Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
This work addresses computational bottlenecks in molecular conformer generation for drug discovery and computational chemistry, offering incremental improvements to existing flow-based methods.
The paper tackled the problem of slow and resource-intensive training and sampling in molecular conformer generation by proposing SO(3)-Averaged Flow for faster training and reflow/distillation for fast inference, achieving state-of-the-art generation quality with efficient few-step or one-step generation.
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.