Sampling 3D Molecular Conformers with Diffusion Transformers

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Frank, J. Thorben, Ripken, Winfried, Lied, Gregor, Müller, Klaus-Robert, Unke, Oliver T., Chmiela, Stefan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914148874452992
author Frank, J. Thorben
Ripken, Winfried
Lied, Gregor
Müller, Klaus-Robert
Unke, Oliver T.
Chmiela, Stefan
author_facet Frank, J. Thorben
Ripken, Winfried
Lied, Gregor
Müller, Klaus-Robert
Unke, Oliver T.
Chmiela, Stefan
contents Diffusion Transformers (DiTs) have demonstrated strong performance in generative modeling, particularly in image synthesis, making them a compelling choice for molecular conformer generation. However, applying DiTs to molecules introduces novel challenges, such as integrating discrete molecular graph information with continuous 3D geometry, handling Euclidean symmetries, and designing conditioning mechanisms that generalize across molecules of varying sizes and structures. We propose DiTMC, a framework that adapts DiTs to address these challenges through a modular architecture that separates the processing of 3D coordinates from conditioning on atomic connectivity. To this end, we introduce two complementary graph-based conditioning strategies that integrate seamlessly with the DiT architecture. These are combined with different attention mechanisms, including both standard non-equivariant and SO(3)-equivariant formulations, enabling flexible control over the trade-off between between accuracy and computational efficiency. Experiments on standard conformer generation benchmarks (GEOM-QM9, -DRUGS, -XL) demonstrate that DiTMC achieves state-of-the-art precision and physical validity. Our results highlight how architectural choices and symmetry priors affect sample quality and efficiency, suggesting promising directions for large-scale generative modeling of molecular structures. Code is available at https://github.com/ML4MolSim/dit_mc.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15378
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sampling 3D Molecular Conformers with Diffusion Transformers
Frank, J. Thorben
Ripken, Winfried
Lied, Gregor
Müller, Klaus-Robert
Unke, Oliver T.
Chmiela, Stefan
Machine Learning
Diffusion Transformers (DiTs) have demonstrated strong performance in generative modeling, particularly in image synthesis, making them a compelling choice for molecular conformer generation. However, applying DiTs to molecules introduces novel challenges, such as integrating discrete molecular graph information with continuous 3D geometry, handling Euclidean symmetries, and designing conditioning mechanisms that generalize across molecules of varying sizes and structures. We propose DiTMC, a framework that adapts DiTs to address these challenges through a modular architecture that separates the processing of 3D coordinates from conditioning on atomic connectivity. To this end, we introduce two complementary graph-based conditioning strategies that integrate seamlessly with the DiT architecture. These are combined with different attention mechanisms, including both standard non-equivariant and SO(3)-equivariant formulations, enabling flexible control over the trade-off between between accuracy and computational efficiency. Experiments on standard conformer generation benchmarks (GEOM-QM9, -DRUGS, -XL) demonstrate that DiTMC achieves state-of-the-art precision and physical validity. Our results highlight how architectural choices and symmetry priors affect sample quality and efficiency, suggesting promising directions for large-scale generative modeling of molecular structures. Code is available at https://github.com/ML4MolSim/dit_mc.
title Sampling 3D Molecular Conformers with Diffusion Transformers
topic Machine Learning
url https://arxiv.org/abs/2506.15378