3D Molecule Generation from Rigid Motifs via $\mathrm{SE}(3)$ Flows

Roman Poletukhin, Marcel Kollovieh, Eike Eberhard, Stephan Günnemann

Keywords: Generative Modelling, Computational Biology, Computational Chemistry, AI4Science, Flow Matching, Molecule Generation

TL;DR: Generating 3D molecules as sets of rigid-body motifs instead of individual atoms, utilising multimodal flow matching to achieve faster sampling and improved stability.

Abstract: Three-dimensional molecular structure generation is typically performed at the level of individual atoms, yet molecular graph generation techniques often consider *fragments* as their structural units. Building on the advances in *frame-based* protein structure generation, we extend these fragmentation ideas to 3D, treating general molecules as sets of *rigid-body motifs*. Utilising this representation, we employ $\mathrm{SE}(3)$-equivariant generative modelling for *de novo* 3D molecule generation from rigid motifs. In our evaluations, we observe comparable or superior results to state-of-the-art across benchmarks, surpassing it in atom stability on GEOM-Drugs, while yielding a $2\times$ to $10\times$ reduction in generation steps and offering $3.5\times$ compression in molecular representations compared to the standard atom-based methods.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 117