Multimodal Cross-scale Feature Fusion for Drug-Target Affinity Prediction

NAVIGATE

Table of Contents

STATISTICS

Viewed20

Downloads48

Multimodal Cross-scale Feature Fusion for Drug-Target Affinity Prediction

PDF下载 (48)

[1]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(XX):1-8.[doi:10.13705/j.issn.1671-6833.2026.04.001]

Copy

Journal of Zhengzhou University (Engineering Science)[ISSN 1671-6833/CN 41-1339/T] Volume: 47 Number of periods: 2026 XX Page number: 1-8 Column: Public date: 2026-09-10

Title:: Multimodal Cross-scale Feature Fusion for Drug-Target Affinity Prediction

Author(s):: ZHENG Hong ; LUO Yujian; LING Kan; F AN Guisheng; School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China

Keywords:: graph neural network; drug-target affinity prediction; feature learning; cross-scale feature fusion; drug development

CLC:: TP183R91R318

DOI:: 10.13705/j.issn.1671-6833.2026.04.001

Abstract:: To address the current challenges of relying solely on single-modal features of target proteins and neglecting network-scale features in biological networks, a drug-target affinity prediction (DTA) model based on multimodal cross-scale feature fusion was proposed. Target proteins as both sequences and graphs for feature extraction were presented, extracting semantic and topological features, respectively, to enhance the target proteins’ feature representation. 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, enriching the feature representations of both target proteins and drug molecules. Experimental results on the DAVIS and KIBA datasets demonstrated that, compared to the more advanced model, the proposed model achieved reductions in MSE by 0.015 and 0.003, respectively, and increases in CI by 0.005 and 0.004, improving the accuracy and stability of affinity prediction. It demonstrated the effectiveness of multimodal and cross-scale feature fusion in DTA prediction tasks.

References:: [1] DING Y J, TANG J J, GUO F. Identification of drug-target interactions via multi-view graph regularized link propagation model[J]. Neurocomputing, 2021, 461: 618-631.
[2] HE T, HEIDEMEYER M, BAN F Q, et al. SimBoost: a read-across approach for predicting drug-target binding affinities using gradient boosting machines[J]. Journal of Cheminformatics, 2017, 9(1): 24.
[3] ÖZTÜRK H, ÖZGÜR A, ÖZKIRIMLI E. DeepDTA: deep drug-target binding affinity prediction[J]. Bioinformatics, 2018, 34(17): i821-i829.
[4] ZHAO Q C, XIAO F, YANG M Y, et al. AttentionDTA: prediction of drug-target binding affinity using attention model[C]//2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Piscataway: IEEE, 2019: 64-69.
[5] YUAN W N, CHEN G X, CHEN C Y. FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction[J]. Briefings in Bioinformatics, 2022, 23(1): 1-13.
[6] ZHAO L L, WANG J J, PANG L, et al. GANsDTA: predicting drug-target binding affinity using GANs[J]. Frontiers in Genetics, 2020, 10: 1243.
[7] NGUYEN T, LE H, 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] 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.
CHENG Z P, LI J H. Drug-target affinity prediction based on graph convolution network and bilinear attention network[J]. Journal of East China University of Science and Technology, 2024, 50(4): 594-601.
[10] HE H H, CHEN G X, CHEN C Y. NHGNN-DTA: a node-adaptive hybrid graph neural network for interpretable drug-target binding affinity prediction[J]. Bioinformatics, 2023, 39(6): 1-9.
[11] YANG X X, YANG G K, CHU J. 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 J R, XIAO Y H, SHANG X Q, et al. Predicting drug-target binding affinity with cross-scale graph contrastive learning[J]. Briefings in Bioinformatics, 2024, 25(1): 1-9.
[13] BI X P, ZHANG S G, MA W J, 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[EB/OL]. (2016-09-09)[2025-09-04]. 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 M J, LI Z, ZHANG S G, 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 Y, et al. Language models generalize beyond natural proteins[EB/OL]. (2022-12-22)[2025-09-01]. 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[EB/OL]. (2023-08-02)[2025-09-04]. https://arxiv.org/abs/1706.03762.
[19] YIN W P, KANN K, YU M, et al. Comparative study of CNN and RNN for natural language processing[EB/OL]. (2017-02-07)[2025-09-04]. 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 J, 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 Z D, ZHONG W H, ZHAO L, et al. MGraphD-TA: deep multiscale graph neural network for explainable drug-target binding affinity prediction[J]. Chemical Science, 2022, 13(3): 816-833.
[25] QIU W J, LIANG Q L, YU L Y, et al. LSTM-SAGDTA: predicting drug-target binding affinity with an attention graph neural network and LSTM approach[J]. Current Pharmaceutical Design, 2024, 30(6): 468-476.
[26] HUANG J P, SUN C, LI M L, 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): 1-11.

Similar References:

Memo

Last Update: 2026-01-13