Please wait a minute...
Advanced Search
数据分析与知识发现  2024, Vol. 8 Issue (2): 155-167     https://doi.org/10.11925/infotech.2096-3467.2022.1225
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于关系融合和双向扩散模型的药物与靶标关系预测方法研究*
张云秋(),黄麒霏,朱祥
吉林大学公共卫生学院 长春 130021
Predicting Drug-Target Relationship Based on Relation Fusion and Bidirectional Mass Diffusion Model
Zhang Yunqiu(),Huang Qifei,Zhu Xiang
School of Public Health, Jilin University, Changchun 130021, China
全文: PDF (1306 KB)   HTML ( 4
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 提出了一种新的药物与靶标关系预测方法来提升预测性能。【方法】 进一步丰富网络的语义信息,采用SNF、AVG和MAX方法分别对药物相似性网络和靶标相似性网络中的多种语义关系进行融合。基于关系融合后的相似性网络和已知的药物-靶标互作网络构建双向扩散模型,以实现药物与靶标关系预测。【结果】 实证研究表明,本文方法相较于主流的预测方法在AUC值指标上分别提升了2.2%和12.8%。并且通过对预测结果进行文献回溯,预测分数排在前10、20和30位的药物-靶标关系对中,可以分别在文献中找到3、8和11对药物-靶标的相关线索与证据。另外,SNF的融合效果最优,能够最大程度提高预测的性能。【局限】 未融合药物或靶标客观属性上的相似性,如药物的化学结构或靶标的序列结构相似性,并且针对新药物和新靶标关系发现的冷启动问题仍待解决。【结论】 本文提出的预测方法具有一定的优越性和有效性,可以为药物重定位以及其他生物医学实体的关系预测相关研究提供参考。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
张云秋
黄麒霏
朱祥
关键词 药物靶标机器学习SNF    
Abstract

[Objective] This study proposes a new method to predict the relationship between drugs and targets to improve the prediction performance. [Methods] Firstly, we used the SNF, AVG, and MAX methods to fuse multiple semantic relationships in drug and target similarity networks, which further enriched the semantic information of the networks. Then, we constructed a bidirectional diffusion model based on the fused similarity networks and the existing drug-target interaction network to predict the drug-target relationship. [Results] Compared with mainstream forecasting models, our method's AUC value index improved by 2.2% and 12.8%. With a retrospective study, the prediction scores ranked in the top 10, 20, and 30 drug-target relationship pairs, and clues and evidence related to 3, 8, and 11 drug-target pairs could be found in the literature. The SNF had the best fusion effect and maximized the prediction. [Limitations] We did not fuse similarities in objective attributes of drugs or targets, such as the chemical structure of drugs or sequence structure similarities of targets. The cold start problem in the relationship between new drugs and new targets still needs to be solved. [Conclusions] The prediction method proposed in this study could provide some references for the research on drug repositioning and relationship prediction of other biomedical entities.

Key wordsDrug    Target    Machine Learning    SNF
收稿日期: 2022-11-18      出版日期: 2023-03-28
ZTFLH:  R96  
  TP181  
  G35  
基金资助:*教育部人文社会科学规划项目(18YJA870017)
通讯作者: 张云秋,ORCID:0000-0002-9790-9581,E-mail:yunqiu@jlu.edu.cn。   
引用本文:   
张云秋, 黄麒霏, 朱祥. 基于关系融合和双向扩散模型的药物与靶标关系预测方法研究*[J]. 数据分析与知识发现, 2024, 8(2): 155-167.
Zhang Yunqiu, Huang Qifei, Zhu Xiang. Predicting Drug-Target Relationship Based on Relation Fusion and Bidirectional Mass Diffusion Model. Data Analysis and Knowledge Discovery, 2024, 8(2): 155-167.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2022.1225      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2024/V8/I2/155
Fig.1  方法流程框架
Fig.2  关系融合过程
Fig.3  双向扩散模型的流程框架
节点类型 来源 数量 边类型及数量
药物 DrugBank 708 药物-药物(10 036)
药物-靶标(1 923)
靶标 HPRD 1512 靶标-靶标(7 363)
疾病 CTD 5603 药物-疾病(199 214)
靶标-疾病(1 596 745)
Table 1  网络节点及边的获取情况
Fig.4  不同相似性融合方法下DTBMD的ROC曲线
Fig.5  不同药物与靶标关系预测方法的ROC曲线
排名 药物 靶标 PMID 具体描述
7 阿米替林 DRD2 22507762 阿米替林可上调DRD2[37]
8 氯氮平 COX-2 24768740 氯氮平治疗会引起环加氧酶-2表达增加[38]
9 喹硫平 Ptgs2 19587612 喹硫平会显著改变Ptgs2基因的表达[39]
11 氯氮平 SLC6A4 34082673 编码5-羟色胺转运蛋白的SLC6A4基因的rs1800532多态性可能与自杀易感性以及对锂和氯氮平的不良反应相关[40]
12 喹硫平 5-HTTLPR 27277475 对抗抑郁药喹硫平治疗反应的预测价值可能受到MDD中5-HTTLPR多态性的影响[41]
13 阿米替林 GABAA 31940131 阿米替林的内感受作用取决于 GABAA受体的功能活性[42]
18 氯氮平 SLC6A2 26282453 SLC6A2与氯氮平的治疗反应有关[43]
19 喹硫平 SLC6A2 29016993 去甲硫平的去甲肾上腺素转运蛋白占用可能是喹硫平抗抑郁作用的因素之一[44]
23 阿立哌唑 COX-2 29241811 阿立哌唑可抑制环加氧酶-2的mRNA表达水平[45]
25 奥氮平 SLC6A4 33432189 遗传和功能分析显示,奥氮平直接靶向SLC6A4[46]
27 阿立哌唑 SLC6A4 17242925 阿立哌唑与5-羟色胺相互作用[47]
Table 2  预测分数前30对药物-靶标及相关证据
[1] 王娜, 常福厚, 钱新宇, 等. 我国新药研发的研究进展[J]. 中国药理学与毒理学杂志, 2019, 33(10): 839.
[1] (Wang Na, Chang Fuhou, Qian Xinyu, et al. Research Progress of New Drug Research and Development in China[J]. Chinese Journal of Pharmacology and Toxicology, 2019, 33(10): 839.)
[2] Pushpakom S, Iorio F, Eyers P A, et al. Drug Repurposing: Progress, Challenges and Recommendations[J]. Nature Reviews Drug Discovery, 2019, 18(1): 41-58.
doi: 10.1038/nrd.2018.168 pmid: 30310233
[3] Wang C, Kurgan L. Survey of Similarity-Based Prediction of Drug-Protein Interactions[J]. Current Medicinal Chemistry, 2020, 27(35): 5856-5886.
doi: 10.2174/0929867326666190808154841
[4] 张晗, 安欣宇, 刘春鹤. 基于多源语义知识图谱的药物知识发现: 以药物重定位为实证[J]. 数据分析与知识发现, 2022, 6(7): 87-98.
[4] (Zhang Han, An Xinyu, Liu Chunhe. Building Multi-Source Semantic Knowledge Graph for Drug Repositioning[J]. Data Analysis and Knowledge Discovery, 2022, 6(7): 87-98.)
[5] Wang B, Jiang J Y, Wang W, et al. Unsupervised Metric Fusion by Cross Diffusion[C]// Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2012: 2997-3004.
[6] Wang B, Mezlini A M, Demir F, et al. Similarity Network Fusion for Aggregating Data Types on a Genomic Scale[J]. Nature Methods, 2014, 11(3): 333-337.
doi: 10.1038/nmeth.2810 pmid: 24464287
[7] Wu G S, Liu J, Wang C H. Semi-Supervised Graph Cut Algorithm for Drug Repositioning by Integrating Drug, Disease and Genomic Associations[C]// Proceedings of the 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Piscataway: IEEE, 2016: 223-228.
[8] Wu G S, Liu J, Wang C H. Predicting Drug-Disease Interactions by Semi-Supervised Graph Cut Algorithm and Three-Layer Data Integration[J]. BMC Medical Genomics, 2017, 10(5): Article No.79.
[9] Tangmanussukum P, Kawichai T, Suratanee A, et al. Heterogeneous Network Propagation with Forward Similarity Integration to Enhance Drug-Target Association Prediction[J]. PeerJ Computer Science, 2022, 8: e1124.
doi: 10.7717/peerj-cs.1124 pmid: 36262151
[10] Thafar M A, Olayan R S, Ashoor H, et al. DTiGEMS+: Drug-Target Interaction Prediction Using Graph Embedding, Graph Mining, and Similarity-Based Techniques[J]. Journal of Cheminformatics, 2020, 12(1): Article No.44.
[11] 孟岩, 汪云云. 典型半监督分类算法的研究分析[J]. 计算机技术与发展, 2017, 27(10): 43-48.
[11] (Meng Yan, Wang Yunyun. Research and Analysis of Typical Semi-Supervised Classification Algorithm[J]. Computer Technology and Development, 2017, 27(10): 43-48.)
[12] 王磊. 基于机器学习的药物-靶标相互作用预测研究[D]. 徐州: 中国矿业大学, 2018.
[12] (Wang Lei. Research on the Prediction of Drug-Target Interactions Based on Machine Learning[D]. Xuzhou: China University of Mining and Technology, 2018.)
[13] 张丽娟. 基于逻辑回归的药物与靶标相互作用关系预测[D]. 长沙: 湖南大学, 2018.
[13] (Zhang Lijuan. Drug Target Interaction Prediction Based on Logistic Regression[D]. Changsha: Hunan University, 2018.)
[14] Huang Y A, You Z H, Chen X. A Systematic Prediction of Drug-Target Interactions Using Molecular Fingerprints and Protein Sequences[J]. Current Protein & Peptide Science, 2018, 19(5): 468-478.
[15] Zheng X P, He S, Song X, et al. DTI-RCNN: New Efficient Hybrid Neural Network Model to Predict Drug-Target Interactions[C]// Proceedings of the 27th International Conference on Artificial Neural. Cham: Springer, 2018: 104-114.
[16] Cheng F X, Liu C, Jiang J, et al. Prediction of Drug-Target Interactions and Drug Repositioning via Network-Based Inference[J]. PLoS Computational Biology, 2012, 8(5): e1002503.
doi: 10.1371/journal.pcbi.1002503
[17] Wang W H, Yang S, Li J. Drug Target Predictions Based on Heterogeneous Graph Inference[J]. Pacific Symposium on Biocomputing, 2013: 53-64.
[18] 李敏, 王晓桐, 罗慧敏, 等. 随机游走技术在网络生物学中的研究进展[J]. 电子学报, 2018, 46(8): 2035-2048.
doi: 10.3969/j.issn.0372-2112.2018.08.033
[18] (Li Min, Wang Xiaotong, Luo Huimin, et al. Progress on Random Walk and Its Application in Network Biology[J]. Acta Electronica Sinica, 2018, 46(8): 2035-2048.)
doi: 10.3969/j.issn.0372-2112.2018.08.033
[19] Chen X, Liu M X, Yan G Y. Drug-Target Interaction Prediction by Random Walk on the Heterogeneous Network[J]. Molecular BioSystems, 2012, 8(7): 1970-1978.
doi: 10.1039/c2mb00002d pmid: 22538619
[20] Zheng X D, Ding H, Mamitsuka H, et al. Collaborative Matrix Factorization with Multiple Similarities for Predicting Drug-Target Interactions[C]// Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2013: 1025-1033.
[21] Ezzat A, Zhao P L, Wu M, et al. Drug-Target Interaction Prediction with Graph Regularized Matrix Factorization[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2017, 14(3): 646-656.
doi: 10.1109/TCBB.2016.2530062 pmid: 26890921
[22] Cui Z, Gao Y L, Liu J X, et al. L2,1-GRMF: An Improved Graph Regularized Matrix Factorization Method to Predict Drug-Target Interactions[J]. BMC Bioinformatics, 2019, 20(Suppl 8): 287.
doi: 10.1186/s12859-019-2768-7
[23] Yue X, Wang Z, Huang J G, et al. Graph Embedding on Biomedical Networks: Methods, Applications and Evaluations[J]. Bioinformatics, 2020, 36(4): 1241-1251.
doi: 10.1093/bioinformatics/btz718 pmid: 31584634
[24] Luo Y N, Zhao X B, Zhou J T, et al. A Network Integration Approach for Drug-Target Interaction Prediction and Computational Drug Repositioning from Heterogeneous Information[J]. Nature Communications, 2017, 8: Article No.573.
[25] Wan F P, Hong L X, 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.
doi: 10.1093/bioinformatics/bty543 pmid: 30561548
[26] Zeng X X, Zhu S Y, Lu W Q, et al. Target Identification Among Known Drugs by Deep Learning from Heterogeneous Networks[J]. Chemical Science, 2020, 11(7): 1775-1797.
doi: 10.1039/c9sc04336e pmid: 34123272
[27] Estrada E. Topological Structural Classes of Complex Networks[J]. Physical Review E, 2007, 75(1): 016103.
doi: 10.1103/PhysRevE.75.016103
[28] Grady L. Random Walks for Image Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(11): 1768-1783.
doi: 10.1109/TPAMI.2006.233 pmid: 17063682
[29] van Laarhoven T, Nabuurs S B, Marchiori E. Gaussian Interaction Profile Kernels for Predicting Drug-Target Interaction[J]. Bioinformatics, 2011, 27(21): 3036-3043.
doi: 10.1093/bioinformatics/btr500 pmid: 21893517
[30] Zhou T, Ren J, Medo M, et al. How to Project a Bipartite Network?[J]. Physical Review E, 2007, 76(4): 046115.
doi: 10.1103/PhysRevE.76.046115
[31] Zhu X Z, Tian H, Zhang P, et al. Personalized Recommendation Based on Unbiased Consistence[J]. EPL (Europhysics Letters), 2015, 111(4): 48007.
doi: 10.1209/0295-5075/111/48007
[32] Deshpande M, Karypis G. Item-Based Top-N Recommendation Algorithms[J]. ACM Transactions on Information Systems, 2004, 22(1): 143-177.
doi: 10.1145/963770.963776
[33] Drugbank: Version 5.1.5[DB/OL]. (2020-01-03) [2020-01-30]. https://www.drugbank.ca/.
[34] Human Protein Reference Database: Version 9[DB/OL]. (2010-04-13) [2020-01-30]. http://www.hprd.org/.
[35] Comparative Toxicogenomics Database: Version 15982[DB/OL]. (2020-01-08) [2020-01-30]. http://ctdbase.org/.
[36] Valdeolivas A, Tichit L, Navarro C, et al. Random Walk with Restart on Multiplex and Heterogeneous Biological Networks[J]. Bioinformatics, 2019, 35(3): 497-505.
doi: 10.1093/bioinformatics/bty637 pmid: 30020411
[37] Lauterbach E C. Psychotropic Drug Effects on Gene Transcriptomics Relevant to Parkinson's Disease[J]. Progress in Neuro-Psychopharmacology & Biological Psychiatry, 2012, 38(2): 107-115.
[38] Zlatković J, Todorović N, Tomanović N, et al. Chronic Administration of Fluoxetine or Clozapine Induces Oxidative Stress in Rat Liver: A Histopathological Study[J]. European Journal of Pharmaceutical Sciences, 2014, 59: 20-30.
doi: 10.1016/j.ejps.2014.04.010 pmid: 24768740
[39] Orsetti M, Di Brisco F, Rinaldi M, et al. Some Molecular Effectors of Antidepressant Action of Quetiapine Revealed by DNA Microarray in the Frontal Cortex of Anhedonic Rats[J]. Pharmacogenetics and Genomics, 2009, 19(8): 600-612.
doi: 10.1097/FPC.0b013e32832ee573 pmid: 19587612
[40] de Berardis D, Vellante F, Pettorruso M, et al. Suicide and Genetic Biomarkers: Toward Personalized Tailored-Treatment with Lithium and Clozapine[J]. Current Pharmaceutical Design, 2021, 27(30): 3293-3304.
doi: 10.2174/1381612827666210603143353 pmid: 34082673
[41] Tatham E L, Hall G B C, Clark D, et al. The 5-HTTLPR and BDNF Polymorphisms Moderate the Association Between Uncinate Fasciculus Connectivity and Antidepressants Treatment Response in Major Depression[J]. European Archives of Psychiatry and Clinical Neuroscience, 2017, 267(2): 135-147.
doi: 10.1007/s00406-016-0702-9 pmid: 27277475
[42] Korolev A O, Kalinina T S, Volkova A V, et al. Role of GABAA Receptors in the Mechanism of in Vivo Psychotropic Activity of Amitriptyline in Rats[J]. Bulletin of Experimental Biology and Medicine, 2020, 168(3): 341-344.
doi: 10.1007/s10517-020-04704-0 pmid: 31940131
[43] Xu Q, Wu X, Li M, et al. Association Studies of Genomic Variants with Treatment Response to Risperidone, Clozapine, Quetiapine and Chlorpromazine in the Chinese Han Population[J]. The Pharmacogenomics Journal, 2016, 16(4): 357-365.
doi: 10.1038/tpj.2015.61
[44] Yatham L N, Sossi V, Ding Y S, et al. A Positron Emission Tomography Study of Norepinephrine Transporter Occupancy and Its Correlation with Symptom Response in Depressed Patients Treated with Quetiapine XR[J]. The International Journal of Neuropsychopharmacology, 2018, 21(2): 108-113.
doi: 10.1093/ijnp/pyx066
[45] Yoo S, Kim M Y, Cho J Y. Syk and SRC-Targeted Anti-Inflammatory Activity of Aripiprazole, an Atypical Antipsychotic[J]. Biochemical Pharmacology, 2018, 148: 1-12.
doi: S0006-2952(17)30710-4 pmid: 29241811
[46] Zhou M S, Wang Q Q, Zheng C L, et al. Drug Repurposing for Opioid Use Disorders: Integration of Computational Prediction, Clinical Corroboration, and Mechanism of Action Analyses[J]. Molecular Psychiatry, 2021, 26(9): 5286-5296.
doi: 10.1038/s41380-020-01011-y pmid: 33432189
[47] Stark A D, Jordan S, Allers K A, et al. Interaction of the Novel Antipsychotic Aripiprazole with 5-HT1A and 5-HT2A Receptors: Functional Receptor-Binding and in Vivo Electrophysiological Studies[J]. Psychopharmacology, 2007, 190(3): 373-382.
doi: 10.1007/s00213-006-0621-y
[48] 陈新谦, 金有豫, 汤光, 等. 新编药物学[M]. 第16版. 北京: 人民卫生出版社, 2007.
[48] (Chen Xinqian, Jin Youyu, Tang Guang, et al. New Edition Pharmacology[M]. 16th Edition. Beijing: People's Medical Publishing House, 2007.)
[49] 李科, 俞兰秀, 刘小雨, 等. γ-氨基丁酸改善睡眠作用机制的研究进展[J]. 食品工业科技, 2019, 40(14):353-358.
[49] (Li Ke, Yu Lanxiu, Liu Xiaoyu, et al. Research Progress on Improving Sleep Mechanism of γ-Aminobutyric Acid[J]. Science and Technology of Food Industry, 2019, 40(14):353-358.)
[1] 刘天畅, 王雷, 朱庆华. 基于SHAP解释方法的智慧居家养老服务平台用户流失预测研究*[J]. 数据分析与知识发现, 2024, 8(1): 40-54.
[2] 刘智锋, 王继民. 可解释机器学习在信息资源管理领域的应用研究综述*[J]. 数据分析与知识发现, 2024, 8(1): 16-29.
[3] 徐晨, 张巍. 不平衡数据背景下基于文本线索的公益众筹欺诈项目检测*[J]. 数据分析与知识发现, 2023, 7(9): 125-135.
[4] 吴佳伦, 张若楠, 康武林, 袁普卫. 基于患者相似性分析的药物推荐深度学习模型研究*[J]. 数据分析与知识发现, 2023, 7(6): 148-160.
[5] 韦华楠, 雷鸣, 汪雪锋, 余音. 基础研究资助导向识别及演化分析:以NSF为例[J]. 数据分析与知识发现, 2023, 7(5): 10-20.
[6] 林伟振, 刘洪伟, 陈燕君, 温展明, 易闽琦. 基于在线评论的顾客满意度研究——以健康监测穿戴产品为例*[J]. 数据分析与知识发现, 2023, 7(5): 145-154.
[7] 蒋林甫, 袁贞明, 张邢炜, 姜华强, 孙晓燕. 基于PCHD-TabNet的十年冠心病预测*[J]. 数据分析与知识发现, 2023, 7(5): 133-144.
[8] 吕琦, 上官燕红, 张琳, 黄颖. 基于文本内容自动分类的跨学科测度研究*[J]. 数据分析与知识发现, 2023, 7(4): 56-67.
[9] 成全, 佘德昕. 融合患者体征与用药数据的图神经网络药物推荐方法研究*[J]. 数据分析与知识发现, 2022, 6(9): 113-124.
[10] 曲宗希, 沙勇忠, 李雨桐. 基于灰狼优化与多机器学习的重大传染病集合预测研究——以COVID-19疫情为例*[J]. 数据分析与知识发现, 2022, 6(8): 122-133.
[11] 郭进京, 夏光辉, 黄奇, 何丽云, 张化冰. 基于在线健康社区的药物不良反应信号识别方法研究*[J]. 数据分析与知识发现, 2022, 6(7): 70-86.
[12] 张晗, 安欣宇, 刘春鹤. 基于多源语义知识图谱的药物知识发现:以药物重定位为实证*[J]. 数据分析与知识发现, 2022, 6(7): 87-98.
[13] 赵杨, 严周周, 沈棋琦, 李钟航. 基于机器学习的医疗健康APP隐私政策合规性研究*[J]. 数据分析与知识发现, 2022, 6(5): 112-126.
[14] 王露, 乐小虬. 科技论文引用内容分析研究进展[J]. 数据分析与知识发现, 2022, 6(4): 1-15.
[15] 王若佳, 严承希, 郭凤英, 王继民. 基于用户画像的在线健康社区用户流失预测研究*[J]. 数据分析与知识发现, 2022, 6(2/3): 80-92.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn