论文标题
边缘方向不变的图形神经网络用于分子偶极矩预测
Edge Direction-invariant Graph Neural Networks for Molecular Dipole Moments Prediction
论文作者
论文摘要
偶极矩是指示分子极性的物理量，并通过反映成分原子的电性能和分子的几何特性来确定。大多数用于表示传统图神经网络方法中的图形表示的嵌入方式将分子视为拓扑图，从而为识别几何信息的目标造成了重大障碍。与现有的嵌入涉及均值的嵌入不同，该嵌入适当地处理分子的3D结构不同，我们提出的嵌入直接表达了偶极矩的局部贡献的物理意义。我们表明，即使对于具有扩展几何形状的分子并捕获更多的原子间相互作用信息，开发的模型甚至可以合理地工作，从而显着改善了预测结果，其准确性与AB-Initio计算相当。
The dipole moment is a physical quantity indicating the polarity of a molecule and is determined by reflecting the electrical properties of constituent atoms and the geometric properties of the molecule. Most embeddings used to represent graph representations in traditional graph neural network methodologies treat molecules as topological graphs, creating a significant barrier to the goal of recognizing geometric information. Unlike existing embeddings dealing with equivariance, which have been proposed to handle the 3D structure of molecules properly, our proposed embeddings directly express the physical implications of the local contribution of dipole moments. We show that the developed model works reasonably even for molecules with extended geometries and captures more interatomic interaction information, significantly improving the prediction results with accuracy comparable to ab-initio calculations.
