PharMeBINet

Heterogeneous biomedical pharmacological databases are important for multiple fields in bioinformatics. Hetionet is a freely available database combining diverse entities and relationships from 29 public resources. Therefore, it is used as the basis for this project. 19 additional pharmacological medical and biological databases such as CTD, DrugBank, and ClinVar are parsed and integrated into Neo4j. Afterwards, the information is merged into the Hetionet structure. Different mapping methods are used such as external identification systems or name mapping. The resulting open-source Neo4j database PharMeBINet has 2,869,407 different nodes with 66 labels and 15,883,653 relationships with 208 edge types. It is a heterogeneous database containing interconnected information on ADRs, diseases, drugs, genes, gene variations, proteins, and more. Relationships between these entities represent drug-drug interactions or drug-causes-ADR relations, to name a few. It has much potential for developing further data analyses including machine learning applications.

异构生物医学药理学数据库对生物信息学的多个研究领域均具有重要价值。Hetionet是一款免费可用的数据库，整合了来自29个公开资源的多样化实体与关联关系，因此本项目以其作为基础数据集。此外，本项目还对CTD、DrugBank、ClinVar等19个药理学、医学及生物学数据库进行解析，并将其整合至Neo4j图数据库中，随后将这些信息合并至Hetionet的结构体系内。本研究采用了多种映射方法，例如外部标识系统映射与名称映射。最终构建的开源Neo4j图数据库PharMeBINet包含2,869,407个不同节点（涵盖66种节点标签）以及15,883,653条关联关系（包含208种边类型）。该数据库为异构数据库，涵盖了药物不良反应（ADRs, Adverse Drug Reactions）、疾病、药物、基因、基因变异、蛋白质等多类互联信息。这些实体间的关联关系涵盖药物-药物相互作用、药物诱发不良反应关联等多种类型。该数据库在包括机器学习应用在内的各类后续数据分析研究中具备广阔的应用潜力。

搜集汇总

背景与挑战

背景概述

PharMeBINet是一个异质药理学医学生化网络数据集，主要服务于医疗专业人士和研究人员，相关研究成果已发表在科学数据期刊。该数据集提供了药物、医学和生化领域的多源异构数据。