基于多源异构数据的中医药知识图谱构建与应用研究<sup>*</sup>

doi:10.11925/infotech.2096-3467.2022.0893

数据分析与知识发现

2023, Vol. 7

Issue (9): 146-158 https://doi.org/10.11925/infotech.2096-3467.2022.0893

研究论文

本期目录 | 过刊浏览 | 高级检索

基于多源异构数据的中医药知识图谱构建与应用研究^*

翟东升,娄莹,阚慧敏,何喜军,梁国强(

),马自飞

北京工业大学经济与管理学院北京 100124

Constructing TCM Knowledge Graph with Multi-Source Heterogeneous Data

Zhai Dongsheng,Lou Ying,Kan Huimin,He Xijun,Liang Guoqiang(

),Ma Zifei

College of Economics and Management, Beijing University of Technology, Beijing 100124, China

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF (2073 KB) HTML ( 40 )
输出: BibTeX | EndNote (RIS)

摘要

【目的】基于多源异构数据构建中医药知识图谱，辅助研究人员进行中医药领域的创新研究。【方法】从IncoPat专利数据库获取中医药专利数据，从TCMSP、OMIM等数据库获取中药靶点、疾病等数据，利用深度学习信息联合抽取模型抽取中医药专利文本中的实体及关系，采用字符串匹配和词典等方式进行数据规范及实体对齐，进而基于所设计的中医药知识图谱本体结构完成知识图谱构建，在此基础上采用频次分析、关联规则Apriori算法对中药处方优化进行分析。【结果】本文所设计的本体结构共包含31种实体类型、48种语义关系，涵盖中医药领域专利中的解决方案、技术功效等特定实体；选取糖尿病肾病领域具体详解基于多源数据的中医药知识图谱构建及应用过程，验证了本文所构建知识图谱的有效性以及对处方优化提供中医药筛选范围的高效性。【局限】在专利文本信息抽取时，部分标注样本采用人工标注，耗费时间较长。【结论】以中医药专利数据为主、结合多源数据所构建的中医药知识图谱，能够为中医药领域创新研究提供数据支撑，该知识图谱不仅可以实现处方优化研究，也可用于中医药领域的多元研究。

	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
	翟东升
	娄莹
	阚慧敏
	何喜军
	梁国强
	马自飞

关键词 ：中医药知识图谱, 中医药创新, 专利文本, 糖尿病肾病

Abstract：

[Objective] This paper constructs a knowledge graph for Traditional Chinese Medicine(TCM) with multi-source heterogeneous data. It supports research innovation in TCM.[Methods] First, we obtained the TCM patents from the IncoPat database. We retrieved the targets and disease data from the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform(TCMSP) and Online Mendelian Inheritance in Man (OMIM). Then, we extracted the entity and relationship of TMC patents with the deep learning information joint extraction model. We also used string matching and dictionaries to finish the data specification and entity alignment. Third, we constructed the TCM knowledge graph based on the ontology structure we designed. Finally, we analyzed the optimization of TCM prescriptions with the frequency analysis and Apriori algorithm. [Results] The ontology structure designed in this paper contains 31 entity types and 48 semantic relationships, covering specific entities such as solutions and technical effects in TCM patents. We examined the effectiveness of the knowledge graph and the efficiency of optimizing prescriptions with the diabetic nephropathy data. [Limitations] It took us a long time to manually annotate some samples to extract textual information.[Conclusions] The knowledge graph constructed in this paper provides data support for TCM research. It also benefits prescription optimization and realizes multivariate research in TCM.

Key words： TCM Knowledge Graph TCM Innovation Patent Text Diabetic Nephropathy

收稿日期: 2022-08-25 出版日期: 2023-03-21

ZTFLH:	G255
	TP391
	R2-03

基金资助:*国家自然科学基金面上项目(71974009);国家自然科学基金青年项目(72204014)

通讯作者: 梁国强，ORCID：0000-0002-9669-4048，E-mail： Lianggq@bjut.edu.cn。

引用本文:

翟东升, 娄莹, 阚慧敏, 何喜军, 梁国强, 马自飞. 基于多源异构数据的中医药知识图谱构建与应用研究^*[J]. 数据分析与知识发现, 2023, 7(9): 146-158.
Zhai Dongsheng, Lou Ying, Kan Huimin, He Xijun, Liang Guoqiang, Ma Zifei. Constructing TCM Knowledge Graph with Multi-Source Heterogeneous Data. Data Analysis and Knowledge Discovery, 2023, 7(9): 146-158.

链接本文:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2022.0893 或 https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2023/V7/I9/146

Table 1 中医药知识图谱及本体结构类型

Table 2 中医药知识图谱的数据来源

Table 3 中医药领域信息抽取方法

Fig.1 基于多源异构数据的中医药知识图谱构建框架

Fig.2 基于多源异构数据的中医药知识图谱本体结构

Table 4 数据源

Fig.3 TPLinkerPLUS模型框架

标记类型		矩阵中的位置表示含义
实体标记类型	$e n t_t y p e, E H 2 E T$	同一个实体的开始和结束标记
关系标记类型	$r e l_t y p e, S H 2 O H$	具有某种关系类型的主语实体和宾语实体的开始标记
	$r e l_t y p e, S T 2 O T$	具有某种关系类型的主语实体和宾语实体的结束标记
	$r e l_t y p e, O H 2 S H$	具有某种关系类型的宾语实体和主语实体的开始标记
	$r e l_t y p e, O T 2 S T$	具有某种关系类型的宾语实体和主语实体的结束标记

Table 5 Handshaking标记框架

Table 6 本文利用BRAT标注的标准

Fig.4 BRAT标注示例

模型	TPLinkerPlus
$r e l_p r e c$ （关系_准确率）	0.894
$r e l_r e c a l l$ （关系_召回率）	0.854
$r e l_F 1$ （关系_ $F 1$ ）	0.874
$e n t_p r e c$ （实体_准确率）	0.918
$e n t_r e c a l l$ （实体_召回率）	0.931
$e n t_F 1$ （实体_ $F 1$ ）	0.925

Table 7 模型评估结果

Table 8 部分实体标准化示例

Fig.5 CN101653499B部分实体关系可视化

Fig.6 核心中医药及性味归经分析

Fig.7 强关联规则图
（注：圆圈大小代表支持度高低。）

[1]	程引, 高文波, 陈彦静, 等. 专利中药复方治疗骨质疏松症的用药规律分析[J]. 世界科学技术-中医药现代化, 2021, 23(9): 3298-3306.
[1]	(Cheng Yin, Gao Wenbo, Chen Yanjing, et al. Analysis of the Medication Patterns of Patented Chinese Herbal Compound for Osteoporosis[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2021, 23(9): 3298-3306.)
[2]	贾李蓉, 刘静, 于彤, 等. 中医药知识图谱构建[J]. 医学信息学杂志, 2015, 36(8): 51-53.
[2]	(Jia Lirong, Liu Jing, Yu Tong, et al. Construction of Traditional Chinese Medicine Knowledge Graph[J]. Journal of Medical Informatics, 2015, 36(8): 51-53.)
[3]	王松, 李正钧, 杨涛, 等. 中医药知识图谱研究现状及发展趋势[J]. 南京中医药大学学报, 2022, 38(3): 272-278.
[3]	(Wang Song, Li Zhengjun, Yang Tao, et al. Current Status and Development Trend of Knowledge Graph Research in Traditional Chinese Medicine[J]. Journal of Nanjing University of Traditional Chinese Medicine, 2022, 38(3): 272-278.)
[4]	Chu X L, Sun B Z, Huang Q C, et al. Quantitative Knowledge Presentation Models of Traditional Chinese Medicine (TCM): A Review[J]. Artificial Intelligence in Medicine, 2020, 103: Article No.101810.
[5]	曾子玲, 张华敏, 于彤, 等. 知识图谱及其关键技术在中医药领域的研究与应用综述[J]. 世界科学技术-中医药现代化, 2022, 24(2): 780-788.
[5]	(Zeng Ziling, Zhang Huamin, Yu Tong, et al. Review on the Research and Application of Knowledge Graph and Its Key Technologies in the Field of Traditional Chinese Medicine[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2022, 24(2): 780-788.)
[6]	于彤, 李敬华, 于琦, 等. 中医养生知识图谱的构建与应用[J]. 中国数字医学, 2017, 12(12): 64-66.
[6]	(Yu Tong, Li Jinghua, Yu Qi, et al. The Construction and Application of Knowledge Mapping of Health Preservation of Traditional Chinese Medicine[J]. China Digital Medicine, 2017, 12(12): 64-66.)
[7]	张莹莹. 基于知识图谱的舌像诊疗系统研究与构建[D]. 成都: 电子科技大学, 2019.
[7]	(Zhang Yingying. Research and Construction of Tongue Image Diagnosis and Treatment System Based on Knowledge Graph[D]. Chengdu: University of Electronic Science and Technology of China, 2019.)
[8]	朱玲, 李敬华, 于琦, 等. 中医哮喘领域本体的构建[J]. 中国实验方剂学杂志, 2017, 23(15): 222-226.
[8]	(Zhu Ling, Li Jinghua, Yu Qi, et al. Construction of Ontology of Asthma in Traditional Chinese Medicine[J]. Chinese Journal of Experimental Traditional Medical Formulae, 2017, 23(15): 222-226.)
[9]	周孜恒, 车立娟, 李明, 等. 基于《脾胃论》的方剂本体构建初探[J]. 数理医药学杂志, 2016, 29(5): 635-637.
[9]	(Zhou Ziheng, Che Lijuan, Li Ming, et al. Preliminary Research of Building Prescription Ontology Based on Treatise on Spleen and Stomach[J]. Journal of Mathematical Medicine, 2016, 29(5): 635-637.)
[10]	郝伟学. 中医健康知识图谱的构建研究[D]. 北京: 北京交通大学, 2017.
[10]	(Hao Weixue. Study on the Construction of Health Knowledge Graph of Traditional Chinese Medicine[D]. Beijing: Beijing Jiaotong University, 2017.)
[11]	原旎, 卢克治, 袁玉虎, 等. 基于深度表示的中医病历症状表型命名实体抽取研究[J]. 世界科学技术-中医药现代化, 2018, 20(3): 355-362.
[11]	(Yuan Ni, Lu Kezhi, Yuan Yuhu, et al. Depth Representation-Based Named Entity Extraction for Symptom Phenotype of TCM Medical Record[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2018, 20(3): 355-362.)
[12]	朱丹. 名老中医治疗脂肪性肝病的证治规律研究及知识图谱构建探索[D]. 北京: 中国中医科学院, 2019.
[12]	(Zhu Dan. Research on the Regularity of Syndrome and Treatment of Fatty Liver Disease by Famous Veteran TCM Doctors and Exploration of Knowledge Map Construction[D]. Beijing: China Academy of Chinese Medical Sciences, 2019.)
[13]	郑子强. 面向慢性肾脏病中医医案的知识图谱学习与推理研究[D]. 成都: 电子科技大学, 2020.
[13]	(Zheng Ziqiang. Research on Knowledge Graph Learning and Reasoning for TCM Prescription of Chronic Kidney Disease[D]. Chengdu: University of Electronic Science and Technology of China, 2020.)
[14]	郭文龙. 中医方剂知识图谱构建研究与实现[D]. 兰州: 兰州大学, 2019.
[14]	(Guo Wenlong. Research and Implementation of Knowledge Mapping of Traditional Chinese Medicine Prescription[D]. Lanzhou: Lanzhou University, 2019.)
[15]	尹丹, 周璐, 周雨玫, 等. 中医经方知识图谱“图搜索模式”设计研究[J]. 中国中医药信息杂志, 2019, 26(8): 94-98.
[15]	(Yin Dan, Zhou Lu, Zhou Yumei, et al. Study on Design of Graph Search Pattern of Knowledge Graph of TCM Classic Prescriptions[J]. Chinese Journal of Information on Traditional Chinese Medicine, 2019, 26(8): 94-98.)
[16]	赵凯, 王华星, 施娜, 等. 基于Neo4j桂枝汤类方知识图谱的研究与实现[J]. 世界中医药, 2019, 14(10): 2636-2639.
[16]	(Zhao Kai, Wang Huaxing, Shi Na, et al. Study and Implementation on Knowledge Graph of Guizhi Decoction Associated Formulas Based on Neo4j[J]. World Chinese Medicine, 2019, 14(10): 2636-2639.)
[17]	邝浩丹. 《伤寒论》知识图谱构建及其在阳明病的应用[D]. 杭州: 浙江中医药大学, 2021.
[17]	(Kuang Haodan. Construction of Knowledge Graph in Treatise on Febrile Diseases and Its Application in Yang Ming Disease[D]. Hangzhou: Zhejiang Chinese Medical University, 2021.)
[18]	王莉军, 李旭婕, 刘志辉, 等. 基于开放信息源的实体挖掘方法研究[J]. 情报科学, 2019, 37(8): 139-144.
[18]	(Wang Lijun, Li Xujie, Liu Zhihui, et al. Research on Entity Mining Method Based on Open Information Source[J]. Information Science, 2019, 37(8): 139-144.)
[19]	肖猛. 面向中医证候的健康领域知识图谱构建与应用研究[D]. 长春: 吉林大学, 2019.
[19]	(Xiao Meng. Research on Construction and Application of Knowledge Graph of Health Domain for Traditional Chinese Medicine Syndrome[D]. Changchun: Jilin University, 2019.)
[20]	Wang X, Zhang Y, Li Q, et al. Distantly Supervised Biomedical Named Entity Recognition with Dictionary Expansion[C]// Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine. IEEE, 2020: 496-503.
[21]	张德政, 谢永红, 李曼, 等. 基于本体的中医知识图谱构建[J]. 情报工程, 2017, 3(1): 35-42.
[21]	(Zhang Dezheng, Xie Yonghong, Li Man, et al. Construction of Knowledge Graph of Traditional Chinese Medicine Based on the Ontology[J]. Technology Intelligence Engineering, 2017, 3(1): 35-42.)
[22]	刘博, 杜建强, 聂斌, 等. 基于二阶HMM的中医诊断古文词性标注[J]. 计算机工程, 2017, 43(7): 211-216. doi: 10.3969/j.issn.1000-3428.2017.07.035
[22]	(Liu Bo, Du Jianqiang, Nie Bin, et al. Part-of-Speech Tagging of Traditional Chinese Medicine Diagnosis Ancient Prose Based on Second-Order HMM[J]. Computer Engineering, 2017, 43(7): 211-216.) doi: 10.3969/j.issn.1000-3428.2017.07.035
[23]	Kambhatla N. Combining Lexical, Semantic Features with Maximum Entropy Models for Extracting Relations[C]// Proceedings of the ACL 2004 on Interactive Poster and Demonstration Sessions. ACL, 2004: 178-181.
[24]	Saha S K, Sarkar S, Mitra P. Feature Selection Techniques for Maximum Entropy Based Biomedical Named Entity Recognition[J]. Journal of Biomedical Informatics, 2009, 42(5): 905-911. doi: 10.1016/j.jbi.2008.12.012 pmid: 19535010
[25]	Liu H L, Qin X N, Fu B. The Symptoms and Pathogenesis Entity Recognition of TCM Medical Records Based on CRF[C]// Proceedings of the 12th International Conference on Ubiquitous Intelligence and Computing and the 12th International Conference on Autonomic and Trusted Computing and 15th International Conference on Scalable Computing and Communications and Its Associated Workshops. IEEE, 2016: 1479-1484.
[26]	袁玉虎. 面向症状表型的命名实体抽取方法研究[D]. 北京: 北京交通大学, 2017.
[26]	(Yuan Yuhu. Research on Named Entity Extraction Method for Symptom Phenotype[D]. Beijing: Beijing Jiaotong University, 2017.)
[27]	Zhou P, Shi W, Tian J, et al. Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. ACL, 2016: 207-212.
[28]	Li J Q, Zhao S H, Yang J J, et al. WCP-RNN: A Novel RNN-Based Approach for Bio-NER in Chinese EMRs[J]. The Journal of Supercomputing, 2020, 76(3): 1450-1467. doi: 10.1007/s11227-017-2229-x
[29]	李明浩, 刘忠, 姚远哲. 基于LSTM-CRF的中医医案症状术语识别[J]. 计算机应用, 2018, 38(S2): 42-46.
[29]	(Li Minghao, Liu Zhong, Yao Yuanzhe. LSTM-CRF Based Symptom Term Recognition on Traditional Chinese Medical Case[J]. Journal of Computer Applications, 2018, 38(S2): 42-46.)
[30]	Huang Z H, Xu W, Yu K. Bidirectional LSTM-CRF Models for Sequence Tagging[OL]. arXiv Preprint, arXiv: 1508.01991.
[31]	Zeng D H, Sun C J, Lin L, et al. LSTM-CRF for Drug-Named Entity Recognition[J]. Entropy, 2017, 19(6): Article No.283.
[32]	罗计根. 面向中医领域知识图谱构建的关键技术研究及应用[D]. 南昌: 江西中医药大学, 2019.
[32]	(Luo Jigen. Research and Application of Key Technologies for Knowledge Graph in Traditional Chinese Medicine[D]. Nanchang: Jiangxi University of Traditional Chinese Medicine, 2019.)
[33]	蒋羽. 面向中医方剂配伍的中药文本挖掘研究[D]. 成都: 电子科技大学, 2019.
[33]	(Jiang Yu. Text Mining for Herb in Prescriptions of Traditional Chinese Medicine[D]. Chengdu: University of Electronic Science and Technology of China, 2019.)
[34]	Zhang M Y, Wang J, Zhang X J. Using a Pre-Trained Language Model for Medical Named Entity Extraction in Chinese Clinic Text[C]// Proceedings of the 10th International Conference on Electronics Information and Emergency Communication. IEEE, 2020: 312-317.
[35]	卢克治. 基于中医古籍的知识图谱构建与应用[D]. 北京: 北京交通大学, 2020.
[35]	(Lu Kezhi. The Construction and Application of Knowledge Graph Based on the Ancient Books of Traditional Chinese Medicine[D]. Beijing: Beijing Jiaotong University, 2020.)
[36]	聂佳. 基于知识发现的藏医药防治高原病用药规律及机制研究[D]. 成都: 成都中医药大学, 2017.
[36]	(Nie Jia. Study on the Law and Mechanism of Tibetan Medicine’s Prevention and Treatment of Plateau Disease Based on Knowledge Discovery[D]. Chengdu: Chengdu University of Traditional Chinese Medicine, 2017.)
[37]	谢先章. 面向中医骨科问诊的疾病知识图谱构建技术研究[D]. 昆明: 昆明理工大学, 2019.
[37]	(Xie Xianzhang. Research on Disease Knowledge Graph Construction Technology for Orthopedic Consultation of Traditional Chinese Medicine[D]. Kunming: Kunming University of Science and Technology, 2019.)
[38]	迟辉. 融合数据挖掘与复杂网络技术探索医师辨治失眠诊疗规律的可视化研究[D]. 北京: 北京中医药大学, 2020.
[38]	(Chi Hui. Fusion Data Mining and Complex Network Technology Explore the Visual Research of Physicians to Identify the Diagnosis and Treatment of Insomnia[D]. Beijing: Beijing University of Chinese Medicine, 2020.)
[39]	李翔, 吴磊宏, 范骁辉, 等. 复方丹参方主要活性成分网络药理学研究[J]. 中国中药杂志, 2011, 36(21): 2911-2915. pmid: 22308672
[39]	(Li Xiang, Wu Leihong, Fan Xiaohui, et al. Network Pharmacology Study on Major Active Compounds of Fufang Danshen Formula[J]. China Journal of Chinese Materia Medica, 2011, 36(21): 2911-2915.) pmid: 22308672
[40]	何家欢. 面向中药新药发现过程的文本挖掘方法研究[D]. 成都: 电子科技大学, 2021.
[40]	(He Jiahuan. Research on Text Mining Method for New Medicine Discovery of Chinese Medicine[D]. Chengdu: University of Electronic Science and Technology of China, 2021.)
[41]	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.
[41]	(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.)
[42]	龚倬. 基于知识图谱的中药复方靶标预测模型研究与实现[D]. 南京: 东南大学, 2021.
[42]	(Gong Zhuo. Research and Implementation for Target Prediction Model of Traditional Chinese Medicine Prescription Based on Knowledge Graph[D]. Nanjing: Southeast University, 2021.)
[43]	Ru J L, Li P, Wang J N, et al. TCMSP: A Database of Systems Pharmacology for Drug Discovery from Herbal Medicines[J]. Journal of Cheminformatics, 2014, 6: Article No.13.
[44]	Hamosh A, Scott A F, Amberger J S, et al. Online Mendelian Inheritance in Man (OMIM), a Knowledgebase of Human Genes and Genetic Disorders[J]. Nucleic Acids Research, 2005, 33(Suppl 1): D514-D517. doi: 10.1093/nar/gki033
[45]	Safran M, Rosen N, Twik M, et al. The GeneCards Suite[A]//Abugessaisa I, Kasukawa T. Practical Guide to Life Science Databases[M]. Springer, 2021: 27-56.
[46]	Szklarczyk D, Gable A L, Nastou K C, et al. The STRING Database in 2021: Customizable Protein-Protein Networks, and Functional Characterization of User-Uploaded Gene/Measurement Sets[J]. Nucleic Acids Research, 2021, 49(D1): D605-D612. doi: 10.1093/nar/gkaa1074 pmid: 33237311
[47]	Wang Y C, Yu B W, Zhang Y Y, et al. TPLinker: Single-Stage Joint Extraction of Entities and Relations Through Token Pair Linking[OL]. arXiv Preprint, arXiv: 2010.13415.
[48]	Richter R R, Austin T M. Using MeSH (Medical Subject Headings) to Enhance PubMed Search Strategies for Evidence-Based Practice in Physical Therapy[J]. Physical Therapy, 2012, 92(1): 124-132. doi: 10.2522/ptj.20100178 pmid: 21979271
[49]	Consortium U. UniProt: The Universal Protein Knowledgebase in 2021[J]. Nucleic Acids Research, 2021, 49(D1): D480-D489. doi: 10.1093/nar/gkaa1100 pmid: 33237286
[50]	Deutsch A, Xu Y, Wu M X, et al. TigerGraph: A Native MPP Graph Database[OL]. arXiv Preprint, arXiv: 1901.08248.
[51]	Stenetorp P, Pyysalo S, Topić G, et al. BRAT: A Web-Based Tool for NLP-Assisted Text Annotation[C]// Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics. 2012: 102-107.

[1]	施国良, 周抒, 王云峰, 施春江, 刘亮. 基于改进多头注意力机制的专利文本摘要生成研究^*[J]. 数据分析与知识发现, 2023, 7(6): 61-72.
[2]	佟昕瑀, 赵蕊洁, 路永和. 基于预训练模型的多标签专利分类研究^*[J]. 数据分析与知识发现, 2022, 6(2/3): 129-137.

Viewed

Full text

Abstract

Cited

Shared

Discussed