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

TL;DR

This paper introduces SO(3)-Averaged Flow training and reflow techniques to significantly accelerate the training and inference of flow-based models for molecular conformer generation, achieving high quality with fewer computational resources.

Contribution

It proposes novel SO(3)-Averaged Flow training and reflow methods that improve training speed and enable rapid inference in molecular conformer generation.

Findings

SO(3)-Averaged Flow converges faster and yields better conformer quality.

Reflow enables one-step conformer generation with high accuracy.

The methods achieve state-of-the-art results with reduced computational cost.

Abstract

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.