|
|
CT-CPI：基于整合CNN模块与Transformer的化合物–蛋白质相互作用深度学习模型
|
Abstract:
本文构建了一个新的预测化合物–蛋白质关联关系的端到端的模型，可直接输入样本序列后直接输出预测结果，命名为“CT-CPI”。在此方法中，模型主要由嵌入模块、CNN模块、transformer模块、合并模块以及多层感知机模块组成。本文对嵌入方法、transformer模型进行了改进，主要表现为优化了嵌入样本信息的语义可解释性以及在模型中将样本信息充分利用。该模型在基于不同的数据集进行实验时结果显示：基于Davis数据库提供的数据集作为实验数据下，模型预测的AUC值达到了95.6%，模型以DrugBank数据库为数据集时，模型预测效果达到了95.8%。结果表明：与传统模型相比，我们的模型具有更好的预测结果。
In this article, we constructed a new end-to-end model for predicting compound-protein associations, which can directly input sample sequences and then directly output the prediction results, named “CT-CPI”. In this method, the model is mainly composed of embedding module, CNN module, transformer module, merging module and multilayer perceptron module. In this paper, the embedding method and transformer model are improved, mainly in terms of optimising the semantic interpretability of the embedded sample information and making full use of the sample information in the model. The results of the model based on different datasets show that the model predicts 95.6% of the AUC value based on the dataset provided by Davis database as the experimental data, and 95.8% of the model prediction effect when the model uses DrugBank database as the dataset. The results show that: our model has better prediction results compared to the traditional model.
| [1] | Knowles, J. and Gromo, G. (2003) A Guide to Drug Discovery: Target Selection in Drug Discovery. Nature Reviews Drug Discovery, 2, 63-69. https://doi.org/10.1038/nrd986 |
| [2] | Unterthiner, T., Mayr, A., Klambauer, G., et al. (2014) Deep Learning as an Opportunity in Virtual Screening. Deep Learning Workshop at NIPS, 27, 1-9. |
| [3] | Bredel, M. and Jacoby, E. (2004) Chemogenomics: An Emerging Strategy for Rapid Target and Drug Discovery. Nature Reviews Genetics, 5, 262-275. https://doi.org/10.1038/nrg1317 |
| [4] | Shi, B.G., Bai, X. and Yao, C. (2016) An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence, 39, 2298-2304. http://arxiv.org/abs/1507.05717v1 |
| [5] | ？ztürk, H., ？zgür, A. and Ozkirimli, E. (2018) DeepDTA: Deep Drug-Target Binding Affinity Prediction. Bioinformatics, 34, i821-i829. https://doi.org/10.1093/bioinformatics/bty593 |
| [6] | Lee, I., Keum, J. and Nam, H. (2019) DeepConv-DTI: Prediction of Drug Protein Interactions via Deep Learning with Convolution on Protein Sequences. PLOS Computational Biology, 15, e1007129. https://doi.org/10.1371/journal.pcbi.1007129 |
| [7] | Nguyen, T., Le, H., Quinn, T.P., et al. (2020) GraphDTA: Predicting Drug-Protein Binding Affinity with Graph Neural Networks. Bioinformatics, 37, 1140-1147. https://doi.org/10.1101/684662 |
| [8] | Li, G.D., Sun, W.C., Xu, J.S., et al. (2023) GA-ENs: A Novel Drug-Target Interactions Prediction Method by Incorporating Prior Knowledge Graph into Dual Wasserstein Generative Adversarial Network with Gradient Penalty. Applied Soft Computing, 139, Article 110151. |
| [9] | Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. https://doi.org/10.48550/arXiv.1706.03762 |
| [10] | Chen, L., Tan, X., Wang, D., et al. (2020) TransformerCPI: Improving Compound-Protein Interaction Prediction by Sequence-Based Deep Learning with Self-Attention Mechanism and Label Reversal Experiments. Bioinformatics, 36, 4406-4414. https://doi.org/10.1093/bioinformatics/btaa524 |
| [11] | Huang, K., Xiao, C., Glass, L., et al. (2021) MolTrans: Molecular Interaction Transformer for Drug-Protein Interaction Prediction. Bioinformatics, 37, 830-836. https://doi.org/10.1093/bioinformatics/btaa880 |
| [12] | Zhao, Q., Zhao, H., Zheng, K., et al. (2021) HyperAttentionDTI: Improving Drug-Protein Interaction Prediction by Sequence-Based Deep Learning with Attention Mechanism. Bioinformatics, 38, 655-662. https://doi.org/10.1093/bioinformatics/btab715 |
| [13] | Wishart, D.S., Knox, C., Guo, A.C., et al. (2016) DrugBank: A Comprehensive Resource for in Silico Drug Discovery and Exploration. Nucleic Acids Research, 34, 668. https://doi.org/10.1093/nar/gkj067 |
| [14] | Davis, M.I., Hunt, J.P., Herrgard, S., et al. (2011) Comprehensive Analysis of Kinase Inhibitor Selectivity. Nature Biotechnology, 29, 1046-1051. https://doi.org/10.1038/nbt.1990 |
| [15] | Toropov, A.A., Toropova, A.P. and Benfenati, E. (2010) Simplified Molecular Input Line Entry System-Based Optimal Descriptors: Quantitative Structure-Activity Relationship Modeling Mutagenicity of Nitrated Polycyclic Aromatic Hydrocarbons. Chemical Biology & Drug Design, 73, 515-525. https://doi.org/10.1111/j.1747-0285.2009.00802.x |
