MolGen/ZINC_250K_prop_train_val_split

该数据集是一个包含化学分子信息的复杂数据集，其中包括不同表示方式的分子结构（SMILES、Deep SMILES、SELFIES）和多个分子属性的数值特征。数据集还包含了与特定蛋白质结合的相关特征。数据集分为训练集和验证集，用于机器学习模型的训练和评估。

This dataset is a complex collection of chemical molecule information, including various molecular structure representations (SMILES, Deep SMILES, SELFIES) and numerical features of multiple molecular properties. The dataset also includes features related to binding with specific proteins. It is split into training and validation sets for machine learning model training and evaluation.