mlsanityData to 7 Oct 2026

Ophiuchus: Scalable Modeling of Protein Structures through Hierarchical Coarse-graining SO(3)-Equivariant Autoencoders

arXiv 2310.02508 ↗First posted 4 Oct 2023cs.LGcited by 3

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Three-dimensional native states of natural proteins display recurring and hierarchical patterns. Yet, traditional graph-based modeling of protein structures is often limited to operate within a single fine-grained resolution, and lacks hourglass neural architectures to learn those high-level building blocks. We narrow this gap by introducing Ophiuchus, an SO(3)-equivariant coarse-graining model that efficiently operates on all-atom protein structures. Our model departs from current approaches that employ graph modeling, instead focusing on local convolutional coarsening to model sequence-motif interactions with efficient time complexity in protein length. We measure the reconstruction capabilities of Ophiuchus across different compression rates, and compare it to existing models. We examine the learned latent space and demonstrate its utility through conformational interpolation. Finally, we leverage denoising diffusion probabilistic models (DDPM) in the latent space to efficiently sample protein structures. Our experiments demonstrate Ophiuchus to be a scalable basis for efficient protein modeling and generation.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 31 of its 69 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

31 of 69 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023A Latent Diffusion Model for Protein Structure Generation6 May
  2. 2023SE(3) diffusion model with application to protein backbone generation5 Feb
  3. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem8 Jun
  4. 2022Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models26 May

Other references · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  5. 2021E(n) Equivariant Graph Neural Networkscited by 951
  6. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  7. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  8. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  9. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  10. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  11. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 308
  12. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
15 more
  1. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  2. 2022Protein Representation Learning by Geometric Structure Pretrainingcited by 161
  3. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 73
  4. 2017Time-lagged autoencoders: Deep learning of slow collective variables for molecular kineticscited by 64
  5. 2023Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Cloudscited by 53
  6. 2020Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Propertiescited by 51
  7. 2017DeepSF: deep convolutional neural network for mapping protein sequences to foldscited by 46
  8. 2018DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequencescited by 45
  9. 2023Ankh: Optimized Protein Language Model Unlocks General-Purpose Modellingcited by 44
  10. 2018Coarse-Graining Auto-Encoders for Molecular Dynamicscited by 30
  11. 2022Generative Coarse-Graining of Molecular Conformationscited by 21
  12. 2023Chemically Transferable Generative Backmapping of Coarse-Grained Proteinscited by 14
  13. 2021Auto-Encoding Molecular Conformationscited by 8
  14. 2020SidechainNet: An All-Atom Protein Structure Dataset for Machine Learningcited by 6
  15. 2022TERMinator: A Neural Framework for Structure-Based Protein Design using Tertiary Repeating Motifscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2cited by 33
  2. 2024EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolantscited by 15
  3. 2025Accelerating Protein Molecular Dynamics Simulation with DeepJumpcited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2025ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
  2. 2023Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure
  3. 2022Protein Sequence and Structure Co-Design with Equivariant Translation
  4. 2024Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation
  5. 2024Bio2Token: All-atom tokenization of any biomolecular structure with Mamba
  6. 2023Graph Denoising Diffusion for Inverse Protein Folding
  7. 2022Protein structure generation via folding diffusion
  8. 2025ConfRover: Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression