E(3)-equivariant models cannot learn chirality: Field-based molecular generation
Alexandru Dumitrescu, Dani Korpela, Markus Heinonen, Yogesh Verma, Valerii Iakovlev, Vikas Garg, Harri Lähdesmäki
Abstract
Obtaining the desired effect of drugs is highly dependent on their molecular geometries. Thus, the current prevailing paradigm focuses on 3D point-cloud atom representations, utilizing graph neural network (GNN) parametrizations, with rotational symmetries baked in via E(3) invariant layers. We prove that such models must necessarily disregard chirality, a geometric property of the molecules that cannot be superimposed on their mirror image by rotation and translation. Chirality plays a key role in determining drug safety and potency. To address this glaring issue, we introduce a novel field-based representation, proposing reference rotations that replace rotational symmetry constraints. The proposed model captures all molecular geometries including chirality, while still achieving highly competitive performance with E(3)-based methods across standard benchmarking metrics.
BibTeX
@inproceedings{
dumitrescu2025eequivariant,
title={E(3)-equivariant models cannot learn chirality: Field-based molecular generation},
author={Alexandru Dumitrescu and Dani Korpela and Markus Heinonen and Yogesh Verma and Valerii Iakovlev and Vikas Garg and Harri L{\"a}hdesm{\"a}ki},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=mXHTifc1Fn}
}