chandar-lab/ZINC_250k

该数据集是一个包含多种分子特征和药物相关数值特征的集合，适用于药物设计和分子性质预测等研究。它包含了分子的SMILES、Deep SMILES、SELFIES等表示，以及与多种药物分子相关的数值属性，如相似度评分和活性评分等。

This dataset is a collection of various molecular features and drug-related numerical attributes suitable for research in drug design and molecular property prediction. It includes representations of molecules such as SMILES, Deep SMILES, and SELFIES, as well as numerical properties related to various drug molecules, such as similarity scores and activity scores.