3D Molecule Generation from Rigid Motifs via SE(3) Flows

• URL: http://arxiv.org/abs/2601.16955v1
• Date: Fri, 23 Jan 2026 18:24:57 GMT
• Title: 3D Molecule Generation from Rigid Motifs via SE(3) Flows
• Authors: Roman Poletukhin, Marcel Kollovieh, Eike Eberhard, Stephan Günnemann,
• Abstract summary: Three-dimensional molecular structure generation is typically performed at the level of individual atoms.<n>We extend these fragmentation ideas to 3D, treating general molecules as sets of rigid-body motifs.<n>We observe comparable or superior results to state-of-the-art across benchmarks.
• Score: 46.02662888367749
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Three-dimensional molecular structure generation is typically performed at the level of individual atoms, yet molecular graph generation techniques often consider fragments as their structural units. Building on the advances in frame-based protein structure generation, we extend these fragmentation ideas to 3D, treating general molecules as sets of rigid-body motifs. Utilising this representation, we employ SE(3)-equivariant generative modelling for de novo 3D molecule generation from rigid motifs. In our evaluations, we observe comparable or superior results to state-of-the-art across benchmarks, surpassing it in atom stability on GEOM-Drugs, while yielding a 2x to 10x reduction in generation steps and offering 3.5x compression in molecular representations compared to the standard atom-based methods.

Related papers

• Applications of Modular Co-Design for De Novo 3D Molecule Generation [0.6903111965769448]
  We present Megalodon, a family of scalable transformer models.<n>These models are enhanced with basic equivariant layers and trained using a joint continuous and discrete denoising co-design objective.<n>We show that Megalodon achieves state-of-the-art results in 3D molecule generation, conditional structure generation, and structure energy benchmarks using diffusion and flow matching.
  arXiv  Detail & Related papers  (2025-05-23T21:41:56Z)
• 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)
• Autoregressive fragment-based diffusion for pocket-aware ligand design [0.0]
  AutoFragDiff is a fragment-based autoregressive diffusion model for generating 3D structures conditioned on target protein structures. We employ geometric vector perceptrons to predict atom types and spatial coordinates of new molecular fragments conditioned on molecular scaffolds and protein pockets.
  arXiv  Detail & Related papers  (2023-12-15T04:03:03Z)
• Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration [63.23362798102195]
  We propose D3FG, a functional-group-based diffusion model for pocket-specific molecule generation and elaboration. D3FG decomposes molecules into two categories of components: functional groups defined as rigid bodies and linkers as mass points. In the experiments, our method can generate molecules with more realistic 3D structures, competitive affinities toward the protein targets, and better drug properties.
  arXiv  Detail & Related papers  (2023-05-30T06:41:20Z)
• Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D [38.181969810488916]
  Existing methods usually generate molecules in atom resolution and ignore intrinsic local structures such as rings. Fragment-based molecule generation is a promising strategy, however, it is non-trivial to be adapted for 3D non-autoregressive generations. In this paper, we propose a coarse-to-fine strategy to tackle this problem, in which a Hierarchical Diffusion-based model (i.e.HierDiff) is proposed to preserve the validity of local segments without relying on autore modeling.
  arXiv  Detail & Related papers  (2023-05-05T13:08:38Z)
• MUDiff: Unified Diffusion for Complete Molecule Generation [104.7021929437504]
  We present a new model for generating a comprehensive representation of molecules, including atom features, 2D discrete molecule structures, and 3D continuous molecule coordinates. We propose a novel graph transformer architecture to denoise the diffusion process. Our model is a promising approach for designing stable and diverse molecules and can be applied to a wide range of tasks in molecular modeling.
  arXiv  Detail & Related papers  (2023-04-28T04:25:57Z)
• An Equivariant Generative Framework for Molecular Graph-Structure Co-Design [54.92529253182004]
  We present MolCode, a machine learning-based generative framework for underlineMolecular graph-structure underlineCo-design. In MolCode, 3D geometric information empowers the molecular 2D graph generation, which in turn helps guide the prediction of molecular 3D structure. Our investigation reveals that the 2D topology and 3D geometry contain intrinsically complementary information in molecule design.
  arXiv  Detail & Related papers  (2023-04-12T13:34:22Z)
• DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding [51.970607704953096]
  Previous works usually generate atoms in an auto-regressive way, where element types and 3D coordinates of atoms are generated one by one. In real-world molecular systems, the interactions among atoms in an entire molecule are global, leading to the energy function pair-coupled among atoms. In this work, a generative diffusion model for molecular 3D structures based on target proteins is established, at a full-atom level in a non-autoregressive way.
  arXiv  Detail & Related papers  (2022-11-21T07:02:15Z)
• Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning [68.8204255655161]
  We introduce a novel framework for scalable 3D design that uses a hierarchical agent to build molecules. In a variety of experiments, we show that our agent, guided only by energy considerations, can efficiently learn to produce molecules with over 100 atoms.
  arXiv  Detail & Related papers  (2022-02-01T18:54:24Z)
• Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models [0.0]
  We describe for the first time a deep generative model that can generate 3D structures conditioned on a three-dimensional molecular binding pocket. We show that valid and unique molecules can be readily sampled from the variational latent space defined by a reference seed' structure.
  arXiv  Detail & Related papers  (2020-10-16T16:27:47Z)

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.