Quantum-mechanical datasets for "Assessing the performance of quantum-mechanical descriptors in physicochemical and biological property prediction"

Here, you can access the quantum-mechanical datasets from TDCommons-LD50 and the MoleculeNet benchmarks that we used to validate the “QUantum Electronic Descriptor” (QUED) framework. ABSTRACT Machine learning (ML) approaches have drastically advanced the exploration of structure-property and property-property relationships in computer-aided drug discovery. A central challenge in this field is the identification of molecular descriptors that can effectively capture both geometric- and electronic structure-derived features, enabling the development of reliable and interpretable predictive models. While numerous descriptors focusing solely on structural characteristics have been recently proposed, improvements in model accuracy often come at the cost of increased computational demands, thereby restricting their practical applicability. To address this challenge, we introduce the “QUantum Electronic Descriptor” (QUED) framework, which integrates both structural and electronic data of molecules to develop ML regression models for property prediction. In doing so, a quantum-mechanical (QM) descriptor is derived from molecular and atomic properties computed using the semi-empirical density functional tight-binding (DFTB) method, which allows for efficient modelling of both small and large drug-like molecules. This descriptor is combined with inexpensive geometric descriptors--capturing two-body and three-body interatomic interactions--to form comprehensive molecular representations used to train Kernel Ridge Regression and XGBoost models. As a proof of concept, we validate QUED using the QM7-X dataset, which comprises equilibrium and non-equilibrium conformations of small drug-like molecules, demonstrating that incorporating electronic structure data notably enhances the accuracy of ML models for predicting physicochemical properties. For biological endpoints, we find that QM properties provide some predictive value for toxicity and lipophilicity prediction, as assessed using the TDCommons-LD50 and the MoleculeNet benchmark datasets. Moreover, a SHapley Additive exPlanations (SHAP) analysis of the toxicity and lipophilicity predictive models reveals that molecular orbital energies and DFTB energy components are among the most influential electronic features. Hence, our work underscores the importance of incorporating QM descriptors to enhance both the accuracy and interpretability of ML models for predicting multiple properties relevant to pharmaceutical and biological applications. PREPRINT https://chemrxiv.org/engage/chemrxiv/article-details/68c61dd73e708a7649eb1250 CODE and MODELS: The main code, the trained regression models, and additional scripts used in this work are available at https://github.com/lmedranos/QUED.您可在此获取本研究用于验证量子电子描述符（QUantum Electronic Descriptor，QUED）框架的、源自TDCommons-LD50与MoleculeNet基准测试集的量子力学数据集。 摘要 机器学习（Machine Learning，ML）方法极大推动了计算机辅助药物发现领域中结构-性质与性质-性质关联关系的探索研究。该领域的核心挑战之一，在于如何筛选出能够有效捕捉几何结构与电子结构衍生特征的分子描述符，从而构建出可靠且可解释的预测模型。尽管近期已有诸多仅聚焦于结构特征的描述符被提出，但模型精度的提升往往伴随着计算资源需求的攀升，这限制了其实际应用价值。为此，我们提出了量子电子描述符（QUED）框架，该框架整合分子的结构与电子数据，用于构建用于性质预测的机器学习回归模型。据此，我们基于半经验密度泛函紧束缚（Density Functional Tight-Binding，DFTB）方法计算得到的分子与原子属性，构建出量子力学（Quantum-Mechanical，QM）描述符，该描述符可高效对小型及大型类药分子进行建模。将该描述符与可捕捉两体及三体原子间相互作用的轻量化几何描述符相结合，可构建出全面的分子表征，用于训练核岭回归（Kernel Ridge Regression）与极限梯度提升树（XGBoost）模型。作为概念验证，我们使用QM7-X数据集对QUED进行验证：该数据集包含小型类药分子的平衡与非平衡构象，实验结果表明，引入电子结构数据可显著提升机器学习模型预测理化性质的精度。针对生物学终点指标，我们通过TDCommons-LD50与MoleculeNet基准数据集开展评估，结果发现量子力学属性对毒性与脂溶性预测具备一定的预测价值。此外，我们对毒性与脂溶性预测模型开展SHAP加性解释（SHapley Additive exPlanations，SHAP）分析，结果显示分子轨道能量与DFTB能量分量是影响力最强的电子特征之一。综上，本研究证实了引入量子力学描述符的重要性：其可同时提升机器学习模型在预测与医药及生物应用相关的多种性质时的精度与可解释性。 预印本 https://chemrxiv.org/engage/chemrxiv/article-details/68c61dd73e708a7649eb1250 代码与模型 本研究使用的核心代码、已训练的回归模型及辅助脚本均已开源至：https://github.com/lmedranos/QUED。