SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers

• URL: http://arxiv.org/abs/2602.06706v1
• Date: Fri, 06 Feb 2026 13:50:13 GMT
• Title: SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers
• Authors: Shentong Mo, Lanqing Li,
• Abstract summary: We present SaDiT, a novel framework that accelerates protein backbone generation by integrating SaProt Tokenization with a Diffusion Transformer (DiT) architecture.<n>Experiments demonstrate that SaDiT outperforms state-of-the-art models, including RFDiffusion and Proteina, in both computational speed and structural viability.
• Score: 50.18388227899971
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative models for de novo protein backbone design have achieved remarkable success in creating novel protein structures. However, these diffusion-based approaches remain computationally intensive and slower than desired for large-scale structural exploration. While recent efforts like Proteina have introduced flow-matching to improve sampling efficiency, the potential of tokenization for structural compression and acceleration remains largely unexplored in the protein domain. In this work, we present SaDiT, a novel framework that accelerates protein backbone generation by integrating SaProt Tokenization with a Diffusion Transformer (DiT) architecture. SaDiT leverages a discrete latent space to represent protein geometry, significantly reducing the complexity of the generation process while maintaining theoretical SE(3) equivalence. To further enhance efficiency, we introduce an IPA Token Cache mechanism that optimizes the Invariant Point Attention (IPA) layers by reusing computed token states during iterative sampling. Experimental results demonstrate that SaDiT outperforms state-of-the-art models, including RFDiffusion and Proteina, in both computational speed and structural viability. We evaluate our model across unconditional backbone generation and fold-class conditional generation tasks, where SaDiT shows superior ability to capture complex topological features with high designability.

Related papers

• Efficient Protein Optimization via Structure-aware Hamiltonian Dynamics [16.336540408998598]
  HADES is a Bayesian optimization method utilizing Hamiltonian dynamics to efficiently sample from a structure-aware approximated posterior.<n>A position discretization procedure is introduced to propose discrete protein sequences from such a continuous state system.<n>Experiments demonstrate that our method outperforms state-of-the-art baselines in in-silico evaluations.
  arXiv  Detail & Related papers  (2026-01-16T05:53:53Z)
• Protein Folding with Neural Ordinary Differential Equations [9.980631693646528]
  We propose a continuous-depth formulation of the Evoformer, replacing its 48 discrete blocks with a Neural ODE parameterization that preserves its core attention-based operations.<n>We find that the Neural ODE-based Evoformer produces structurally plausible predictions and reliably captures certain secondary structure elements, such as alpha-helices.<n>Our model achieves this performance using dramatically fewer resources, just 17.5 hours of training on a single GPU.
  arXiv  Detail & Related papers  (2025-10-17T22:56:03Z)
• ProteinAE: Protein Diffusion Autoencoders for Structure Encoding [64.77182442408254]
  We introduce ProteinAE, a novel and streamlined protein diffusion autoencoder.<n>ProteinAE directly maps protein backbone coordinates from E(3) into a continuous, compact latent space.<n>We demonstrate that ProteinAE achieves state-of-the-art reconstruction quality, outperforming existing autoencoders.
  arXiv  Detail & Related papers  (2025-10-12T14:30:32Z)
• Distilled Protein Backbone Generation [59.63474232035653]
  Diffusion- and flow-based generative models offer unprecedented capabilities for de novo protein design.<n>These models are limited by their generating speed, often requiring hundreds of iterative steps in the reverse-diffusion process.<n>We show how to appropriately adapt Score identity Distillation (SiD), a state-of-the-art score distillation strategy, to train few-step protein backbone generators.
  arXiv  Detail & Related papers  (2025-10-03T15:25:08Z)
• The Latent Road to Atoms: Backmapping Coarse-grained Protein Structures with Latent Diffusion [19.85659309869674]
  Latent Diffusion Backmapping (LDB) is a novel approach leveraging denoising diffusion within latent space to address these challenges. We evaluate LDB's state-of-the-art performance on three distinct protein datasets. Our results position LDB as a powerful and scalable approach for backmapping, effectively bridging the gap between CG simulations and atomic-level analyses in computational biology.
  arXiv  Detail & Related papers  (2024-10-17T06:38:07Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)
• Learning Geometrically Disentangled Representations of Protein Folding Simulations [72.03095377508856]
  This work focuses on learning a generative neural network on a structural ensemble of a drug-target protein. Model tasks involve characterizing the distinct structural fluctuations of the protein bound to various drug molecules. Results show that our geometric learning-based method enjoys both accuracy and efficiency for generating complex structural variations.
  arXiv  Detail & Related papers  (2022-05-20T19:38:00Z)
• EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models [53.17320541056843]
  We propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network. Our EBM-Fold approach can efficiently produce high-quality decoys, compared against traditional Rosetta-based structure optimization routines.
  arXiv  Detail & Related papers  (2021-05-11T03:40:29Z)

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.