural networks (DNN) to mine inherent characteristics. Using DeepWalk and Node2vec algorithms, we obtained node embeddings and extracted graph embedding features through a TopN strategy combined with bidirectional long short-term memory (BiLSTM) networks. Additionally, we introduced the Doc2vec algorithm to replace the Word2vec module in graph embedding algorithms, generating graph embedding feature vector encodings. By employing an attention mechanism to fuse graph embedding features with network topological features, we constructed a high-precision prediction model, achieving 87.85% prediction accuracy on a bacterial protein dataset. Furthermore, we analyzed the differences in the contributions of network topological features in the model and the differences among various graph embedding methods, and found that the combination of DeepWalk features with Doc2vec and all topological features was crucial for the identification of thermostable proteins. This study provides a practical and effective new method for protein thermostability prediction, and at the same time offers theoretical guidance for exploring protein diversity, discovering new thermostable proteins, and the intelligent modification of mesophilic proteins.

1.	Finch A J, Kim J R. Thermophilic proteins as versatile scaffolds for protein engineering. Microorganisms, 2018, 6(4): 97.
2.	Silva N H, Vilela C, Marrucho I M, et al. Protein-based materials: from sources to innovative sustainable materials for biomedical applications. Mater Chem B, 2014, 2(24): 3715-3740.
3.	Guta M, Abebe G, Bacha K, et al. Screening and characterization of thermostable enzyme-producing bacteria from selected hot springs of Ethiopia. Microbiol Spectr, 2024, 12(3): e0371023.
4.	Venev S V, Zeldovich K B. Thermophilic adaptation in prokaryotes is constrained by metabolic costs of proteostasis. Mol Biol Evol, 2018, 35(1): 211-224.
5.	Rousseau M, Oulavallickal T, Williamson A, et al. Characterisation and engineering of a thermophilic RNA ligase from Palaeococcus pacificus. Nucleic Acids Res, 2024, 52(7): 3924-3937.
6.	Barabasi A L, Oltvai Z N. Network biology: understanding the cell's functional organization. Nat Rev Genet, 2004, 5(2): 101-113.
7.	常珊, 焦雄, 王美华, 等. 蛋白质氨基酸网络研究进展. 现代生物医学进展, 2011, 11(001): 190-193.
8.	Grewal R K, Roy S. Modeling proteins as residue interaction networks. Protein Pept Lett, 2015, 22(10): 923-933.
9.	Guan Ruining, Liu Wencheng, Li Ningqi, et al. Machine learning models based on residue interaction network for ABCG2 transportable compounds recognition. Environ Pollut, 2023, 337: 122620.
10.	Inan T, Yuce M, Mackerell JR A D, et al. Exploring druggable binding sites on the Class A GPCRs using the residue interaction network and site identification by ligand competitive saturation. ACS Omega, 2024, 9(38): 40154-40171.
11.	Hu Guang, Yan Wenying, Zhou Jianhong, et al. Residue interaction network analysis of Dronpa and a DNA clamp. J Theor Biol, 2014, 348: 55-64.
12.	Verkhivker G. Molecular dynamics simulations and modelling of the residue interaction networks in the BRAF kinase complexes with small molecule inhibitors: probing the allosteric effects of ligand-induced kinase dimerization and paradoxical activation. Mol Biosyst, 2016, 12(10): 3146-3165.
13.	Jiao Xiong, Chang Shan, Li Chunhua, et al. Construction and application of the weighted amino acid network based on residue fluctuations. Phys Rev E Stat Nonlin Soft Matter Phys, 2007, 75(5 Pt 1): 051903.
14.	Jiao Xiong, Yang Lifeng, An Meiwen, et al. A modified amino acid network model contains similar and dissimilar weight. Comput Math Methods Med, 2013, 2013(1): 197892.
15.	Wang Ziqi, Zhang Yuanyuan, Wang Shudong, et al. SINE: second-order information network embedding. IEEE Access, 2020, 8: 139044-139051.
16.	Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations// Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. New York: ACM SIGKDD, 2014: 701-710.
17.	Grover A, Leskovec J. node2vec: Scalable feature learning for networks// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016: 855-864.
18.	Berman H M, Westbrook J, Feng Z, et al. The protein data bank. Nucleic Acids Res, 2000, 28(1): 235-242.
19.	Schober I, Koblitz J, Sardà C J, et al. BacDive in 2025: the core database for prokaryotic strain data. Nucleic Acids Res, 2025, 53(D1): D748-D756.
20.	Piovesan D, Minervini G, Tosatto S C. The RING 2. 0 web server for high quality residue interaction networks. Nucleic Acids Res, 2016, 44(W1): W367-W74.
21.	Page L, Brin S, Motwani R, et al. The PageRank citation ranking: Bringing order to the web. stanford digital libraries working paper, 1999.
22.	Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space. arXiv preprint arXiv, 2013: 1301.3781.
23.	Le Q, Mikolov T. Distributed representations of sentences and documents// Proceedings of the 31th International Conference on Machine Learning. Beijing: IMLS, 2014: 1188-1196.
24.	Shaw P, Uszkoreit J, Vaswani A. Self-attention with relative position representations. arXiv preprint arXiv, 2018: 1803.02155.

1. Finch A J, Kim J R. Thermophilic proteins as versatile scaffolds for protein engineering. Microorganisms, 2018, 6(4): 97.
2. Silva N H, Vilela C, Marrucho I M, et al. Protein-based materials: from sources to innovative sustainable materials for biomedical applications. Mater Chem B, 2014, 2(24): 3715-3740.
3. Guta M, Abebe G, Bacha K, et al. Screening and characterization of thermostable enzyme-producing bacteria from selected hot springs of Ethiopia. Microbiol Spectr, 2024, 12(3): e0371023.
4. Venev S V, Zeldovich K B. Thermophilic adaptation in prokaryotes is constrained by metabolic costs of proteostasis. Mol Biol Evol, 2018, 35(1): 211-224.
5. Rousseau M, Oulavallickal T, Williamson A, et al. Characterisation and engineering of a thermophilic RNA ligase from Palaeococcus pacificus. Nucleic Acids Res, 2024, 52(7): 3924-3937.
6. Barabasi A L, Oltvai Z N. Network biology: understanding the cell's functional organization. Nat Rev Genet, 2004, 5(2): 101-113.
7. 常珊, 焦雄, 王美华, 等. 蛋白质氨基酸网络研究进展. 现代生物医学进展, 2011, 11(001): 190-193.
8. Grewal R K, Roy S. Modeling proteins as residue interaction networks. Protein Pept Lett, 2015, 22(10): 923-933.
9. Guan Ruining, Liu Wencheng, Li Ningqi, et al. Machine learning models based on residue interaction network for ABCG2 transportable compounds recognition. Environ Pollut, 2023, 337: 122620.
10. Inan T, Yuce M, Mackerell JR A D, et al. Exploring druggable binding sites on the Class A GPCRs using the residue interaction network and site identification by ligand competitive saturation. ACS Omega, 2024, 9(38): 40154-40171.
11. Hu Guang, Yan Wenying, Zhou Jianhong, et al. Residue interaction network analysis of Dronpa and a DNA clamp. J Theor Biol, 2014, 348: 55-64.
12. Verkhivker G. Molecular dynamics simulations and modelling of the residue interaction networks in the BRAF kinase complexes with small molecule inhibitors: probing the allosteric effects of ligand-induced kinase dimerization and paradoxical activation. Mol Biosyst, 2016, 12(10): 3146-3165.
13. Jiao Xiong, Chang Shan, Li Chunhua, et al. Construction and application of the weighted amino acid network based on residue fluctuations. Phys Rev E Stat Nonlin Soft Matter Phys, 2007, 75(5 Pt 1): 051903.
14. Jiao Xiong, Yang Lifeng, An Meiwen, et al. A modified amino acid network model contains similar and dissimilar weight. Comput Math Methods Med, 2013, 2013(1): 197892.
15. Wang Ziqi, Zhang Yuanyuan, Wang Shudong, et al. SINE: second-order information network embedding. IEEE Access, 2020, 8: 139044-139051.
16. Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations// Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. New York: ACM SIGKDD, 2014: 701-710.
17. Grover A, Leskovec J. node2vec: Scalable feature learning for networks// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016: 855-864.
18. Berman H M, Westbrook J, Feng Z, et al. The protein data bank. Nucleic Acids Res, 2000, 28(1): 235-242.
19. Schober I, Koblitz J, Sardà C J, et al. BacDive in 2025: the core database for prokaryotic strain data. Nucleic Acids Res, 2025, 53(D1): D748-D756.
20. Piovesan D, Minervini G, Tosatto S C. The RING 2. 0 web server for high quality residue interaction networks. Nucleic Acids Res, 2016, 44(W1): W367-W74.
21. Page L, Brin S, Motwani R, et al. The PageRank citation ranking: Bringing order to the web. stanford digital libraries working paper, 1999.
22. Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space. arXiv preprint arXiv, 2013: 1301.3781.
23. Le Q, Mikolov T. Distributed representations of sentences and documents// Proceedings of the 31th International Conference on Machine Learning. Beijing: IMLS, 2014: 1188-1196.
24. Shaw P, Uszkoreit J, Vaswani A. Self-attention with relative position representations. arXiv preprint arXiv, 2018: 1803.02155.

Journal of Biomedical Engineering

Latest ArticlesResearch on prediction model of protein thermostability integrating graph embedding and network topology features

Abstract Full text Figures/Tables Video References Cited by

Format

Content