English

Conformation Generation using Transformer Flows

Machine Learning 2025-02-18 v2 Quantitative Methods Machine Learning

Abstract

Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus central to molecular modeling. Recent advances in graph-based deep networks have accelerated conformation generation from hours to seconds. However, current network architectures do not scale well to large molecules. Here we present ConfFlow, a flow-based model for conformation generation based on transformer networks. In contrast with existing approaches, ConfFlow directly samples in the coordinate space without enforcing any explicit physical constraints. The generative procedure is highly interpretable and is akin to force field updates in molecular dynamics simulation. When applied to the generation of large molecule conformations, ConfFlow improve accuracy by up to 40%40\% relative to state-of-the-art learning-based methods. The source code is made available at https://github.com/IntelLabs/ConfFlow.

Keywords

Cite

@article{arxiv.2411.10817,
  title  = {Conformation Generation using Transformer Flows},
  author = {Sohil Atul Shah and Vladlen Koltun},
  journal= {arXiv preprint arXiv:2411.10817},
  year   = {2025}
}

Comments

This paper was completed in December 2022. Code available at https://github.com/IntelLabs/ConfFlow

R2 v1 2026-06-28T20:02:17.398Z