面向科学知识发现的造血干细胞知识图谱构建研究

doi:10.11871/jfdc.10-1649.2021.06.006

数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (6): 81-97.

doi: 10.11871/jfdc.10-1649.2021.06.006

• 专刊:科学大数据挖掘与知识发现 • 上一篇下一篇

面向科学知识发现的造血干细胞知识图谱构建研究

胡正银^1,^2,^*(),刘蕾蕾²(),陈文杰¹(),刘春江¹(),钱力^2,³(),宋亦兵⁴

1. 中国科学院成都文献情报中心,四川成都 610041
2. 中国科学院大学,经济与管理学院,图书情报与档案管理系,北京 100190
3. 中国科学院文献情报中心,北京 100190
4. 中国科学院广州生物医药与健康研究院,广东广州 510530

收稿日期:2021-11-10 出版日期:2021-12-20 发布日期:2022-01-26
通讯作者: 胡正银
作者简介:胡正银,中国科学院成都文献情报中心,知识系统部主任,中国科学院大学情报学硕士研究生导师,中国科学院西部之光人才培养计划人选,博士,研究馆员,合作出版专著（编著）3部、发表论文80余篇、申请计算机软件著作权8项。主要研究领域为科技大数据分析方法与技术、科技情报挖掘与知识发现。
负责制定论文研究框架、负责构建HSC KG与负责SKD场景分析,撰写论文初稿。
HU Zhengyin, Ph.D, is a professor of Chengdu Library and Information Center, Chinese Academy of Sciences, and master supervisor of University of Chinese Academy of Science, and a selected candidate of West Light Talent Program of the Chinese Academy of Sciences. He has published three monographs and more than 80 papers and has applied 8 computer software copyright cooperatively. His main research interests include S&T big data analysis, S&T intelligence mining and knowledge discovery.
In this paper, he is responsible for research framework design, generating the data of HSC KG, and constructing the SKDsce-narios. E-mail: huzy@clas.ac.cn;|刘蕾蕾,中国科学院大学,情报学硕士研究生,研究方向为知识图谱、科技情报知识挖掘与知识发现。
参与设计论文研究框架、参与构建HSC KG。
LIU Leilei is a master’s student of Infor-mation and Archives Management, University of Chinese Aca-demy of Sciences. Her research interests include knowledge gra-ph, S&T intelligence mining, scientific knowledge discovery.
In this paper, she is responsible for designing the research framework and generating the data of HSC KG. E-mail: liuleilei@mail.las.ac.cn;|陈文杰,中国科学院成都文献情报中心,馆员,从事知识挖掘、知识发现研究与知识服务平台建设,研究方向为机器学习、表示学习和知识图谱。
参与SKD场景分析,开发HSC KG网站。
CHEN Wenjie is a librarian of Chengdu Library and Infor-mation Center, Chinese Academy of Sciences. He has long been engaged in the research of knowledge mining, knowledge discovery and the construction of the knowledge service system. His research interests include machine learning, representation learning, and knowledge graph.
In this paper, he is responsible for conducting the SKD scena-rios and developing the HSC KG website. E-mail: chenwj@clas.ac.cn;|刘春江,中国科学院成都文献情报中心,副研究馆员,研究方向为专利挖掘与知识发现。
协助HSC KG构建和SKD场景分析。
LIU Chunjiang is an associated professor of Chengdu Library and Information Center, Chinese Academy of Sciences. His research interests include patent mining and knowledge discovery.
LIU Chunjiang helps to generate the HSC KG and design the SKD scenarios. E-mail: liucj@clas.ac.cn;|钱力,中国科学院文献情报中心,知识系统部主任,中国科学院大学情报学硕士研究生导师,博士,研究馆员。研究领域为科技大数据分析方法与技术、科技情报挖掘与智能知识服务。
协助HSC KG构建和SKD场景分析。
QIAN Li, Ph.D, is a professor of Library and Information Center, Chinese Academy of Sciences, master supervisor of University of Chinese Academy of Science. His research interests include S&T big data analysis, S&T intelli-gence mining, and intelligent knowledge service.
QIAN Li helps to generate the HSC KG and design the SKD scenarios. E-mail: qianl@mail.las.ac.cn;|宋亦兵,中国科学院广州生物医药与健康研究院信息情报中心主任,高级工程师,研究领域为生命医学学科情报分析、生命医学知识服务。
协助HSC KG构建,协助解读SKD分析结果。
SONG Yibing, senior engineer, is the director of Information Center of Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences. His research interests include biomedical subject information analysis and biomedical know-ledge service.
SONG Yibing helps to generate the HSC KG and interpret SKD analysis results. E-mail: song_yibing@gibh.ac.cn;
基金资助:
National Key Research and Development Program “Application demonstration of comprehensive science and technology services for typical industries in Pearl River Delta Urban Agglomeration”(Grant No:2018YFB1404205);the Ministry of Science and Technology Innovation Methods Special Project(Grant No: 2019IM020100)

Generating a Hematopoietic Stem Cell Knowledge Graph for Scientific Knowledge Discovery

HU Zhengyin^1,^2,^*(),LIU Leilei²(),CHEN Wenjie¹(),LIU Chunjiang¹(),QIAN Li^2,³(),SONG Yibing⁴

1. Chengdu Library and Information Centre, Chinese Academy of Sciences, Chengdu, Sichuan 610041, China
2. Department of Library, Information and Archives Management, School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190, China
3. National Science Library, Chinese Academy of Sciences, Beijing 100190, China
4. Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou, Guangdong 510530, China

Received:2021-11-10 Online:2021-12-20 Published:2022-01-26
Contact: HU Zhengyin

摘要/Abstract

摘要：

【目的】造血干细胞（HSC）是临床治疗最有效的干细胞之一,通过文献挖掘发现领域重要的知识实体、知识关系和知识路径对于HSC领域知识发现具有重要意义。知识图谱（KG）是一种新型知识组织技术,支持知识实体、知识关系和知识路径等知识单元的多层次、细粒度、富语义知识组织与知识互联,被广泛应用于科学知识发现（SKD）中。【方法】本文提出了一个基于“主-谓-宾”（SPO）三元组构建领域知识图谱的框架,该框架包括文献检索、SPO提取、SPO清洗、SPO排序、知识发现模式集成和图谱构建等过程。然后,基于该框架构建了HSC 知识图谱。最后,基于HSC知识图谱,介绍了“开放式知识发现”、“封闭式知识发现”与“研究主题挖掘”三种HSC领域SKD场景。【结果】结果表明,利用该框架构建的HSC知识图谱具有“使用图数据结构”、“集成知识发现模式”、“融合原生图挖掘算法”和“易于使用”等优点,可以有效地支持HSC领域知识发现。

关键词: 知识图谱, SPO三元组, 科学知识发现, 文献挖掘, 造血干细胞

Abstract:

[Objective] The hematopoietic stem cell (HSC) is one kind of the most effective stem cells for clinical treatments. It is of great significance to discover important knowledge entities, knowledge relations, and knowledge paths by literature mining for HSC knowledge discovery. Knowledge graph (KG), which represents knowledge entities and their relations with more details in a simple manner is widely used in scientific knowledge discovery (SKD).[Methods] This paper proposes a framework of generating KG using Subject-Predicate-Object (SPO) triples from literature, which includes six processes: literature retrieval, SPO extracting, SPO cleanup, SPO ranking, discovery pattern integrating, and graph building. Then, an HSC KG was constructed based on the Neo4j graph database following the framework. Finally, three kinds of SKD scenarios using HSC KG are introduced by empirical analysis. [Results] The results show that HSC KG has the advantages of “using graph data structure”, “integrating discovery patterns”, “fusing native graph mining algorithms”, and “easy to use”, which can effectively support deep open discovery, close discovery, and topic discovery in HSC.

Key words: knowledge graph, SPO triple, scientific knowledge discovery, literature mining, hematopoietic stem cell

胡正银,刘蕾蕾,陈文杰,刘春江,钱力,宋亦兵. 面向科学知识发现的造血干细胞知识图谱构建研究[J]. 数据与计算发展前沿, 2021, 3(6): 81-97.

HU Zhengyin,LIU Leilei,CHEN Wenjie,LIU Chunjiang,QIAN Li,SONG Yibing. Generating a Hematopoietic Stem Cell Knowledge Graph for Scientific Knowledge Discovery[J]. Frontiers of Data and Computing, 2021, 3(6): 81-97.

图/表 10

Fig. 1

Table 1

Fig.2

Table 2

Table 3

Table 4

Fig.3

Table 5

Fig. 4

Fig.5

参考文献 29

[1]	Swanson D. Medical literature as a potential source of new knowledge[J]. Bull Med Libr Assoc, 1990,78(1):29-37.
[2]	Hey T, Tansley S, Tolle K. The Fourth Paradigm: Data-Intensive Scientific Discovery[J]. Proceedings of the IEEE, 2011,99(8):1334-1337.
[3]	Smalheiser N R, Torvik V I. The Place of Literature-Based Discovery in Contemporary Scientific Practice[J]. Springer Berlin Heidelberg, 2008,15:13-22.
[4]	H. Zhengyin, L. Leilei, D. Bing, et al. Discovering Subject Knowledge in Life and Medical Sciences with Knowledge Graph[J]. Data Analysis and Knowledge Discovery, 2020,4(11):1-14.
[5]	Xu Z, Y Sheng, He L, et al. Review on Knowledge Graph Techniques[J]. Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2016,45:589-606.
[6]	Guilin Q I, Gao H, Tianxing W U. The Research Adva-nces of Knowledge Graph[J]. Technology Intelligence Engineering, 2017,3:4-25.
[7]	H. Sha, D. Fang, H. Linping, et al. Biology and Clinical Application Research of Hematopoietic Stem Cells[J]. Chinese Journal of Cell Biology, 2018,40:2237-2248.
[8]	Rindflesch T C, Fiszman M. The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text[J]. Journal of Biomedical Informatics, 2003,36:462-477.
[9]	He F, Zhang L, Qu W, et al. Research on Construction of Knowledge Graph of Intestinal Cells[J]. Journal of Artificial Intelligence for Medical Sciences, 2020,1:15-22.
[10]	H. Zhengyin, Z. Rongqiang, Q. Xiaochu, et al. A Method of Biomedical Knowledge Discovery by Literature Mining Based on SPO Predications: A Case Study of Induced Pluripotent Stem Cells[C]. Proceedings of 2018 Machine Learning and Data Mining in Pattern Recog-nition, 2018: 383-393.
[11]	Kilicoglu H, Rosemblat G, Fiszman M, et al. Con-structing a semantic predication gold standard from the biomedical literature[J]. Bmc Bioinformatics, 2011,12:1-17.
[12]	Rindflesch T C, Kilicoglu H, Fiszman M, et al. Semantic MEDLINE: An advanced information management app-lication for biomedicine[J]. Information services & use, 2011,31(1-2):15-21.
[13]	C. W. Hsuan, A. Alexis, L. Robert, et al. PubTator cent-ral: automated concept annotation for biomedical full text articles[J]. Nucleic Acids Research, 2019,47:587-593.
[14]	A.Lamurias, J. D. Ferreira, L. A. Clarke, et al. Generating a Tolerogenic Cell Therapy Knowledge Graph from Lite-rature[J]. Frontiers in Immunology, 2017,8:1-12.
[15]	S. Pyysalo, S. Baker, I. Ali, et al. LION LBD: A Litera-ture-Based Discovery System for Cancer Biology[J]. Bioinformatics, 2019,35:1553-1561.
[16]	H. Zhengyin, X Haiyun, Q. Xiaochu. A Knowledge Graph of Stem Cell Oriented to Subject Knowledge Discovery[C]. Proceedings of the 7th IEEE International Conference on Healthcare Informatics, Xi’an, China, 2019.
[17]	S. Henry, B. Mcinnes. Literature Based Discovery: Mo-dels, methods, and trends[J]. Journal of Biomedical Informatics, 2017,74:20-32.
[18]	Z. Zhiqiang, H. Zhengyin, Y. Ning, et al. Big Data Pla-tform for Subject Knowledge Discovery in the Stem Cell Field[C]. China’s e-Science Blue Book 2020, Beijing: Science Press, 2020: 85-92.
[19]	Du J, Li X. Towards a Knowledge Graph of Combined Drug Therapies using Semantic Predications from Bio-medical Literature (Preprint)[J]. JMIR Medical Infor-matics, 2020,8(4):162-169.
[20]	M. Fiszman, T.C. Rindflesch, H. Kilicoglu. Abstraction summarization for managing the biomedical research literature[C]. Proceedings of the HLT-NAACL Workshop on Computational Lexical Semantics, 2004: 76-83.
[21]	NLM. Semantic Type Mappings[EB/OL]. 2018.https://metamap.nlm.nih.gov/Docs/SemanticTypes2018AB.txt.
[22]	L. Chen, W. Wesley & S. Fred, et al. Path knowledge discovery: Association mining based on multi-category lexicons[C]. 2014 IEEE International Conference on Big Data, Washington, DC, 2014: 1049-1059.
[23]	Hristovski D, Kastrin A, Peterlin B, et al. Combining semantic relations and DNA microarray data for novel hypotheses generation.[J]. Lecture Notes in Computer Science, 2010,6004:53-61.
[24]	T. Cohen, D. Widdows, R.W. Schvaneveldt, et al. Disco-very at a distance: Farther journeys in predication space[C]. Bioinformatics and Biomedicine Workshops (BIBMW), 2012 IEEE International Conference, 2012: 158-164.
[25]	L. Zongyao, Y. Zhihao, W. Xiaofang, et al. Using sem-antic relations for biomedical literature-based discovery[J]. Journal of Chinese information process, 2016,30:176-182.
[26]	M. Needham & A. Hodler. Graph Algorithms: Practical Examples in Apache Spark and Neo4j[M]. Sebastopol: O’Reilly Press, 2019.
[27]	Kiem H P, Jerome K, Deeks S, et al. Hematopoietic-Stem-Cell-Based Gene Therapy for HIV Disease[J]. Cell Stem Cell, 2012,10(2):137-147.
[28]	R.K. Gupta S. Abdul-Jawad, L.E. McCoy, et al. HIV-1 remission following CCR5Δ32/Δ32 haematopoietic stem-cell transplantation[J]. Nature, 2019,568:244-248.
[29]	D. Jian. Discover the unknown known: the past, presen and future[EB/OL]. 2021.

Literature type	Database	Retrieval strategy	Number
Paper	PubMed	(((((((stem cells) OR stem cell)) AND (((((stem cellulose) OR stem. Cellular) OR cello) OR cellar) OR cellphone))) OR ((((((((((((ESC) OR ASC) OR iPS) OR PGC) OR MSC) OR CSC) OR LSC) OR TSC) OR ADSC) OR HSC)) near ((cell) OR cells)))) AND ((Hematopoiet) AND stem cell) Publication Date：2010/01/01 - 2019/12/31	21,098
Patent	DI	(((ALLD=((“stem cells” OR “stem cell”) NOT (“stem cellulose” or “stem. Cellular” or “cello” or “cellar” or “cellphone”)) OR ALLD=((ESC or ASC or iPS or PGC or MSC or CSC or LSC or TSC or ADSC or HSC) near (cells OR cell)) OR ALLD=(((“totipotent” or “pluripotent” or “multipotent” or “unipotent” or “progenitor” or “precursor”) NOT (“non-pluripotent”)) ADJ (cells OR cell))) NOT ALLD=(“fuel cell” or “in-plane switching” or “Intrusion Prevention System”) NOT IC=(H or D or E or F or A23 or A46 or A24 or A47 or A63 or A62 or A44 or A45 or C07B or C07C or C07D or C07F or C07J)) AND ICR=(C12N) AND SSTO=(“HEMATOPOIETIC STEM CELL” “HSC”)):AY>=(2010) AND AY<=(2019): CC=(WO OR US OR EP OR JP):1 AND 2 AND 3 Application Year：2010 - 2019	4,786

A-B relations	B-C relations	A-C relations
<INHIBITS, STIMULATES,COEXISTS_WITH, INTERACTS_WITH>	<ASSOCIATED_WITH>	May_Treat
< INHIBITS >	<CAUSES>	May_Disrupt
<INHIBITS, COEXISTS_WITH, INTERACTS_WITH>	<PREVENTS>	May_Prevent
<AFFECTS >	<AFFECTS, DISRUPTS >	Indirect_Affect

Label	Semantic Type Abbreviation	Number	Samples
DISEASE	dsyn, emod, sosy	1,485	Atherosclerosis, Myocardial Infarction, Diabetes, Acute coronary syndrome, Hematological Disease…
GENE	genf, gngm	3,106	CD34 gene, CCR9 gene, KDR gene, CXCR4 Receptors, Interleukin 7 Receptor, Interleukin-6…
CELL	celc, celf, cell, comd	890	HSC, Stem cells, Bone Marrow Cells, Endothelial Cells, Jurkat Cells, cytokine secretion, ES Cell Line…
TISSUE	ortf, tisu	226	Umbilical Cord Blood, Endothelium, Transplanted tissue, Bone Matrix, Myocardium…
VIRUS	virs	101	HIV, Herpesvirus 6, Retroviridae, Adenoviruses, BK Virus, Cytomegalovirus…
Others (Organism, Receptor, Vitamin, …)	other semantic types	8,809	Granulocyte Colony-Stimulating Factor, Hepatocyte Growth Factor, MicroRNAs…

	Semantic Group	Relationships Type
Knowledge Entity — Knowledge Entity	Interaction Group	ASSOCIATED_WITH, INTERACT_WITH, PRODUCE, CONVERTS_TO, COEXISTS_WITH
	Function Group	TREAT, PREVENT, USE, MEASURE, METHOD_OF, ADMINISTERED_TO
	Distinguish Group	DIAGNOSES, MANIFESTATION_OF
	Compare Group	HIGH_THAN, LOWER_THAN, compared_with
	Location Group	OCCURS_IN
	Affect Group	AFFECTS, DISRUPTS, CAUSES, INHITBITS, PREDISPOSE, AUGMENTS, PRECEDE, PROCESS_OF, COMPLICATES, STIMULATE,
Knowledge Entity— Literature	Subordination	belong_to
SPO— Literature	Subordination	belong_to

Name	CUI	Frequency
Bone remodeling	C0085268	22
Tissue homeostasis	C1523351	20
Natural regeneration	C0034963	17
Bone metabolism	C0596204	15
Cytokine production	C1327413	15
Degenerative abnormality	C0011164	14
Dysmyelopoietic Syndromes	C0026986	11
Heart valve disease	C0018824	10

面向科学知识发现的造血干细胞知识图谱构建研究

Generating a Hematopoietic Stem Cell Knowledge Graph for Scientific Knowledge Discovery

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 29

相关文章 8

编辑推荐

Metrics

本文评价

[1]	罗婕溪,刘帅,张玉志,李正丹,孙羽菲,张圣林. 基于知识图谱技术的线上教学资源推荐系统设计与实现[J]. 数据与计算发展前沿, 2022, 4(3): 3-18.
[2]	兰格,王瑾瑜,孙羽菲,张玉志. 基于知识图谱的图匹配文本分类[J]. 数据与计算发展前沿, 2022, 4(2): 39-49.
[3]	陶磊,苏晨阳,李正丹,朱静雯,张玉志. 基于ElasticSearch和语义相似度匹配的教学资源搜索策略[J]. 数据与计算发展前沿, 2022, 4(2): 50-62.
[4]	白如江*,赵梦梦,张玉洁,董坤. 科技文献挖掘工具平台与关键技术综述[J]. 数据与计算发展前沿, 2021, 3(6): 60-80.
[5]	李序,连一峰,张海霞,黄克振. 网络安全知识图谱关键技术[J]. 数据与计算发展前沿, 2021, 3(3): 9-18.
[6]	刘佳,夏晓蕾,王姝,王丽娟,郭志斌,胡良霖,周园春. 科技资源标识服务系统及创新应用[J]. 数据与计算发展前沿, 2020, 2(6): 62-73.
[7]	孙艳艳,毛卫南,毛宇斐,吴海博. 基于区域科技资源服务平台的虚拟创新生态系统构建研究[J]. 数据与计算发展前沿, 2020, 2(5): 30-40.
[8]	周园春,常青玲,杜一. SKS：一种科技领域大数据知识图谱平台 ^*[J]. 数据与计算发展前沿, 2019, 1(1): 82-93.