Abstract
Drug-target interaction (DTIs) prediction is crucial for drug discovery and repositioning, but traditional biological experimental methods are time-consuming and expensive. Therefore, deep learning-based methods have been widely applied in the field of DTIs prediction. In recent years, methods utilizing graph convolutional neural networks to learn the features of drug-protein pairs (DPPs) and thus achieve DTI prediction have achieved certain success. However, these methods struggle to effectively integrate the topological and semantic features of DPPs and capture their interaction relationships when learning the features of DPPs. Therefore, this paper proposes a DTI prediction model named HMFGCN-DTI, which utilizes multi-path graph convolution and graph-level attention mechanism to learn features of DPPs. Experimental results indicate that compared to other state-of-the-art methods, the proposed approach demonstrates higher accuracy and generalization capability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ye, Q., et al.: Drug-target interaction prediction via graph auto-encoder and multi-subspace deep neural networks. IEEE/ACM Trans. Comput. Biol. Bioinform. 20, 2647–2658 (2022)
Li, A., Lin, X., Yu, H.: Inferring DTIs based on similarity clustering and CaGCN-DTI model from heterogeneous network. In: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 2399–2406. IEEE, Location (2021)
Dominguez, C., et al.: HADDOCK: a protein-protein docking approach based on bio-chemical or biophysical information. J. Am. Chem. Soc. 125(7), 1731–1737 (2003)
Bagherian, M., et al.: Machine learning approaches and databases for prediction of drug–target interaction: a survey paper. Briefings Bioinform. 22(3), 247–269 (2020)
Rayhan, F., Ahmed, S., Mousavian, Z., et al.: FRnet-DTI: Deep convolutional neural network for drug-target interaction prediction. Heliyon 6(3) (2020)
Langley, G., et al.: Towards a 21st-century roadmap for biomedical research and drug discovery: consensus report and recommendations. Drug Discovery Today 22(2), 327–339 (2017)
Lin, X., Zhang, X., Xu, X.: Efficient classification of hot spots and hub protein interfaces by recursive feature elimination and gradient boosting. IEEE/ACM Trans. Comput. Biol. Bioinform. 17(5), 1525–1534 (2019)
Xia, Z., et al.: Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces. BMC Syst. Biol. 4, S6–S6 (2010)
Xuan, P., et al.: Prediction of drug–target interactions based on network representation learning and ensemble learning. IEEE/ACM Trans. Comput. Biol. Bioinform. 18(6), 2671–2681 (2020)
Yamanishi, Y., et al.: Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework. Bioinformatics 26(12), i246–i254 (2010)
Luo, Y., et al.: A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nature Communications 8(1), 573 (2017)
Abbasi, K., Razzaghi, P., Poso, A., Ghanbari-Ara, S., Masoudi-Nejad, A.: Deep learning in drug target interaction prediction: current and future perspectives. Curr. Med. Chem. 28(11), 2100–2113 (2021)
Lee, I., Keum, J., Nam, H.: DeepConv-DTI: prediction of drug-target interactions via deep learning with convolution on protein sequences. PLoS Comput. Biol. 15(6), e1007129 (2019)
Torng, W., Altman, R.B.: Graph convolutional neural networks for predicting drug-target interactions. J. Chem. Inf. Model. 59(10), 4131–4149 (2019)
Nguyen, T., Le, H., Quinn, T.P., et al.: GraphDTA: predicting drug–target binding affinity with graph neural networks. Bioinformatics 37(8), 1140–1147 (2021)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Sun, M., et al.: Graph convolutional networks for computational drug development and discovery. Briefings Bioinform. 21(3), 919–935 (2020)
Feng, Q., et al.: Padme: A deep learning-based framework for drug-target interaction prediction. arXiv preprint arXiv:1807.09741 (2018)
Wan, F., Hong, L., Xiao, A., et al.: NeoDTI: neural integration of neighbor information from a heterogeneous network for discovering new drug–target interactions. Bioinformatics 35(1), 104–111 (2019)
Zhao, T., et al.: Identifying drug–target interactions based on graph convolutional network and deep neural network. Briefings Bioinform. 22(2), 2141–2150 (2021)
Tian, Z., et al.: MHADTI: predicting drug–target interactions via multiview heterogeneous information network embedding with hierarchical attention mechanisms. Briefings Bioinform. 23(6), bbac434 (2022)
Iorio, F., et al.: Discovery of drug mode of action and drug repositioning from transcriptional responses. Proc. Natl. Acad. Sci. 107(33), 14621–14626 (2010)
Abeywickrama, T., Cheema, M.A., Taniar, D.: K-nearest neighbors on road networks: a journey in experimentation and in-memory implementation. arXiv preprint arXiv:1601.01549 (2016)
Zheng, Y., Peng, H., Zhang, X., et al.: Predicting drug targets from heterogeneous spaces using anchor graph hashing and ensemble learning. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2018)
Li, Y., Qiao, G., Gao, X., Wang, G.: Supervised graph co-contrastive learning for drug–target interaction prediction. Bioinformatics 38(10), 2847–2854 (2022)
Peng, J., et al.: An end-to-end heterogeneous graph representation learning-based framework for drug–target interaction prediction. Briefings Bioinform. 22(5), bbaa430 (2021)
Li, J., et al.: IMCHGAN: inductive matrix completion with heterogeneous graph attention networks for drug-target interactions prediction. IEEE/ACM Trans. Comput. Biol. Bioinform. 19(2), 655–665 (2021)
Acknowledgment
. This work is supported by the National Natural Science Foundation of China (No. 61972299, 62372342). The authors thank the members of Machine Learning and Artificial Intelligence Laboratory, School of Computer Science and Technology, Wuhan University of Science and Technology, for their helpful discussion within seminars.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, W., Zhang, X., Lin, X., Hu, J. (2024). Drug-Target Interaction Prediction Based on Multi-path Graph Convolution and Graph-Level Attention Mechanism. In: Huang, DS., Pan, Y., Zhang, Q. (eds) Advanced Intelligent Computing in Bioinformatics. ICIC 2024. Lecture Notes in Computer Science(), vol 14882. Springer, Singapore. https://doi.org/10.1007/978-981-97-5692-6_13
Download citation
DOI: https://doi.org/10.1007/978-981-97-5692-6_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5691-9
Online ISBN: 978-981-97-5692-6
eBook Packages: Computer ScienceComputer Science (R0)