ChEMBL-v33 LogD structure activity

This is an update of the dataset for the previously published manuscript A confidence predictor for logD using conformal regression and a support-vector machine. The main update is that it is based on a newer version of ChEMBL (v33, May 2023). The dataset consists of 2,311,523 chemical structures and the LogP property from ChEMBLS is CX LogD 7.4. The data was extracted following the procedure outlined in download data.

本数据集为此前发表的题为《基于共形回归（conformal regression）与支持向量机的logD置信预测器》的论文配套数据集的更新版本。本次更新的核心改动为：数据集基于2023年5月发布的最新版ChEMBL数据库（版本33）。数据集共包含2,311,523个化学结构，其源自ChEMBL的属性为CX LogD 7.4。本数据集按照「下载数据」章节中载明的流程完成提取。