Abstract
Drug-Target Interaction (DTI) prediction usually devotes to accurately identify the potential binding targets on proteins so as to guide the drug development. However, the sparse imbalance of known drug-target pairs remains a challenge for high-quality representation learning of drugs and targets, interfering with accurate prediction. The labeled drug-target pairs are far less than the missed since the obtained DTIs are recorded with pathogenic proteins and sophisticated bio-experiments. Therefore, we propose a deep learning paradigm via Heterogeneous graph data Augmentation and node Similarity (HAS) to solve the sparse imbalanced problem on drug-target interaction prediction. Heterogeneous graph data augmentation is devised to generate multi-view augmented graphs through a heterogeneous neighbors sampling strategy. Then the consistency across different graph structures is captured using graph contrastive optimization. Node similarity is calculated on the heterogeneous entity association matrices, aiming to integrate similarity information and heterogeneous attribute gain for drug-target interaction prediction. Extensive experiments show that HAS offers superior performance in sparse imbalanced scenarios compared state-of-the-art methods. Ablation studies prove the effectiveness of heterogeneous graph data augmentation and node similarity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sun, M., Zhao, S., Gilvary, C.: Graph convolutional networks for computational drug development and discovery. Briefings in bioinformatics 21(3), 919–935 (2020)
Vamathevan, J., Clark, D., Czodrowski, P.: Applications of machine learning in drug discovery and development. Nature Reviews Drug Discovery 18(6), 463–477 (2019)
Bagherian, M., Sabeti, E., Wang, K.: Machine learning approaches and databases for prediction of drug-target interaction: a survey paper. Briefings in bioinformatics 22(1), 247–269 (2021)
Hakime, Ö.: zgür Arzucan and Elif O: DeepDTA: Deep Drug-Target Binding Affinity Prediction. Bioinformatics 34(17), 821–829 (2018)
Lee I, Keum J, Nam H: DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences. PLoS Comput Biol (2019)
Nguyen, T., Le, H., Quinn, T.P.: GraphDTA: Predicting drug-target binding affinity with graph neural networks. Bioinformatics 37(8), 1140–1147 (2021)
Huang, K., Xiao, C., Glass, L.M.: MolTrans: Molecular Interaction Transformer for drug-target interaction prediction. Bioinformatics 37(6), 830–836 (2021)
Chen, L., Tan, X., Wang, D.: TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36(16), 4406–4414 (2020)
Chen H, Li J: Modeling Relational Drug-Target-Disease Interactions via Tensor Factorization with Multiple Web Sources. In: WWW (2019)
Wan, F., Hong, L., Xiao, A.: NeoDTI: neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions. Bioinformatics 35(1), 104–111 (2019)
Zhou D, Xu Z, Li W T: MultiDTI: drug-target interaction prediction based on multi-modal representation learning to bridge the gap between new chemical entities and known heterogeneous network. Bioinformatics, (2021)
Xia, X.: Bioinformatics and drug discovery. Current topics in medicinal chemistry 17(15), 1709–1726 (2017)
Qiu J, Chen Q, Dong Y: Gcc: Graph contrastive coding for graph neural network pre-training. In: KDD, pp. 1150–1160 (2020)
You Y, Chen T, Sui Y: Graph contrastive learning with augmentations. In: NeurIPS, pp. 5812–5823 (2020)
L. S. Jung and Y. -R. Cho: Survey of network-based approaches of drug-target interaction prediction. In: BIBM, pp. 1793–1796 (2020)
Wu, Z., Pan, S., Chen, F.: A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems 32(1), 4–24 (2020)
Y Zeng, X Chen, Y Luo: Deep drug-target binding affinity prediction with multiple attention blocks. Briefings in Bioinformatics, (2021)
Peng J, Wang Y, Guan J: An end-to-end heterogeneous graph representation learning-based framework for drug-target interaction prediction. Briefings in Bioinformatics, (2021)
Zhang C, Song D, Huang C: Heterogeneous graph neural network. In: KDD, pp. 793–803 (2019)
Wang X, Ji H, Shi C: Heterogeneous graph attention network. In: WWW, pp. 2022–2032 (2019)
Wu J, Wang X, Feng F: Self-supervised graph learning for recommendation. In: SIGIR, pp. 726–735 (2021)
Luo, Y., Zhao, X., Zhou, J.: A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nature communications 8(1), 1–13 (2017)
Acknowledgements
This work was supported by the National Natural Science Foundation of China (61503273, 61702356), Industry-University Cooperation Education Program of the Ministry of Education, and Shanxi Scholarship Council of China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, R., Zhang, Z., Zhang, Y., Jiang, Z., Sun, S., Zhang, C. (2022). Sparse Imbalanced Drug-Target Interaction Prediction via Heterogeneous Data Augmentation and Node Similarity. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_43
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)