[1]郑红,罗俞建,凌侃,等.多模态跨尺度特征融合的药物靶标亲和力预测[J].郑州大学学报(工学版),2026,47(4):58-65.[doi:10.13705/j.issn.1671-6833.2026.04.001]
　ZHENG Hong,LUO Yujian,LING Kan,et al.Multimodal Cross-scale Feature Fusion for Drug-Target Affinity Prediction[J].Journal of Zhengzhou University (Engineering Science),2026,47(4):58-65.[doi:10.13705/j.issn.1671-6833.2026.04.001]
点击复制

多模态跨尺度特征融合的药物靶标亲和力预测()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
47
期数:
2026年4期
页码:
58-65
栏目:
出版日期:
2026-07-10

文章信息/Info

Title:
Multimodal Cross-scale Feature Fusion for Drug-Target Affinity Prediction
文章编号:
1671-6833(2026)04-0058-08
作者:
郑红, 罗俞建, 凌侃, 范贵生
华东理工大学 信息科学与工程学院,上海 200237
Author(s):
ZHENG Hong, LUO Yujian, LING Kan, FAN Guisheng
School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237,China
关键词:
图神经网络;  药物靶标亲和力预测;  特征学习;  跨尺度特征融合;  药物研发
Keywords:
graph neural network;  drug-target affinity prediction;  feature learning;  cross-scale feature fusion;  drug development
分类号:
TP183R91R318
DOI:
10.13705/j.issn.1671-6833.2026.04.001
文献标志码:
A
摘要:
针对当前研究仅依赖靶标蛋白单一模态特征以及忽略生物网络中网络尺度特征信息的问题,提出一种基于多模态跨尺度特征融合的药物靶标亲和力(DTA)预测模型。 将靶标蛋白表示为序列和图两种模态进行特征提取,分别提取其语义特征和拓扑结构特征从而增强靶标蛋白的特征表示;分析药物与靶标蛋白强亲和力关系从而构建药物靶标相互作用异构图网络,利用跨尺度特征融合方法有效融合异构图网络尺度特征,从而丰富靶标蛋白与药物分子的特征表示。 在 DAVIS 和 KIBA 两个数据集上的实验结果表明:与当前比较先进的模型 SISDTA 相比,所提模型的 MSE 分别降低了 0. 015 和 0. 003,CI 分别提高了 0. 005 和 0. 004,亲和力预测的准确性与稳定性有所提高,验证了多模态跨尺度特征融合在 DTA 预测任务中的有效性。
Abstract:
To address the current challenges in relying solely on single-modal features of target proteins and neglec-tingnetwork-scale features of biological networks, a drug-target affinity prediction (DTA) model based on multimo-dalcross-scale feature fusion was proposed. Target proteins both as sequences and graphs for feature extraction were presented, with semantic and topological features respectively, to enhance the target proteins′ feature representa-tion.The strong affinity relationships between drugs and target proteins were analyzed to construct a heterogeneous graph network of drug-target interaction. A cross-scale feature fusion method was then used to effectively integrate the scale features of the heterogeneous graph network, then to enrich the feature representations of both target pro-teinsand drug molecules. Experimental results on the DAVIS and KIBA datasets demonstrated that, compared with the more advanced model SISDTA, the proposed model achieved reductions in MSE by 0. 015 and 0. 003, respectively,and increases in CI by 0. 005 and 0. 004, respectively, improving the accuracy and stability of affinity pre-diction.It demonstrated the effectiveness of multimodal and cross-scale feature fusion in DTA prediction tasks.

参考文献/References:

[1] Ding Yijie, Tang Jijun, Guo Fei. Identification of drug-target interactions via multi-view graph regularized link propagation model[J]. Neurocomputing, 2021, 461: 618–631.
[2] He Tong, Heidemeyer M, Ban Fuqiang, et al. SimBoost: a read-across approach for predicting drug-target binding affinities using gradient boosting machines[J]. Journal of Cheminformatics, 2017, 9: 24.
[3] Öztürk H, Özgür A, Ozkirimli E. DeepDTA: deep drug-target binding affinity prediction[J]. Bioinformatics, 2018, 34(17): i821–i829.
[4] Zhao Qichang, Xiao Fen, Yang Mengyun, et al. AttentionDTA: prediction of drug-target binding affinity using attention model[C]//Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Piscataway: IEEE, 2019: 64–69.
[5] Yuan Weining, Chen Guanxing, Chen C Y C. FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction[J]. Briefings in Bioinformatics, 2022, 23(1): bbab506.
[6] Zhao Lingling, Wang Junjie, Pang Long, et al. GANsDTA: predicting drug-target binding affinity using GANs[J]. Frontiers in Genetics, 2020, 10: 1243.
[7] Nguyen T, Le Hang, Quinn T P, et al. GraphDTA: predicting drug-target binding affinity with graph neural networks[J]. Bioinformatics, 2021, 37(8): 1140–1147.
[8] Mukherjee S, Ghosh M, Basuchowdhuri P. DeepGLSTM: deep graph convolutional network and LSTM based approach for predicting drug-target binding affinity[C]//SIAM International Conference on Data Mining. Philadelphia: Society for Industrial and Applied Mathematics, 2022: 729–737.
[9] Cheng Zhuping, Li Jianhua. Drug-target affinity prediction based on graph convolution network and bilinear attention network[J]. Journal of East China University of Science and Technology (Natural Science Edition), 2024, 50(4): 594–601. [程竹平，李建华. 基于图卷积和双线性注意力网络的药物靶标亲和力预测[J]. 华东理工大学学报(自然科学版)，2024，50(4)：594–601.]
[10] He Haohuai, Chen Guanxing, Chen C Y C. NHGNN-DTA: a node-adaptive hybrid graph neural network for interpretable drug-target binding affinity prediction[J]. Bioinformatics, 2023, 39(6): btad355.
[11] Yang Xinxing, Yang Genke, Chu Jian. GraphCL-DTA: a graph contrastive learning with molecular semantics for drug-target binding affinity prediction[J]. IEEE Journal of Biomedical and Health Informatics, 2024, 28(8): 4544–4552.
[12] Wang Jingru, Xiao Yihang, Shang Xuequn, et al. Predicting drug-target binding affinity with cross-scale graph contrastive learning[J]. Briefings in Bioinformatics, 2023, 25: bbad516.
[13] Bi Xiangpeng, Zhang Shugang, Ma Wenjian, et al. HiSIF-DTA: a hierarchical semantic information fusion framework for drug-target affinity prediction[J]. IEEE Journal of Biomedical and Health Informatics, 2025, 29(3): 1579–1590.
[14] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks [PP/OL]. V4. arXiv (2017−02−22)[2025−12−04]. https://arxiv.org/abs/1609.02907.
[15] Ramsundar B, Eastman P, Walters P, et al. Deep learning for the life sciences: applying deep learning to genomics, microscopy, drug discovery, and more[M]. Sebastopol: O’Reilly, 2019.
[16] Jiang Mingjian, Li Zhen, Zhang Shugang, et al. Drug-target affinity prediction using graph neural network and contact maps[J]. RSC Advances, 2020, 10(35): 20701–20712.
[17] Verkuil R, Kabeli O, Du Yilun, et al. Language models generalize beyond natural proteins[PP/OL]. V1. bioRxiv (2022−12−22)[2025−12−04]. https://www.biorxiv.org/content/10.1101/2022.12.21.521521v1.
[18] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[PP/OL]. V7. arXiv (2023−08−02)[2025−12−04]. https://arxiv.org/abs/1706.03762.
[19] Yin Wenpeng, Kann K, Yu Mo, et al. Comparative study of CNN and RNN for natural language processing[PP/OL]. V1. arXiv(2017−02−07)[2025−12−04]. https://arxiv.org/abs/1702.01923.
[20] Davis M I, Hunt J P, Herrgard S, et al. Comprehensive analysis of kinase inhibitor selectivity[J]. Nature Biotechnology, 2011, 29(11): 1046–1051.
[21] Tang Jing, Szwajda A, ShakyaWar S, et al. Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis[J]. Journal of Chemical Information and Modeling, 2014, 54(3): 735–743.
[22] Allen D M. Mean square error of prediction as a criterion for selecting variables[J]. Technometrics, 1971, 13(3): 469–475.
[23] Gönen M, Heller G. Concordance probability and discriminatory power in proportional hazards regression[J]. Biometrika, 2005, 92(4): 965–970.
[24] Yang Ziduo, Zhong Weihe, Zhao Lu, et al. MGraph-DTA: deep multiscale graph neural network for explainable drug-target binding affinity prediction[J]. Chemical Science, 2022, 13(3): 816–833.
[25] Qiu Wenjing, Liang Qianle, Yu Liyi, et al. LSTM-SAG-DTA: predicting drug-target binding affinity with an attention GraphNeural network and LSTM approach[J]. Current Pharmaceutical Design, 2024, 30(6): 468–476.
[26] Huang Jipeng, Sun Chang, Li Minglei, et al. Structure-inclusive similarity based directed GNN: a method that can control information flow to predict drug-target binding affinity[J]. Bioinformatics, 2024, 40(10): btae563.

相似文献/References:

[1]郝武帮,段文强,李　 琰,等.基于GNN-FOCOPS的配电网动态集群划分方法[J].郑州大学学报(工学版),2027,48(XX):1.[doi:10. 13705 / j. issn. 1671-6833. 2026. 06. 003]
　HAO Wubang,DUAN Wenqiang,LI Yan,et al.A Dynamic Clustering Method for Distribution Networks Based on GNN-FOCOPS[J].Journal of Zhengzhou University (Engineering Science),2027,48(4):1.[doi:10. 13705 / j. issn. 1671-6833. 2026. 06. 003]
[2]韩继辉,石玉鹏,黄子奇,等.结构-特征协同防御的图神经网络[J].郑州大学学报(工学版),2026,47(4):134.[doi:10.13705/j.issn.1671-6833.2026.04.010]
　HAN Jihui,SHI Yupeng,HUANG Ziqi,et al.A Graph Neural Network for Structure-Feature Collaborative Defense[J].Journal of Zhengzhou University (Engineering Science),2026,47(4):134.[doi:10.13705/j.issn.1671-6833.2026.04.010]

更新日期/Last Update: 2026-10-21