Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
This addresses the challenge of limited labeled data for drug and material discovery by enabling better pretraining on 3D molecular structures, though it appears incremental as it builds on existing pretraining methods.
The paper tackled the problem of pretraining molecular representations on 3D geometric structures by proposing GeoSSL-DDM, a framework that uses SE(3)-invariant denoising of pairwise atomic distances, and achieved effectiveness and robustness in experiments.
Molecular representation pretraining is critical in various applications for drug and material discovery due to the limited number of labeled molecules, and most existing work focuses on pretraining on 2D molecular graphs. However, the power of pretraining on 3D geometric structures has been less explored. This is owing to the difficulty of finding a sufficient proxy task that can empower the pretraining to effectively extract essential features from the geometric structures. Motivated by the dynamic nature of 3D molecules, where the continuous motion of a molecule in the 3D Euclidean space forms a smooth potential energy surface, we propose GeoSSL, a 3D coordinate denoising pretraining framework to model such an energy landscape. Further by leveraging an SE(3)-invariant score matching method, we propose GeoSSL-DDM in which the coordinate denoising proxy task is effectively boiled down to denoising the pairwise atomic distances in a molecule. Our comprehensive experiments confirm the effectiveness and robustness of our proposed method.