3D Molecule Generation from Rigid Motifs via SE(3) Flows
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915750969606144 |
|---|---|
| author | Poletukhin, Roman Kollovieh, Marcel Eberhard, Eike Günnemann, Stephan |
| author_facet | Poletukhin, Roman Kollovieh, Marcel Eberhard, Eike Günnemann, Stephan |
| contents | 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 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 2x to 10x reduction in generation steps and offering 3.5x compression in molecular representations compared to the standard atom-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16955 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | 3D Molecule Generation from Rigid Motifs via SE(3) Flows Poletukhin, Roman Kollovieh, Marcel Eberhard, Eike Günnemann, Stephan Machine Learning 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 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 2x to 10x reduction in generation steps and offering 3.5x compression in molecular representations compared to the standard atom-based methods. |
| title | 3D Molecule Generation from Rigid Motifs via SE(3) Flows |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.16955 |