Data for: Advances and critical assessment of machine learning techniques for prediction of docking scores

Semi-flexible docking was performed using AutoDock Vina 1.2.2 software on the SARS-CoV-2 main protease Mpro (PDB ID: 6WQF).
Two data sets are provided in the xyz format containing the AutoDock Vina docking scores. These files were used as input and/or reference in the machine learning models using TensorFlow, XGBoost, and SchNetPack to study their docking scores prediction capability. The first data set originally contained 60,411 in-vivo labeled compounds selected for the training of ML models. The second data set,denoted as in-vitro-only, originally contained 175,696 compounds active or assumed to be active at 10 μM or less in a direct binding assay. These sets were downloaded on the 10th of December 2021 from the ZINC15 database. Four compounds in the in-vivo set and 12 in the in-vitro-only set were left out of consideration due to presence of Si atoms. Compounds with no charges assigned in mol2 files were excluded as well (523 compounds in the in-vivo and 1,666 in the in-vitro-only..., Molecular docking calculations and the machine learning approaches are described in the Computational details section of [1].
Reference[1] Lukas Bucinsky, Marián Gall, Ján Matúška, Michal Pitoňák, Marek Štekláč. Advances and critical assessment of machine learning techniques for prediction of docking scores. Int. J. Quantum. Chem. (2023) DOI: 10.1002/qua.27110., ,

本研究以SARS-CoV-2主蛋白酶Mpro（PDB编号：6WQF）为靶点，采用AutoDock Vina 1.2.2软件开展半柔性对接（Semi-flexible docking）实验。本数据集包含两份xyz格式文件，其中存储了AutoDock Vina的对接打分（docking scores）结果。上述文件被用作基于TensorFlow、XGBoost及SchNetPack构建的机器学习（Machine Learning，ML）模型的输入与/或参照，以评估模型对对接打分的预测性能。第一份数据集初始包含60411个体内（in-vivo）标记的化合物，用于机器学习模型的训练。第二份数据集被命名为仅体外（in-vitro-only）数据集，初始包含175696个在直接结合实验中活性值≤10μM，或被认为具有该活性水平的化合物。上述两份数据集均于2021年12月10日从ZINC15数据库下载获取。由于体内标记数据集存在4个含有硅（Si）原子的化合物，仅体外数据集存在12个含硅原子的化合物，均被剔除出数据集。此外，mol2文件中未分配电荷的化合物也被排除（体内标记数据集剔除523个，仅体外数据集剔除1666个……）。分子对接计算及机器学习方法的详细说明参见参考文献[1]的计算细节章节。参考文献[1]：Lukas Bucinsky、Marián Gall、Ján Matúška、Michal Pitoňák、Marek Štekláč. 《对接打分预测机器学习技术的进展与批判性评估》，《International Journal of Quantum Chemistry》（2023），DOI: 10.1002/qua.27110.