Sampling 3D Molecular Conformers with Diffusion Transformers

• URL: http://arxiv.org/abs/2506.15378v1
• Date: Wed, 18 Jun 2025 11:47:59 GMT
• Title: Sampling 3D Molecular Conformers with Diffusion Transformers
• Authors: J. Thorben Frank, Winfried Ripken, Gregor Lied, Klaus-Robert Müller, Oliver T. Unke, Stefan Chmiela,
• Abstract summary: Diffusion Transformers (DiTs) have demonstrated strong performance in generative modeling.<n>Applying DiTs to molecules introduces novel challenges, such as integrating discrete molecular graph information with continuous 3D geometry.<n>We propose DiTMC, a framework that adapts DiTs to address these challenges through a modular architecture.
• Score: 13.536503487456622
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 available at https://github.com/ML4MolSim/dit_mc.

Related papers

• Aligned Manifold Property and Topology Point Clouds for Learning Molecular Properties [55.2480439325792]
  This work introduces AMPTCR, a molecular surface representation that combines local quantum-derived scalar fields and custom topological descriptors within an aligned point cloud format.<n>For molecular weight, results confirm that AMPTCR encodes physically meaningful data, with a validation R2 of 0.87.<n>In the bacterial inhibition task, AMPTCR enables both classification and direct regression of E. coli inhibition values.
  arXiv  Detail & Related papers  (2025-07-22T04:35:50Z)
• TABASCO: A Fast, Simplified Model for Molecular Generation with Improved Physical Quality [15.030633864521562]
  TABASCO is a non-equivariant transformer model for 3D molecular generation.<n>It treats atoms in a molecule as sequences and reconstructs bonds deterministically after generation.<n>On the GEOM-Drugs benchmark TABASCO achieves state-of-the-art PoseBusters validity and delivers inference roughly 10x faster than the strongest baseline.
  arXiv  Detail & Related papers  (2025-07-01T16:01:58Z)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [77.26556208024633]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates [28.452581855002855]
  Mol-StrucTok is a novel method for tokenizing 3D molecular structures.<n>We design a line notation for 3D molecules by extracting local atomic coordinates in a spherical coordinate system.<n>We employ a Vector Quantized Variational Autoencoder (VQ-VAE) to tokenize these coordinates, treating them as generation descriptors.
  arXiv  Detail & Related papers  (2024-12-02T14:50:44Z)
• Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation [18.394348744611662]
  We introduce a novel generative model termed Equivariant Blurring Diffusion (EBD) EBD defines a forward process that moves towards the fragment-level coarse-grained structure by blurring the fine atomic details of conformers. We demonstrate the effectiveness of EBD by geometric and chemical comparison to state-of-the-art denoising diffusion models on a benchmark of drug-like molecules.
  arXiv  Detail & Related papers  (2024-10-26T19:17:31Z)
• Geometric Trajectory Diffusion Models [58.853975433383326]
  Generative models have shown great promise in generating 3D geometric systems. Existing approaches only operate on static structures, neglecting the fact that physical systems are always dynamic in nature. We propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories.
  arXiv  Detail & Related papers  (2024-10-16T20:36:41Z)
• Learning Modulated Transformation in GANs [69.95217723100413]
  We equip the generator in generative adversarial networks (GANs) with a plug-and-play module, termed as modulated transformation module (MTM) MTM predicts spatial offsets under the control of latent codes, based on which the convolution operation can be applied at variable locations. It is noteworthy that towards human generation on the challenging TaiChi dataset, we improve the FID of StyleGAN3 from 21.36 to 13.60, demonstrating the efficacy of learning modulated geometry transformation.
  arXiv  Detail & Related papers  (2023-08-29T17:51:22Z)
• CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer Generation [3.31521245002301]
  We introduce CoarsenConf, which integrates molecular graphs based on torsional angles into an SE(3)-equivariant hierarchical variational autoencoder. Through equivariant coarse-graining, we aggregate the fine-grained atomic coordinates of subgraphs connected via rotatable bonds, creating a variable-length coarse-grained latent representation. Our model uses a novel aggregated attention mechanism to restore fine-grained coordinates from the coarse-grained latent representation, enabling efficient generation of accurate conformers.
  arXiv  Detail & Related papers  (2023-06-26T17:02:54Z)
• FAENet: Frame Averaging Equivariant GNN for Materials Modeling [123.19473575281357]
  We introduce a flexible framework relying on frameaveraging (SFA) to make any model E(3)-equivariant or invariant through data transformations. We prove the validity of our method theoretically and empirically demonstrate its superior accuracy and computational scalability in materials modeling.
  arXiv  Detail & Related papers  (2023-04-28T21:48:31Z)
• 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction [9.67574543046801]
  The inclusion of 3D structures during targeted drug design shows superior performance to other target-free models. We develop a 3D equivariant diffusion model to solve the above challenges. Our model could generate molecules with more realistic 3D structures and better affinities towards the protein targets, and improve binding affinity ranking and prediction without retraining.
  arXiv  Detail & Related papers  (2023-03-06T23:01:43Z)
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles [60.12186997181117]
  Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements. We propose GeoMol, an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate 3D conformers.
  arXiv  Detail & Related papers  (2021-06-08T14:17:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.