maomlab/ChAFF
收藏Hugging Face2025-08-29 更新2025-10-18 收录
下载链接：
https://hf-mirror.com/datasets/maomlab/ChAFF
下载链接
链接失效反馈官方服务：
资源简介：
ChAFF数据集包含约200K个经过审核的活性化合物列表，源自大约90个不同的生物测定数据集，专注于已知测定干扰artifacts。数据集通过RDKit和MolVS进行了SMILES标准化，包括分子净化和片段移除，适用于训练和评估机器学习模型。
The ChAFF dataset collection contains ~200K curated Active compound lists from ~90 different BioAssay datasets, focusing on known assay interference artifacts. SMILES standardization using RDKit and MolVS, including molecule sanitization and fragment removal, has been applied. The dataset is suitable for training and evaluating machine learning models.
提供机构：
maomlab
