mlsanityData to 13 Oct 2026

A Latent Diffusion Model for Protein Structure Generation

arXiv 2305.04120 ↗First posted 6 May 2023q-bio.BM cs.AI cs.LGcited by 28

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

Abstract (arXiv)

Proteins are complex biomolecules that perform a variety of crucial functions within living organisms. Designing and generating novel proteins can pave the way for many future synthetic biology applications, including drug discovery. However, it remains a challenging computational task due to the large modeling space of protein structures. In this study, we propose a latent diffusion model that can reduce the complexity of protein modeling while flexibly capturing the distribution of natural protein structures in a condensed latent space. Specifically, we propose an equivariant protein autoencoder that embeds proteins into a latent space and then uses an equivariant diffusion model to learn the distribution of the latent protein representations. Experimental results demonstrate that our method can effectively generate novel protein backbone structures with high designability and efficiency. The code will be made publicly available at https://github.com/divelab/AIRS/tree/main/OpenProt/LatentDiff

Key facts. Cited by 28 papers in the map (data through 13 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 31 of its 59 references that are in the map. First posted on arXiv 6 May 2023.

Builds on

31 of 59 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023SE(3) diffusion model with application to protein backbone generation5 Feb
  2. 2022Structure-based Drug Design with Equivariant Diffusion Models24 Oct
  3. 2022Protein structure generation via folding diffusion30 Sep
  4. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem8 Jun
  5. 2022Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models26 May
  6. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar
  7. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,777
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  5. 2021E(n) Equivariant Graph Neural Networkscited by 957
  6. 2020Learning to Simulate Complex Physics with Graph Networkscited by 873
  7. 2019On the Convergence of Adam and Beyondcited by 837
  8. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  9. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 178
  10. 2021Spherical Message Passing for 3D Graph Networkscited by 167
  11. 2022ProGen2: Exploring the Boundaries of Protein Language Modelscited by 158
  12. 2020ProGen: Language Modeling for Protein Generationcited by 128
12 more
  1. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  2. 2022Periodic Graph Transformers for Crystal Material Property Predictioncited by 87
  3. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  4. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  5. 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
  6. 2023Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Cloudscited by 54
  7. 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46
  8. 2021Protein sequence design with deep generative modelscited by 35
  9. 2022Protein Sequence and Structure Co-Design with Equivariant Translationcited by 31
  10. 2021Learning ground states of quantum Hamiltonians with graph networkscited by 12
  11. 2021Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networkscited by 10
  12. 2022Lattice Convolutional Networks for Learning Ground States of Quantum Many-Body Systemscited by 7

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 4; 2024: 11; 2025: 9; 2026: 4.

28 papers.

Sort:

By area:

  1. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 68
  2. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  3. 2024Complete and Efficient Graph Transformers for Crystal Material Property Predictioncited by 34
  4. 2024Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2cited by 34
  5. 2024A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generationcited by 29
  6. 2025La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matchingcited by 28
  7. 2024Equivariance via Minimal Frame Averaging for More Symmetries and Efficiencycited by 18
  8. 2023De novo protein design using geometric vector field networkscited by 14
  9. 2024Diffusion on language model encodings for protein sequence generationcited by 11
  10. 2023Towards Joint Sequence-Structure Generation of Nucleic Acid and Protein Complexes with SE(3)-Discrete Diffusioncited by 9
  11. 2024Energy based diffusion generator for efficient sampling of Boltzmann distributionscited by 7
  12. 2024A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Predictioncited by 7
16 more
  1. 2024Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Modelscited by 6
  2. 2025ProxelGen: Generating Proteins as 3D Densitiescited by 4
  3. 2023Ophiuchus: Scalable Modeling of Protein Structures through Hierarchical Coarse-graining SO(3)-Equivariant Autoencoderscited by 3
  4. 2025ProteinAE: Protein Diffusion Autoencoders for Structure Encodingcited by 3
  5. 2024Diffusion-based Graph Generative Methodscited by 2
  6. 2024Constraint Decoupled Latent Diffusion for Protein Backmappingcited by 2
  7. 2025Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddingscited by 2
  8. 2025Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecastingcited by 2
  9. 2024Sifting through the Noise: A Survey of Diffusion Probabilistic Models and Their Applications to Biomoleculescited by 1
  10. 2025Towards More Accurate Personalized Image Generation: Addressing Overfitting and Evaluation Biascited by 1
  11. 2026SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformerscited by 1
  12. 2025PharMolixFM: All-Atom Foundation Models for Molecular Modeling and Generationcited by 0
  13. 2025Demystify Protein Generation with Hierarchical Conditional Diffusion Modelscited by 0
  14. 2026No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddingscited by 0
  15. 2026Efficient Synthetic Network Generation via Latent Embedding Reconstructioncited by 0
  16. 2026Enhancing Protein Representation Learning via Manifold Restore Mixingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From thermodynamics to protein design: Diffusion models for biomolecule generation towards autonomous protein engineering
  2. 2023Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure
  3. 2023EigenFold: Generative Protein Structure Prediction with Diffusion Models
  4. 2025Discriminative protein sequence modelling with Latent Space Diffusion
  5. 2024Secondary Structure-Guided Novel Protein Sequence Generation with Latent Graph Diffusion
  6. 2023Graph Denoising Diffusion for Inverse Protein Folding
  7. 2024Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation
  8. 2023Geometric Latent Diffusion Models for 3D Molecule Generation