发表机构
Shanghai Jiao Tong University; Shanghai Innovation Institute; East China Normal University（上海交通大学; 上海创新研究院; 华东师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PhysECD是一种物理约束的E(3)等变框架，可从分子三维结构直接预测ECD谱，在CMCDS数据集上的皮尔逊相关系数优于现有方法，可用于实时确定手性分子绝对构型。
AI 中文摘要
电子圆二色谱（ECD）是确定手性分子绝对构型的主要实验探针，但解读测量得到的ECD谱需要耗时密度泛函理论（TDDFT）计算，每一个分子的计算都需要数小时，且必须针对每一个候选立体异构体和构象重复计算。本文提出PhysECD，这是一种物理约束、宇称感知的E(3)等变框架，可绕过计算成本高昂的TDDFT，直接从单个构象体的三维结构预测ECD谱。PhysECD没有将谱作为不透明序列进行回归，而是预测生成ECD谱的物理量：每个态的激发能以及电和磁跃迁偶极矩。这些物理量决定了旋转强度R——即两个偶极矩的点积，是一种在镜像反射下符号反转的赝标量，且通过从基础物理推导而来的可微高斯展宽公式生成最终谱。等变特征的宇称结构保证了正确的手性光学对称性：对分子进行镜像反射会使预测的ECD谱恰好取反。在CMCDS数据集上，PhysECD实现了每分子谱的皮尔逊相关系数均值为0.642、中位数为0.822，显著优于现有的学习型预测器，同时保持了物理可解释性。对多种骨干网络的实验进一步表明，该框架与骨干网络无关，为实时确定绝对构型铺平了道路。
英文摘要
The electronic circular dichroism (ECD) spectrum is a primary experimental probe for assigning the absolute configuration of chiral molecules, yet interpreting a measured spectrum requires time-dependent density functional theory (TDDFT) calculations that can cost hours per molecule and must be repeated for every candidate stereoisomer and conformation. We present PhysECD, a physics-constrained, parity-aware E(3)-equivariant framework that bypasses computationally expensive TDDFT and predicts ECD spectra directly from the 3D structure of an individual conformer. Instead of regressing the spectrum as an opaque sequence, PhysECD predicts the physical quantities that generate it: per-state excitation energies and electric and magnetic transition dipoles. These quantities determine the rotatory strength R -- the dot product of the two dipoles, a pseudoscalar that reverses sign under mirror reflection -- and yield the final spectrum through a differentiable Gaussian-broadening formula derived from the underlying physics. The parity structure of the equivariant features guarantees the correct chiroptical symmetry: reflecting a molecule exactly negates the predicted spectrum. On the CMCDS dataset, PhysECD attains a per-molecule spectral Pearson correlation of 0.642 (mean) / 0.822 (median), substantially exceeding prior learned predictors while remaining physically interpretable. Experiments across multiple backbones further show that the framework is backbone-agnostic, paving the way for real-time assignment of absolute configuration.
