CryptoBench
收藏IEEE2026-04-17 收录
下载链接：
https://ieee-dataport.org/documents/crypkanet-datasets
下载链接
链接失效反馈官方服务：
资源简介：
The dataset was curated through a pipeline that included resolution filtering, geometric quality assessment, pocket RMSD calculation, and ligand-based filtration, followed by clustering at 40% sequence similarity. To prevent data leakage, the dataset was split into training and test sets with an 8:2 ratio. Finally, the dataset contains 1,107 protein structures and 1,361 CBSs.
提供机构：
Xianchen Zheng
