Pith. sign in

REVIEW 13 cited by

Fast protein backbone generation with SE(3) flow matching

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.05297 v2 pith:WZCMNTH4 submitted 2023-10-08 q-bio.QM

Jason Yim , Andrew Campbell , Andrew Y. K. Foong , Michael Gastegger , José Jiménez-Luna , Sarah Lewis , Victor Garcia Satorras , Bastiaan S. Veeling
show 3 more authors
Regina Barzilay Tommi Jaakkola Frank Noé
This is my paper
classification q-bio.QM
keywords proteinflowmatchingbackbonefastframediffframeflowgeneration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present FrameFlow, a method for fast protein backbone generation using SE(3) flow matching. Specifically, we adapt FrameDiff, a state-of-the-art diffusion model, to the flow-matching generative modeling paradigm. We show how flow matching can be applied on SE(3) and propose modifications during training to effectively learn the vector field. Compared to FrameDiff, FrameFlow requires five times fewer sampling timesteps while achieving two fold better designability. The ability to generate high quality protein samples at a fraction of the cost of previous methods paves the way towards more efficient generative models in de novo protein design.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Open Materials Generation with Inference-Time Reinforcement Learning

    cs.LG 2026-01 conditional novelty 7.0 of 10

    Reinforcement learning can be applied to velocity-only flow models of crystals by adding small noise at inference time, matching score-based RL and cutting integration steps by roughly tenfold.

  2. La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

    cs.LG 2025-07 conditional novelty 7.0 of 10

    La-Proteina generates full-atom protein structures and sequences via flow matching over an explicit alpha-carbon backbone plus fixed-size per-residue latents, achieving state-of-the-art co-designability and scaling to...

  3. Spectral Diffusion for Protein Dynamics

    q-bio.BM 2026-07 conditional novelty 6.5 of 10

    Diffusion over DCT spectral volumes of Cα displacements yields fast, temperature-conditioned protein trajectories with RMSF Pearson r of 0.844 on held-out mdCATH.

  4. SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups

    cs.LG 2026-07 conditional novelty 6.0 of 10

    SE(3)-MeanFlow trains a protein backbone generator to predict average Lie-group velocities, reaching comparable designability to flow matching at 20–100 steps and leading at 10 steps after rectification.

  5. Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Using a product-of-hyperspheres Riemannian flow matching model on VGGT's latent codes, the authors generate plausible depth, point maps, and RGB for target views from one to four unposed context images.

  6. Exploring the Alignment of Generation and Understanding in Protein Structure Modeling

    cs.CE 2026-07 conditional novelty 6.0 of 10

    Aligning a protein diffusion generator's internal representations to a pretrained structure encoder (ProteinMPNN) raises the MotifBench motif-scaffolding score from 39.2 to 47.1 (~20% relative) over the Protpardelle-1...

  7. Variable-Length Generative Protein Design via Generalized Poisson Flow

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Generalized Poisson Flow learns variable protein length via an inhomogeneous Poisson rate plus within-length flow matching, with KL bounds and gains on structure, sequence, motif, and peptide tasks.

  8. Design-CP: Context Parallelism for Design of Protein Nanoparticles

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Context-parallel inference for RFdiffusion 3 enables end-to-end all-atom design of large symmetric protein nanoparticles on multi-GPU hardware without retraining.

  9. MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation Optimization

    q-bio.BM 2026-01 conditional novelty 6.0 of 10

    A multi-stage generative pipeline—backbone flow matching, side-chain flow matching, and force-field minimization—produces cyclic peptide conformations with lower predicted energy and higher sampled diversity than AF2-...

  10. Text2Structure3D: Graph-Based Generative Modeling of Equilibrium Structures with Diffusion Transformers

    cs.CE 2026-01 conditional novelty 6.0 of 10

    A text-conditioned latent diffusion model over structural graphs generates funicular and truss bridge designs that are post-processed into static equilibrium.

  11. Sesame: Opening the door to protein pockets

    q-bio.BM 2025-08 conditional novelty 6.0 of 10

    Sesame uses flow matching to turn apo protein backbones into holo-like backbones, outperforming a Schrödinger-bridge baseline on geometric benchmarks but with limited docking validation.

  12. Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders

    cs.LG 2026-02 conditional novelty 5.0 of 10

    Training flow matching along sphere geodesics with a curvature-aware loss weight lets standard DiT-B converge on DINOv2 features (FID 3.37 with guidance), contradicting the need for width scaling.

  13. Energy-Based Flow Matching for Generating 3D Molecular Structure

    cs.LG 2025-08 conditional novelty 5.0 of 10

    IDFlow trains a flow matching network to refine its own predicted 3D molecular structure, improving docking and protein backbone generation over HarmonicFlow and FrameFlow baselines.

Pith tools