基于多源数据的疾病知识图谱构建研究

A Research on the Construction of Disease Knowledge Graph Based on Multi-source Data

[目的/意义]基于PubMed、OMIM等医学数据库中的多源数据设计疾病知识图谱构建方案,为疾病的生物学实验研究及诊断治疗提供参考和依据。[方法/过程]首先利用语义分析工具SemRep抽取SPO三元组,通过实体对齐、关系映射等数据处理方法进行知识融合,然后利用Neo4j图数据库实现知识存储及可视化展示,以多囊卵巢综合征为例进行实证检验和分析,最终获得61589个SPO三元组、34697个实体和27种语义关系并归纳总结7种语义模式。[局限]数据处理时,涉及人工审查,但由于数据量较大,审查过程中可能存在些许误差。[结果/结论]本研究改进现有的知识融合方法,验证了该疾病知识图谱构建方案的可行性。为后续基于疾病知识图谱进行医学领域知识发现探索奠定基础。

[Objective/Significance]Based on the multi-source data in PubMed,OMIM and other medical databases,the construction scheme of disease knowledge graph is designed to provide reference and basis for biological experimental research,diagnosis and treatment of diseases.[Methods/Processes]Firstly,SPO triples are extracted by SemRep,and knowledge fusion is carried out by data processing methods such as entity alignment and relationship mapping.Then,knowledge storage and visual display are realized by Neo4j graph database.Taking polycystic ovary syndrome as an example,61589 SPO triples,34697 entities and 27 semantic relationships are finally obtained,and 7 semantic patterns are summarized.[Limitations]In the process of data processing,manual examination is involved,but due to the large amount of data,there may be some errors in the examination process.[Results/Conclusions]This study improves the existing knowledge fusion method and verifies the feasibility of the disease knowledge graph construction scheme.It lays a foundation for the follow-up exploration of knowledge discovery in medical field based on disease knowledge graph.