An Evaluation of Unconditional 3D Molecular Generation Methods
Abstract
Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in *de novo* drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has an 87\% success rate in generating valid, unique, and novel molecules without post-processing and 92.4\% with post-processing.
Cite
Text
Buttenschoen et al. "An Evaluation of Unconditional 3D Molecular Generation Methods." ICLR 2025 Workshops: GEM, 2025.Markdown
[Buttenschoen et al. "An Evaluation of Unconditional 3D Molecular Generation Methods." ICLR 2025 Workshops: GEM, 2025.](https://mlanthology.org/iclrw/2025/buttenschoen2025iclrw-evaluation/)BibTeX
@inproceedings{buttenschoen2025iclrw-evaluation,
title = {{An Evaluation of Unconditional 3D Molecular Generation Methods}},
author = {Buttenschoen, Martin and Ziv, Yael and Morris, Garrett M and Deane, Charlotte},
booktitle = {ICLR 2025 Workshops: GEM},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/buttenschoen2025iclrw-evaluation/}
}