Knowledge Graph from VCF Files
收藏arXiv2025-09-30 收录
下载链接:
https://github.com/MU-Data-Science/GAF
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是一个由511个VCF文件生成的大型知识图谱,包含了31亿个三元组信息,用于下游的图神经网络任务。该数据集通过整合变异级别的遗传信息和患者元数据构建而成,并采用BlazeGraph进行存储,以便进行高效的查询。其规模达到了31亿个三元组,旨在支持图神经网络的相关下游任务。
This dataset is a large-scale knowledge graph generated from 511 VCF files, which contains 3.1 billion triples and is designed for downstream graph neural network tasks. It is constructed by integrating variant-level genetic information and patient metadata, and stored using BlazeGraph to facilitate efficient querying. Boasting a scale of 3.1 billion triples, this dataset aims to support relevant downstream tasks for graph neural networks.
提供机构:
IEEE Dataport



