基于领域知识图谱的生命医学学科知识发现探析  

Discovering Subject Knowledge in Life and Medical Sciences with Knowledge Graph

作　　者：胡正银[1,2] 刘蕾蕾 代冰 覃筱楚 Hu Zhengyin;Liu Leilei;Dai Bing;Qin Xiaochu(Chengdu Library and Information Center,Chinese Academy of Sciences,Chengdu 610041,China;Department of Library,Information and Archives Management,School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190,China;Guangzhou Regenerative Medicine and Health Guangdong Laboratory,Guangzhou 510700,China;Guangzhou Institutes of Biomedicine and Health,Chinese Academy of Sciences,Guangzhou 510530,China)

机构地区：[1]中国科学院成都文献情报中心,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]广州市再生医学与健康广东省实验室,广州510700 [4]中国科学院广州生物医药与健康研究院,广州510530

出　　处：《数据分析与知识发现》2020年第11期1-14,共14页Data Analysis and Knowledge Discovery

基　　金：中国科学院“十三五”信息化专项“面向干细胞领域知识发现的科研信息化应用”(项目编号:XXH13506-203);中国科学院文献情报能力建设专项“科技知识服务大数据基础设施”(项目编号:Y9290002);科技部创新方法工作专项“基于群智理论的创新方法新系统研究与应用示范”(项目编号:2019IM020100)的研究成果之一。

摘　　要：【目的】探讨融合多源数据,开展深层次学科知识发现研究与服务的方法。【方法】通过构建科技文献SPO语义网络形成领域知识图谱的核心;通过"实体对齐、概念层次融合与关系融合"实现多源异构数据融合,生成完整领域知识图谱;基于领域知识图谱开展深层次学科知识发现;选择造血干细胞癌症治疗进行实证研究。【结果】提出一套基于知识图谱的学科知识发现方法框架KGSKD,可多维度、细粒度融合多源异构数据,定义数据间复杂语义关系,原生支持知识推理、路径发现、链路预测等知识发现应用。【局限】KGSKD存在容易出现数据过饱和、知识发现过程可解释性较差、与领域专家沟通难度较高等局限。【结论】KGSKD具有数据类型更丰富、知识关联更全面、挖掘方法更先进、发现结果更深入等优势,可更有效地支持生命医学学科深层次知识发现研究与服务。[Objective]This paper explores new methods for deep subject knowledge discovery using multi-source heterogeneous data.[Methods]First,we constructed a SPO semantic network of literature to create the core domain knowledge graph.Then,we implemented multi-source heterogeneous data fusion through“entity alignment,concept level fusion and relationship fusion”to obtain the whole domain knowledge graph.Finally,we discovered deep subject knowledge with the help of this knowledge graph.We examined our method with data on Hematopoietic Stem Cell for Cancer Treatment(HSCCT).[Results]This paper proposed a knowledge graphbased framework for subject knowledge discovery(KGSKD),which fuses multi-source heterogeneous data multidimensionally and fine-grainedly,enriches semantic relationships among data,and supports knowledge discovery techniques such as knowledge inference,pathfinder,and link prediction natively.[Limitations]KGSKD has some limitations including data supersaturation,poor interpretability of knowledge discovery results and difficulty in communicating with domain experts.[Conclusions]KGSKD has the advantages of“richer data types”,“more comprehensive knowledge linkage”,“more advanced mining methods”and“deeper discovery results”,which effectively supports research and services of deep knowledge discovery in life sciences and medicine.

关 键 词：学科知识发现 知识图谱 SPO三元组 数据融合 实体对齐 

分 类 号：G251[文化科学—图书馆学] TP393[自动化与计算机技术—计算机应用技术]