Drug-target interaction prediction based on structure-network collaborative features and grid-attention enhanced Kolmogorov-Arnold network

doi:10.11772/j.issn.1001-9081.2025040505

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (4): 1344-1353.DOI: 10.11772/j.issn.1001-9081.2025040505

• Frontier and comprehensive applications • Previous Articles

Drug-target interaction prediction based on structure-network collaborative features and grid-attention enhanced Kolmogorov-Arnold network

Xumeng DOU¹, Bin XIE¹^,²^,³(), Zhaohui ZHANG¹^,²^,³, Zhengang ZHAO¹, Hanyu DUAN¹, Aolei GUO¹

^1.College of Computer and Cyber Security，Hebei Normal University，Shijiazhuang Hebei 050024，China
^2.Hebei Provincial Key Laboratory of Network and Information Security （Hebei Normal University），Shijiazhuang Hebei 050024，China
^3.Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics and Data Security （Hebei Normal University），Shijiazhuang Hebei 050024，China

Received:2025-05-08 Revised:2025-08-08 Accepted:2025-08-11 Online:2025-08-15 Published:2026-04-10
Contact: Bin XIE
About author:DOU Xumeng， born in 2001， M. S. candidate. Her research interests include machine learning， bioinformatics.
ZHANG Zhaohui， born in 1969， Ph. D.， associate professor. Her research interests include machine learning， image recognition.
ZHAO Zhengang， born in 1986， Ph. D.， experimentalist. His research interests include image processing， bioinformatics.
DUAN Hanyu， born in 2001， M. S. candidate. Her research interests include machine learning， bioinformatics.
GUO Aolei， born in 1999， M. S. candidate. His research interests include machine learning， remote sensing image processing.
Supported by:
National Natural Science Foundation of China(62476078);Central Government Guided Local Science and Technology Development Fund(236Z0104G)

基于结构‒网络协同特征与网格注意力增强KAN的药物靶标相互作用预测

豆旭梦¹, 解滨¹^,²^,³(), 张朝晖¹^,²^,³, 赵振刚¹, 段菡煜¹, 郭澳磊¹

^1.河北师范大学计算机与网络空间安全学院，石家庄 050024
^2.河北省网络与信息安全重点实验室（河北师范大学），石家庄 050024
^3.供应链大数据分析与数据安全河北省工程研究中心（河北师范大学），石家庄 050024

通讯作者: 解滨
作者简介:豆旭梦（2001—），女，河北邯郸人，硕士研究生，主要研究方向：机器学习、生物信息学
张朝晖（1969—），女，河北乐亭人，副教授，博士，CCF会员，主要研究方向：机器学习、图像识别
赵振刚（1986—），男，河北武安人，实验师，博士，主要研究方向：图像处理、生物信息学
段菡煜（2001—），女，河北石家庄人，硕士研究生，主要研究方向：机器学习、生物信息学
郭澳磊（1999—），男，河北邯郸人，硕士研究生，主要研究方向：机器学习、遥感图像处理。
基金资助:
国家自然科学基金资助项目(62476078);中央引导地方科技发展基金资助项目(236Z0104G)

Abstract

Abstract:

Drug-Target Interaction （DTI） prediction is a key task in drug discovery and repurposing. The challenge lies in how to integrate multi-source heterogeneous features to characterize the complex relationships between drugs and targets comprehensively. To address the shortcomings of traditional methods that rely on a single data source and model complex nonlinear relationships in a low-quality way， a DTI prediction method based on Structure-Network collaborative features and grid-attention enhanced KAN （Kolmogorov-Arnold Network）（SNKDTI） was proposed. Firstly， a feature extraction strategy based on structure and network collaboration was designed： for drug representation， molecular fingerprints were fused with graph embedding methods to quantify chemical structures； for target representation， traditional physicochemical encoding was combined with pre-trained models to extract sequence features. Meanwhile， heterogeneous networks such as drug-disease associations and protein-protein interactions were introduced， network topological features were extracted by using the Random Walk with Restart （RWR） algorithm， and the features were compressed by using a Denoising AutoEncoder （DAE）， so as to integrate structural and network information of drugs and targets. Secondly， a Heterogeneous Biological Information Network （HBIN） was constructed to carry out feature propagation by using a Graph Convolutional Network （GCN）. Additionally， a Grid-Attention enhanced KAN （GA-KAN） was proposed， which introduced multiple learnable B-spline basis function grids and attention mechanisms to achieve adaptive combinations of multiple nonlinear mapping modules， thereby enhancing the model’s expressive power and input adaptability. Finally， a Gradient Boosting Decision Tree （GBDT） was used to build an end-to-end prediction framework. Experimental results of comparing the proposed method and benchmark methods on public datasets show that SNKDTI achieves improvements of 0.81%， 1.36%， and 3.29% in Area Under the receiver operating characteristic Curve （AUC）， Area Under the Precision-Recall curve （AUPR）， and F1-score， respectively， over the best-performing benchmark methods. The above prove that SNKDTI enhances accuracy， robustness， and generalization ability significantly， providing an efficient tool for new drug target screening.

Key words: Drug-Target Interaction (DTI) prediction, structure-network collaborative feature, KAN (Kolmogorov-Arnold Network), Graph Neural Network (GNN), attention mechanism

摘要：

药物?靶标相互作用（DTI）预测是药物发现与再利用的关键任务，它的难点是融合多源异构特征以全面表征药物与靶标间的复杂关联。针对传统方法依赖单一数据源的问题和建模复杂非线性关系方面的不足，提出一种基于结构?网络协同特征与网格注意力增强的KAN（Kolmogorov-Arnold Network）的DTI预测方法（SNKDTI）。首先，设计结构与网络协同的特征提取策略：在药物表示方面，融合分子指纹与图嵌入方法以量化化学结构；在靶标表示方面，结合传统物理化学编码与预训练模型提取序列特征；同时，引入药物?疾病关联和蛋白质相互作用等异构网络，基于重启随机游走（RWR）算法提取网络的拓扑特征，并利用去噪自编码器（DAE）压缩特征，从而融合药物与靶标的结构与网络信息；其次，构建异质生物信息网络（HBIN），使用图卷积网络（GCN）传播特征，并提出一种网格注意力增强的KAN（GA-KAN），以通过引入多组可学习的B样条基函数网格与注意力机制，实现多个非线性映射模块的自适应组合，从而增强模型的表达能力与输入适应性；最后，使用梯度提升决策树（GBDT）构建端到端预测框架。在公开数据集上的对比实验结果表明，SNKDTI的特征曲线下面积（AUC）、精确度?召回率曲线下面积（AUPR）和F1-score相较于对应指标的最优基准方法分别提升了0.81%、1.36%和3.29%。以上验证了SNKDTI在准确性、鲁棒性和泛化能力方面均有显著提升，可为新药靶标筛选提供高效工具。

关键词: 药物?靶标相互作用预测, 结构?网络协同特征, Kolmogorov-Arnold网络, 图神经网络, 注意力机制

CLC Number:

TP183

Xumeng DOU, Bin XIE, Zhaohui ZHANG, Zhengang ZHAO, Hanyu DUAN, Aolei GUO. Drug-target interaction prediction based on structure-network collaborative features and grid-attention enhanced Kolmogorov-Arnold network[J]. Journal of Computer Applications, 2026, 46(4): 1344-1353.

豆旭梦, 解滨, 张朝晖, 赵振刚, 段菡煜, 郭澳磊. 基于结构‒网络协同特征与网格注意力增强KAN的药物靶标相互作用预测[J]. 《计算机应用》唯一官方网站, 2026, 46(4): 1344-1353.

Figures/Tables 15

References 36

[1]	刘一迪，温自豪，任富香，等. 自适应球形演化的药物‒靶标相互作用预测方法［J］. 计算机应用， 2024， 44（3）： 989-994.
	LIU Y D， WEN Z H， REN F X， et al. Self-adaptive spherical evolution for prediction of drug target interaction［J］. Journal of Computer Applications， 2024， 44（3）： 989-994.
[2]	MAROUA A， TIAN G， WANG R， et al. TriCvT-DTI： predicting drug-target interactions using trimodal representations and convolutional vision Transformers［J］. IEEE Journal of Biomedical and Health Informatics， 2025， 29（6）： 4585-4592.
[3]	刘晓光，李梅. 基于深度学习的药物‒靶标相互作用预测研究综述［J］. 智能系统学报， 2024， 19（3）： 494-524.
	LIU X G， LI M. A survey of deep learning-based drug-target interaction prediction［J］. CAAI Transactions on Intelligence Systems， 2024， 19（3）： 494-524.
[4]	YU D， LIU H， YAO S. Drug-target interaction prediction based on improved heterogeneous graph representation learning and feature projection classification［J］. Expert Systems with Applications， 2024， 252（Pt B）： No.124289.
[5]	CUI S， YU S， HUANG H Y， et al. miRTarBase 2025： updates to the collection of experimentally validated microRNA-target interactions［J］. Nucleic Acids Research， 2025， 53（D1）： D147-D156.
[6]	ZHANG Z， CHEN L， ZHONG F， et al. Graph neural network approaches for drug-target interactions［J］. Current Opinion in Structural Biology， 2022， 73： No.102327.
[7]	ZHAO W， YU Y， LIU G， et al. MSI-DTI： predicting drug-target interaction based on multi-source information and multi-head self-attention［J］. Briefings in Bioinformatics， 2024， 25（3）： No.bbae238.
[8]	ZHU Z， ZHENG X， QI G， et al. Drug-target binding affinity prediction model based on multi-scale diffusion and interactive learning［J］. Expert Systems with Applications， 2024， 255（Pt B）： No.124647.
[9]	BLEAKLEY K， YAMANISHI Y. Supervised prediction of drug-target interactions using bipartite local models［J］. Bioinformatics， 2009， 25（18）： 2397-2403.
[10]	PERLMAN L， GOTTLIEB A， ATIAS N， et al. Combining drug and gene similarity measures for drug-target elucidation［J］. Journal of Computational Biology， 2011， 18（2）： 133-145.
[11]	LUO Y， ZHAO X， ZHOU J， et al. A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information［J］. Nature Communications， 2017， 8： No.573.
[12]	WAN F， HONG L， XIAO A， et al. NeoDTI： neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions［J］. Bioinformatics， 2019， 35（1）： 104-111.
[13]	张家豪，王琪，刘明铭，等. 基于序列和多视角网络的药物‒靶标相互作用预测［J］. 计算机应用， 2025， 45（11）： 3658-3665.
	ZHANG J H， WANG Q， LIU M M， et al. Prediction of drug-target interactions based on sequence and multi-view networks［J］. Journal of Computer Applications， 2025， 45（11）： 3658-3665.
[14]	WEININGER D. SMILES， a chemical language and information system. 1. Introduction to methodology and encoding rules［J］. Journal of Chemical Information and Computer Sciences， 1988， 28（1）： 31-36.
[15]	ROGERS D， HAHN M. Extended-connectivity fingerprints［J］. Journal of Chemical Information and Modeling， 2010， 50（5）： 742-754.
[16]	SHERVASHIDZE N， SCHWEITZER P， VAN LEEUWEN E J， et al. Weisfeiler-Lehman graph kernels［J］. Journal of Machine Learning Research， 2011， 12： 2539-2561.
[17]	TONG H， FALOUTSOS C， PAN J Y. Random walk with restart： fast solutions and applications［J］. Knowledge and Information Systems， 2008， 14（3）： 327-346.
[18]	XIE Y， WANG X， WANG P， et al. A pseudo-label supervised graph fusion attention network for drug-target interaction prediction［J］. Expert Systems with Applications， 2025， 259： No.125264.
[19]	LI Y， QIAO G， WANG K， et al. Drug-target interaction predication via multi-channel graph neural networks［J］. Briefings in Bioinformatics， 2022， 23（1）： No.bbab346.
[20]	LIU Z， WANG Y， VAIDYA S， et al. KAN： Kolmogorov-Arnold networks［EB/OL］. ［2025-06-13］..
[21]	FRIEDMAN J H. Greedy function approximation： a gradient boosting machine［J］. The Annals of Statistics， 2001， 29（5）： 1189-1232.
[22]	KNOX C， LAW V， JEWISON T， et al. DrugBank 3.0： a comprehensive resource for “omics” research on drugs［J］. Nucleic Acids Research， 2011， 39（S1）： D1035-D1041.
[23]	PRASAD T S K， GOEL R， KANDASAMY K， et al. Human Protein Reference Database — 2009 update［J］. Nucleic Acids Research， 2009， 37（S1）： D767-D772.
[24]	DAVIS A P， GRONDIN C J， JOHNSON R J， et al. Comparative Toxicogenomics Database （CTD）： update 2021［J］. Nucleic Acids Research， 2021， 49（D1）： D1138-D1143.
[25]	KUHN M， LETUNIC I， JENSEN L J， et al. The SIDER database of drugs and side effects［J］. Nucleic Acids Research， 2016， 44（D1）： D1075-D1079.
[26]	LIANG Z， ZHOU Y， SESIA M. Conformal inference is （almost） free for neural networks trained with early stopping［C］// Proceedings of the 40th International Conference on Machine Learning. New York： JMLR.org， 2023： 20810-20851.
[27]	PENG J， WANG Y， GUAN J， et al. An end-to-end heterogeneous graph representation learning-based framework for drug-target interaction prediction［J］. Briefings in Bioinformatics， 2021， 22（5）： No.bbaa430.
[28]	LI J， WANG J， LV H， et al. IMCHGAN： inductive matrix completion with heterogeneous graph attention networks for drug-target interactions prediction［J］. IEEE/ACM Transactions on Computational Biology and Bioinformatics， 2022， 19（2）： 655-665.
[29]	TANG R， SUN C， HUANG J， et al. Predicting drug-protein interactions by self-adaptively adjusting the topological structure of the heterogeneous network［J］. IEEE Journal of Biomedical and Health Informatics， 2023， 27（11）： 5675-5684.
[30]	DEHGHAN A， ABBASI K， RAZZAGHI P， et al. CCL-DTI： contributing the contrastive loss in drug-target interaction prediction［J］. BMC Bioinformatics， 2024， 25： No.48.
[31]	LI Z， HUANG J， LIU X， et al. KRN-DTI： towards accurate drug-target interaction prediction with Kolmogorov-Arnold and residual networks［J］. Methods， 2025， 240： 137-144.
[32]	BREIMAN L. Random forests［J］. Machine Learning， 2001， 45（1）： 5-32.
[33]	CORTES C， VAPNIK V. Support-vector networks［J］. Machine Learning， 1995， 20（3）： 273-297.
[34]	PEDREGOSA F， VAROQUAUX G， GRAMFORT A， et al. Scikit‑learn： machine learning in Python［J］. Journal of Machine Learning Research， 2011， 12： 2825-2830.
[35]	HOSMER D W， LEMESHOW S， STURDIVANT R X. Applied logistic regression［M］. 3rd ed. New York： John Wiley & Sons， Inc.， 2013： 8-19.
[36]	CHEN T， GUESTRIN C. XGBoost： a scalable tree boosting system［C］// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2016： 785-794.

数据集	数据来源地址	节点类型	节点数	相关节点类型	相关节点数	关联关系条数
DrugBank	https：//go.drugbank.com/	药物	708	药物	708	10 036
DrugBank	https：//go.drugbank.com/	药物	708	蛋白质	1 512	1 923
CTD	http：//ctdbase.org/	疾病	5 603	药物	708	199 214
CTD	http：//ctdbase.org/	疾病	5 603	蛋白质	1 512	1 596 745
SIDER	http：//sideeffects.embl.de/	副作用	4 192	药物	708	80 163
HPRD	http：//www.hprd.org/	蛋白质	1 512	蛋白质	1 512	7 363

数据集	数据来源地址	节点类型	节点数	相关节点类型	相关节点数	关联关系条数
DrugBank	https：//go.drugbank.com/	药物	708	药物	708	10 036
DrugBank	https：//go.drugbank.com/	药物	708	蛋白质	1 512	1 923
CTD	http：//ctdbase.org/	疾病	5 603	药物	708	199 214
CTD	http：//ctdbase.org/	疾病	5 603	蛋白质	1 512	1 596 745
SIDER	http：//sideeffects.embl.de/	副作用	4 192	药物	708	80 163
HPRD	http：//www.hprd.org/	蛋白质	1 512	蛋白质	1 512	7 363

网格数M	AUC	AUPR	F1-score
2	0.974 5	0.979 3	0.925 4
3	0.986 2	0.986 9	0.939 8
4	0.985 9	0.986 0	0.938 3
5	0.985 2	0.984 8	0.937 5

网格数M	AUC	AUPR	F1-score
2	0.974 5	0.979 3	0.925 4
3	0.986 2	0.986 9	0.939 8
4	0.985 9	0.986 0	0.938 3
5	0.985 2	0.984 8	0.937 5

GBDT树深	AUC	AUPR	F1-score
3	0.979 6	0.980 1	0.931 1
5	0.986 2	0.986 9	0.939 8
7	0.984 0	0.983 4	0.936 0
9	0.982 1	0.981 5	0.932 8

Drug-target interaction prediction based on structure-network collaborative features and grid-attention enhanced Kolmogorov-Arnold network

基于结构‒网络协同特征与网格注意力增强KAN的药物靶标相互作用预测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 36

Related Articles 15

Recommended Articles

Metrics

方法	AUC	AUPR	F1-score
DTINet	0.903 0±0.022	0.918 7±0.017	0.796 7±0.020
EEG-DTI	0.953 1±0.022	0.964 2±0.021	0.813 4±0.015
IMCHGAN	0.954 4±0.019	0.920 3±0.017	0.891 2±0.025
SATS	0.943 2±0.018	0.454 1±0.013	0.801 1±0.008
DTI-MGNN	0.966 5±0.026	0.968 3±0.025	0.841 8±0.021
CCL-DTI	0.978 1±0.048	0.964 3±0.051	0.860 4±0.021
KRN-DTI	0.970 6±0.016	0.973 7±0.021	0.909 9±0.028
SNKDTI	0.986 2±0.010	0.986 9±0.005	0.939 8±0.009

方法	AUC	AUPR	F1-score
SNKDTI-S	0.929 5	0.934 5	0.854 7
SNKDTI-N	0.954 4	0.954 8	0.880 1
SNKDTI-M	0.978 5	0.979 8	0.916 2
SNKDTI-K	0.983 8	0.983 2	0.938 0
SNKDTI	0.986 2	0.986 9	0.939 8

M	S	总参数量/10⁶	单轮训练时间/s	CPU内存峰值/MB
2	3	1.10	167.2	508.16
3	3	1.68	166.4	820.15
4	3	2.15	163.1	1 022.46
5	3	2.67	155.0	1 148.23

药物	相关蛋白质	预测结果	准确率/%
DB00248： Cabergoline	P35626：ADRBK2	True	93.3
	P13631：RARG	True
	P05089：ARG1	True
	P08913：ADRA2A	True
	P25098：ADRBK1	True
	P23945：FSHR	True
	P60880：SNAP25	True
	Q9UIC8：LCMT1	True
	O14646：CHD1	False
	P08559：PDHA1	True
	O43772：SLC25A20	True
	P00390：GSR	True
	P01589：IL2RA	True
	P49448：GLUD2	True
	P14867：GABRA1	True
DB00186： Lorazepam	P31937：HIBADH	True	100.0
	Q16739：UGCG	True
	P40394：ADH7	True
	P09601：HMOX1	True
	P04150：NR3C1	True
	Q14832：GRM3	True
	P18505：GABRB1	True
	P28472：GABRB3	True
	P30532：CHRNA5	False
	P18507：GABRG2	True
	Q8N1C3：GABRG1	True
	Q99928：GABRG3	True
	P28476：GABRR2	True

靶标	相关药物	预测结果	准确率/%
P03372：ESR1	DB00364：Sucralfate	True	100.0
	DB00395：Carisoprodol	True
	DB00480：Lenalidomide	True
	DB00538：Gadoversetamide	True
	DB00602：Ivermectin	True
	DB00674：Galantamine	True
	DB00782：Propantheline	True
	DB01182：Propafenone	True
	DB01184：Domperidone	False
	DB01195：Flecainide	True
	DB01400：Neostigmine	True
P08588： ADRB1	DB00186：Lorazepam	True	93.7
	DB00193：Tramadol	True
	DB00263：Sulfisoxazole	True
	DB00334：Olanzapine	True
	DB00367：Levonorgestrel	True
	DB00371：Meprobamate	True
	DB00486：Nabilone	True
	DB00520：Caspofungin	False
	DB00567：Cephalexin	True
	DB00595：Oxytetracycline	True
	DB00611：Butorphanol	True
	DB00665：Nilutamide	True
	DB00839：Tolazamide	True
	DB00959：Methylprednisolone	True
	DB01062：Oxybutynin	True
	DB01117：Atovaquone	True

[1]	Xiang BAI, Juchuan LI, Huimin WANG, Chao JING, Jian NIU, Xingzhong ZHANG, Yongqiang CHENG. Power image retrieval method based on improved Swin Transformer [J]. Journal of Computer Applications, 2026, 46(4): 1334-1343.
[2]	Huanxian LIU, Hongtao WANG, Xian’ao WANG, Hongmei WANG, Weifeng XU. Multimodal fact verification with cross-modal semantic association [J]. Journal of Computer Applications, 2026, 46(4): 1069-1076.
[3]	Peirong SHAO, Suzhen LIN, Yanbo WANG. Human-centric detail-enhanced virtual try-on method [J]. Journal of Computer Applications, 2026, 46(3): 915-923.
[4]	Rilong WANG, Zhenping LI, Xiaosong LI, Qiang GAO, Ya HE, Yong ZHONG, Yingxiao ZHAO. Multi-Agent collaborative knowledge reasoning framework [J]. Journal of Computer Applications, 2026, 46(3): 708-714.
[5]	Zuxi ZHANG, Zhancheng ZHANG, Fuyuan HU. Local and long-range temporal complementary modeling for video action recognition [J]. Journal of Computer Applications, 2026, 46(3): 758-766.
[6]	Rifeng ZHANG, Guangming LI, Yurong OUYANG. Low-light image enhancement network guided by reflection prior map [J]. Journal of Computer Applications, 2026, 46(2): 546-554.
[7]	Qianhui XU, Ke NIU, Shunzhe ZHU, Lin SHI, Jun LI. GAB3D-SEVSN： enhanced video steganography model via invertible neural network [J]. Journal of Computer Applications, 2026, 46(2): 467-474.
[8]	Jinjiao LIN, Canshun ZHANG, Shuya CHEN, Tianxin WANG, Jian LIAN, Yonghui XU. Vehicle insurance fraud detection method based on improved graph attention network [J]. Journal of Computer Applications, 2026, 46(2): 437-444.
[9]	Junrui WU, Jiangchuan YANG, Haisheng YU, Sai ZOU, Wenyong WANG. Performance evaluation method for deterministic networks based on complex-enhanced attention graph neural network [J]. Journal of Computer Applications, 2026, 46(2): 505-517.
[10]	Ming LI, Mengqi WANG, Aili ZHANG, Hua REN, Yuqiang DOU. Image steganography method based on conditional generative adversarial networks and hybrid attention mechanism [J]. Journal of Computer Applications, 2026, 46(2): 475-484.
[11]	Sizhong ZHANG, Jianyang LIU, Linfeng LI. Action quality assessment model based on trajectory-guided perceptual learning with X3D [J]. Journal of Computer Applications, 2026, 46(2): 555-563.
[12]	Hu LUO, Mingshu ZHANG. Rumor detection method based on cross-modal attention mechanism and contrastive learning [J]. Journal of Computer Applications, 2026, 46(2): 361-367.
[13]	Lifang WANG, Wenjing REN, Xiaodong GUO, Rongguo ZHANG, Lihua HU. Trident generative adversarial network for low-dose CT image denoising [J]. Journal of Computer Applications, 2026, 46(1): 270-279.
[14]	Wen LI, Kairong LI, Kai YANG. Subgraph-aware contrastive learning with data augmentation [J]. Journal of Computer Applications, 2026, 46(1): 1-9.
[15]	Yingjie MA, Jingying QIN, Geng ZHAO, Jing XIAO. Deep compressive sensing network for IoT images and its chaotic encryption protection method [J]. Journal of Computer Applications, 2026, 46(1): 144-151.