基于多特征融合的药物疾病关联预测模型构建

doi:10.3969/j.issn.0258-8021.2023.04.008

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1905 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract We constructed a drug-disease association prediction model on the basis of drug multi feature fusion, which can provide theoretical foundation for drug knowledge discovery. Three similarities fused into drug comprehensive similarity by drug chemical structure, drug-side effect and drug-target multi-features. Disease similarity was calculated based on MeSH tree number. Next, GCN method was used to extract feature information of drug-disease graph data. Finally, MFFGCN was constructed for drug-disease association prediction. The association of drug diseases was predicted on the same data set, with the help of multiple evaluation indicators such as AUC, AUPR, accuracy, sensitivity, recall and F1, MFFGCN has better performance than the single feature association prediction method and 4 existing representative algorithms. The AUC index is 0.866 2, which is 2.48% higher than the average predicted AUC index of single feature and 1.67% higher than the baseline method. The AUPR index is 0.3412, which is 1.67% higher than the average predicted AUC index of single feature and 27.49% higher than the baseline method. MFFGCN has achieved good performance in the prediction of unknown drug disease association. This methods can find new indications of drugs, and also provide methodological reference and theoretical basis for drug relocation.

Key words： multi-feature fusion drug disease association prediction graph convolution network

Received: 01 July 2022

PACS:

R318

Corresponding Authors: ^*E-mail: hou.li@imicams.ac.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Kang Hongyu
	Li Qin
	Li Jiao
	Gu Yaowen
	Hou Li

Cite this article:

Kang Hongyu,Li Qin,Li Jiao, et al. Drug-Disease Association Prediction Based on Multi-Feature Fusion[J]. Chinese Journal of Biomedical Engineering, 2023, 42(4): 453-460.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2023.04.008 OR http://cjbme.csbme.org/EN/Y2023/V42/I4/453

[1] 王可鉴,石乐明,贺林,等.中国药物研发的新机遇:基于医药大数据的系统性药物重定位[J].科学通报,2014, 59(18):1790-1796.
[2] 徐燕,郭颖.药物重定位的研究策略[J].中国新药杂志, 2017, 26(11): 1253-1258.
[3] Mullard A. 2021FDA drug approvals[J]. Nature Reviews Drug Discovery, 2022, 21(2):83-88.
[4] Pushpakom S, Iorio F, Eyers PA, et al. Drug repurposing: progress, challenges and recommendations[J]. Nature Reviews Drug Discovery, 2019,18(1):41-58.
[5] Wang Wenhui, Yang Sen, Zhang Xiang, et al. Drug repositioning by integrating target information through a heterogeneous network model[J]. Bioinformatics, 2014,30(20):2923-2930.
[6] Luo Huimin, Wang Jianxin, Li Min, et al. Drug repositioning based on comprehensive similarity measures and Bi-Random Walk algorithm[J]. Bioinformatics, 2016,32(17):2664-2671.
[7] Luo Huimin, Wang Jianxin, Li Min. Computational drug repositioning with random walk on a heterogeneous network[J]. IEEE/ACM Transactions on Computational Biology & Bioinformatics, 2019,6(16):1890-1900.
[8] Jiang Hanjing, Huang Yabing. An effective drug-disease associations prediction model based on graphic representation learning over multi-biomolecular network[J]. BMC Bioinformatics, 2022,23(9):1-17.
[9] Liang Xujun, Zhang Pengfei, Yan Lu, et al. LRSSL: predict and interpret drug-disease associations based on data integration using sparse subspace learning[J]. Bioinformatics, 2017,33(8):1187-1196.
[10] 李宗耀,杨志豪,吴晓芳,等.基于语义资源的生物医学文献知识发现研究[J].中文信息学报,2016,30(1):176-182.
[11] Zitnik M, Agrawal M, Leskovec J. Modeling polypharmacy side effects with graph convolutional networks[J], Bioinformatics, 2018, 34(13):457-466.
[12] Fatehifar M, Karshenas H. Drug-drug interaction extraction using a position and similarity fusion-based attention mechanism[J]. Journal of Biomedical Informatics, 2021, 115(3):103707-103721.
[13] Pang Shanchen, Zhang Ying, Song Tao, et al. AMDE: a novel attention-mechanism-based multidimensional feature encoder for drug-drug interaction prediction[J]. Briefings in Bioinformatics, 2021,23(1):1-12.
[14] 郝志峰,詹健明,蔡瑞初.基于有监督的多视角图神经网络的药物组合协同预测算法[J].计算机应用研究, 2022,39(7):2020-2024.
[15] Gu Yaowen, Zheng Si, Li Jiao. CurrMG: a curriculum learning approach for graph based molecular property prediction[C]// 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Houston:IEEE, 2021: 2686-2693.
[16] Marinka Z, Monica A, Jure L. Modeling polypharmacy side effects with graph convolutional networks[J]. Bioinformatics, 2018, 34(13):i457-i466.
[17] 杨霞,韩春燕,琚生根.基于实体信息和图神经网络的药物相互作用关系抽取[J].四川大学学报(自然科学版),2022,59(2):48-56.
[18] Wen Zhang, Xiang Yue, Lin Weiran, et al. Predicting drug-disease associations by using similarity constrained matrix factorization[J]. BMC Bioinformatics, 2018, 19(1):233-245.
[19] 于亚运,刘勇国,蒋羽,等.基于指纹相似度的药物-靶点相互作用预测[J].中国中药杂志,2017,42(18):3578-3583.
[20] Campillos M, Michael K, Gavin A, et al. Drug target identification using side-effect similarity[J]. Science, 2008,321(5886):263-266.
[21] 刘忠雨,李彦霖,周洋. 深入浅出图神经网络[M].北京:机械工业出版社.
[22] 马怡青,蔡美玲,陈明,等.基于图神经网络的药物相互预测方法[J].电脑知识与技术,2022,18(18):61-63.
[23] Li Jin, Zhang Sai, Liu Tao, et al. Neural inductive matrix completion with graph convolutional networks for miRNA-disease Association Prediction[J]. Bioinformatics, 2020,36(8): 2538-2546.
[24] Qu Wei, Gu Shanshan, Luo Han, et al. Effects of olanzapine-fluoxetine combination treatment of major depressive disorders on the quality of life during acute treatment period[J]. Cell Biochemistry & Biophysics, 2014, 70(3):1799-1802.
[25] Bo Qifu, Sun Xiumei, Jin Liu, et al. Antitumor action of the peroxisome proliferator-activated receptor-γ agonist rosiglitazone in hepatocellular carcinoma[J]. Oncology Letters, 2015, 10(4): 1979-1984.
[26] Borota D, Murray E, Keceli G, et al. Post-study caffeine administration enhances memory consolidation in humans [J]. Nature Neuroscience, 2014, 17(2):201-212.
[27] 段婷婷.依那普利联合硝苯地平对稳定型心绞痛患者疗效及血管内皮功能的影响[J].基层医学论坛,2021,25(10):1396-1398.
[28] 王学艳.西咪替丁与川芎嗪注射液治疗肺源性心脏病疗效观察[J].医学理论与实践,2011,24(1):40-41.
[29] 周仙文.西咪替丁对肠炎患儿炎性因子水平的影响[J]. 蛇志, 2017,29(3):303-304.
[30] Ghosh S, Lalani R, Maiti K, et al. Synergistic co-loading of vincristine improved chemotherapeutic potential of pegylated liposomal doxorubicin against triple negative breast cancer and non-small cell lung cancer[J]. Nanomedicine. 2021,31(2): e102320.
[31] Yan D, Wei H, Lai X, et al. Co-delivery of homoharringtonine and doxorubicin boosts therapeutic efficacy of refractory acute myeloid leukemia[J]. Journal of Controlled Release. 2020,327(10): 766-778.
[32] Perry JM, Tao F, Roy A, et al. Overcoming WNT-β-catenin dependent anticancer therapy resistance in leukaemia stem cells[J]. Nature Cell Biology, 2020,22(6):689-700.
[33] Zheng B, Song L, Liu H. Gasserian ganglion injected with Adriamycin successfully relieves intractable trigeminal nerve postherpetic neuralgia for an elderly patient: a case report[J]. Medicine (Baltimore). 2018,97(38): e12388.
[34] Niu Wenbo, Xiao Qian, Wang Xuejiao, et al. A biomimetic drug delivery system by integrating grapefruit extracellular vesicles and doxorubicin-loaded heparin-based nanoparticles for glioma therapy[J]. Nano Letters 2021,21(3):1484-1492.
[35] Wei Hongxiang, Chen Jinyuan, Wang Shenglin, et al. A nanodrug consisting of doxorubicin and exosome derived from mesenchymal stem cells for osteosarcoma treatment in vitro[J]. International Journal of Nanomedicine. 2019,14(1):8603-8610.
[36] Bosman M, Krüger DN, Favere K, et al. Doxorubicin impairs smooth muscle cell contraction: novel insights in vascular toxicity[J]. International Journal of Molecular Sciences, 2021,22(23):12812.