Predicting quantum chemical properties is a fundamental challenge for computational chemistry. While the development of graph neural networks has advanced molecular representation learning and property prediction, their performance could be further enhanced by incorporating three-dimensional (3D) structural geometry into two-dimensional (2D) molecular graph representation. In this study, we introduce the PointGAT model for quantum molecular property prediction, which integrates 3D molecular coordinates with graph-attention modeling. Comparison with other current models in molecular prediction tasks showed that PointGAT could provide higher predictive accuracy in various benchmark data sets from MoleculeNet, including ESOL, FreeSolv, Lipop, HIV, and 6 out of 12 tasks of the QM9 data set. To further examine PointGAT prediction of quantum mechanical (QM) energies, we constructed a C10 data set comprising 11,841 charged and chiral carbocation intermediates with QM energies calculated at the DM21/6-31G*//B3LYP/6-31G* levels. Notably, PointGAT achieved an R² value of 0.950 and an MAE of 1.616 kcal/mol, outperforming even the best-performing graph neural network model with a reduction of 0.216 kcal/mol in MAE and an improvement of 0.050 in R². Additional ablation studies indicated that incorporating molecular geometry into the model resulted in markedly higher predictive accuracy, reducing the MAE value from 1.802 to 1.616 kcal/mol. Moreover, visualization of PointGAT atomic attention weights suggested its predictions were interpretable. Findings in this study support the application of PointGAT as a powerful and versatile tool for quantum chemical property prediction that can facilitate high-accuracy modeling for fundamental exploration of chemical space as well as drug design and molecular engineering.

中文翻译：

---

PointGAT：集成图注意力和 3D 几何的量子化学性质预测模型


预测量子化学性质是计算化学的一个基本挑战。虽然图神经网络的发展具有先进的分子表示学习和属性预测，但通过将三维（3D）结构几何合并到二维（2D）分子图表示中可以进一步增强其性能。在本研究中，我们引入了用于量子分子特性预测的 PointGAT 模型，该模型将 3D 分子坐标与图注意力建模相结合。与当前分子预测任务中的其他模型进行比较表明，PointGAT 可以在 MoleculeNet 的各种基准数据集（包括 ESOL、FreeSolv、Lipop、HIV 和 QM9 数据集的 12 个任务中的 6 个）中提供更高的预测准确性。为了进一步检验 PointGAT 对量子力学 (QM) 能量的预测，我们构建了一个 C10 数据集，其中包含 11,841 个带电和手性碳正离子中间体，其 QM 能量在 DM21/6-31G*//B3LYP/6-31G* 能级计算。值得注意的是，PointGAT 的 R ² 值为 0.950，MAE 为 1.616 kcal/mol，甚至超越了性能最好的图神经网络模型，MAE 降低了 0.216 kcal/mol，提高了 0.050在 R ² 中。其他消融研究表明，将分子几何结构纳入模型可显着提高预测精度，将 MAE 值从 1.802 kcal/mol 降低至 1.616 kcal/mol。此外，PointGAT 原子注意力权重的可视化表明其预测是可以解释的。 这项研究的结果支持 PointGAT 作为一种强大且多功能的量子化学性质预测工具的应用，可以促进化学空间基础探索以及药物设计和分子工程的高精度建模。