bnymnsen/CROssBARv2-KG

CROssBARv2-KG是一个异构的、通用的生物医学知识图谱系统，包含约270万个节点和1260万条边，涵盖14种不同的节点类型和51种不同的边类型，整合了34个生物数据源。数据集还包括多个本体（如基因本体、Mondo疾病本体）以及丰富的节点和边属性。此外，CROssBARv2通过生成和存储关键生物实体（如蛋白质、药物和基因本体术语）的嵌入，增强了语义深度。数据集分为节点和边两个主要目录，节点目录包含定义生物实体的CSV文件，边目录包含定义这些实体之间关系的CSV文件。

The CROssBARv2-KG is a heterogeneous and general-purpose biomedical knowledge graph system comprising approximately 2.7 million nodes spanning 14 distinct node types and around 12.6 million edges representing 51 different edge types, all integrated from 34 biological data sources. The dataset also incorporates several ontologies (e.g., Gene Ontology, Mondo Disease Ontology) along with rich metadata captured as node and edge properties. Additionally, CROssBARv2 enhances semantic depth by generating and storing embeddings for key biological entities, such as proteins, drugs, and Gene Ontology terms. The dataset is organized into two primary directories: nodes, containing CSV files defining biological entities, and edges, containing CSV files defining relationships between these entities.