QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3856

This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3856 (TID: 10768), and it has 80 rows and 62 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied.

本数据集包含源自ChEMBL第17版的定量构效关系（Quantitative Structure-Activity Relationship, QSAR）数据，记录了多款化合物针对药物靶点ChEMBL_ID: CHEMBL3856（TID: 10768）的活性值，活性单位为伪pCI50。该数据集共计80条样本与62项特征（不含分子ID（molecule_id）与类别特征pXC50）。所涉特征均为基于SMILES（Simplified Molecular-Input Line-Entry System, SMILES）字符串生成的分子描述符（Molecular Descriptors）。本数据集已完成缺失值补全，采用中位数法进行缺失值插补；同时执行了特征选择操作。