NeurIPS

Rem3Di: Learning smooth, chiral 3D molecular descriptors from atomistic foundation models

Rem3Di：从原子基础模型学习平滑、手性3D分子描述符

Steffen Wedig, Felix Burton, Rokas Elijošius, Christoph Schran, Lars L. Schaaf

AI总结 Rem3Di是一种表征学习框架，利用原子基础模型潜在特征生成可转移分子描述符，用于性质预测和虚拟筛选。它能捕捉分子手性，在药物性质基准测试中表现出色，还能区分过渡金属配合物，为化学机器学习提供新途径。

Comments An earlier version of this work appeared at the NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations (NeurReps). Workshop version: https://openreview.net/forum?id=jOmZsvXoK5