DRKG

该数据集是一个生物知识图谱，它将基因、化合物、疾病、生物过程、副作用和症状等多源信息相互关联。它还包括了与新冠病毒最新研究相关的数据。具体规模上，该数据集包含了107种关系、97,238个实体以及5,874,261个三元组信息。其任务重点在于链接预测和规则挖掘。This dataset is a biological knowledge graph that interrelates multi-source information such as genes, compounds, diseases, biological processes, adverse effects, symptoms and other related entities. It also includes data associated with the latest research on SARS-CoV-2 (COVID-19). In terms of scale, this dataset contains 107 types of relations, 97,238 entities and 5,874,261 triples. The core tasks of this dataset focus on link prediction and rule mining.