Steering 3D Molecule Generation in Data-Sparse Regions via Distributional Physical Priors
Lists
Only you see this
Abstract
Can we train a 3D molecule generator using data from dense regions to generate samples in sparse regions? This challenge can be framed as an out-of-distribution (OOD) generation problem. Existing works on OOD generation primarily focus on property shifts. However, the distribution shifts may come from structural variations in molecules, such as certain types of scaffolds, dubbed as physical priors. This work introduces a novel and principled diffusion-based generative framework, termed _GODD_, which enables training a generator on data-abundant distributions to generalize to data-scarce distributions under structure shifts. Specifically, we propose utilizing a designated equivariant asymmetric autoencoder to capture distributional physical priors. The asymmetric module allows generalization to unseen, out-of-distribution structural variations. As these captured physical priors represent distinct distributions, they can steer the generation of samples that are not in dense regions. We demonstrate that with these encoded structural-grained distributional physical priors, _GODD_ does not need to train with any molecules from the sparse regions. We conduct extensive experiments across various out-of-distribution molecule generation tasks using benchmark datasets. Compared to alternative baselines, our approach shows a significant improvement of up to 65.6\% in success rate, defined based on molecular validity, uniqueness, and novelty. Additionally, we show that our generative framework, steered by physical priors, can be readily adapted to canonical fragment-based drug design tasks, exhibiting promising performance.
BibTeX
@misc{hong2025steering,
author = {Haokai Hong and Wanyu Lin and Ming Yang and KC Tan},
title = {{Steering 3D Molecule Generation in Data-Sparse Regions via Distributional Physical Priors}},
year = {2025},
url = {https://openreview.net/forum?id=an3kPpce6b},
howpublished = {OpenReview},
note = {Submitted to ICLR 2025},
}Loading related content...