Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Zhonglin, Geiger, Mario, Costa, Allan dos Santos, Reidenbach, Danny, Kreis, Karsten, Geffner, Tomas, Pellegrini, Franco, Zhou, Guoqing, Kucukbenli, Emine
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909688204886016
author Cao, Zhonglin
Geiger, Mario
Costa, Allan dos Santos
Reidenbach, Danny
Kreis, Karsten
Geffner, Tomas
Pellegrini, Franco
Zhou, Guoqing
Kucukbenli, Emine
author_facet Cao, Zhonglin
Geiger, Mario
Costa, Allan dos Santos
Reidenbach, Danny
Kreis, Karsten
Geffner, Tomas
Pellegrini, Franco
Zhou, Guoqing
Kucukbenli, Emine
contents Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we build upon flow-matching and propose two mechanisms for accelerating training and inference of generative models for 3D molecular conformer generation. For fast training, we introduce the SO(3)-Averaged Flow training objective, which leads to faster convergence to better generation quality compared to conditional optimal transport flow or Kabsch-aligned flow. We demonstrate that models trained using SO(3)-Averaged Flow can reach state-of-the-art conformer generation quality. For fast inference, we show that the reflow and distillation methods of flow-based models enable few-steps or even one-step molecular conformer generation with high quality. The training techniques proposed in this work show a path towards highly efficient molecular conformer generation with flow-based models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09785
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
Cao, Zhonglin
Geiger, Mario
Costa, Allan dos Santos
Reidenbach, Danny
Kreis, Karsten
Geffner, Tomas
Pellegrini, Franco
Zhou, Guoqing
Kucukbenli, Emine
Machine Learning
Chemical Physics
Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we build upon flow-matching and propose two mechanisms for accelerating training and inference of generative models for 3D molecular conformer generation. For fast training, we introduce the SO(3)-Averaged Flow training objective, which leads to faster convergence to better generation quality compared to conditional optimal transport flow or Kabsch-aligned flow. We demonstrate that models trained using SO(3)-Averaged Flow can reach state-of-the-art conformer generation quality. For fast inference, we show that the reflow and distillation methods of flow-based models enable few-steps or even one-step molecular conformer generation with high quality. The training techniques proposed in this work show a path towards highly efficient molecular conformer generation with flow-based models.
title Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
topic Machine Learning
Chemical Physics
url https://arxiv.org/abs/2507.09785