Structure-based RNA Design by Step-wise Optimization of Latent Diffusion Model

• URL: http://arxiv.org/abs/2601.19232v1
• Date: Tue, 27 Jan 2026 06:04:02 GMT
• Title: Structure-based RNA Design by Step-wise Optimization of Latent Diffusion Model
• Authors: Qi Si, Xuyang Liu, Penglei Wang, Xin Guo, Yuan Qi, Yuan Cheng,
• Abstract summary: RNA inverse folding is critical for therapeutics, gene regulation, and synthetic biology.<n>Current methods, focused on sequence recovery, struggle to address structural objectives.<n>We propose a reinforcement learning framework integrated with a latent diffusion model.
• Score: 22.539981000962374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: RNA inverse folding, designing sequences to form specific 3D structures, is critical for therapeutics, gene regulation, and synthetic biology. Current methods, focused on sequence recovery, struggle to address structural objectives like secondary structure consistency (SS), minimum free energy (MFE), and local distance difference test (LDDT), leading to suboptimal structural accuracy. To tackle this, we propose a reinforcement learning (RL) framework integrated with a latent diffusion model (LDM). Drawing inspiration from the success of diffusion models in RNA inverse folding, which adeptly model complex sequence-structure interactions, we develop an LDM incorporating pre-trained RNA-FM embeddings from a large-scale RNA model. These embeddings capture co-evolutionary patterns, markedly improving sequence recovery accuracy. However, existing approaches, including diffusion-based methods, cannot effectively handle non-differentiable structural objectives. By contrast, RL excels in this task by using policy-driven reward optimization to navigate complex, non-gradient-based objectives, offering a significant advantage over traditional methods. In summary, we propose the Step-wise Optimization of Latent Diffusion Model (SOLD), a novel RL framework that optimizes single-step noise without sampling the full diffusion trajectory, achieving efficient refinement of multiple structural objectives. Experimental results demonstrate SOLD surpasses its LDM baseline and state-of-the-art methods across all metrics, establishing a robust framework for RNA inverse folding with profound implications for biotechnological and therapeutic applications.

Related papers

• RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion [19.386628516684695]
  RIDER is an RNA Inverse DEsign framework with Reinforcement learning that directly optimize for 3D structural similarity.<n>First, we develop and pre-train a GNN-based generative diffusion model conditioned on the target 3D structure.<n>Then, we fine-tune the model with an improved policy gradient algorithm using four task-specific reward functions based on 3D self-consistency metrics.
  arXiv  Detail & Related papers  (2026-02-18T15:52:26Z)
• Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design [58.8094854658848]
  We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design.<n>We propose an iterative distillation-based fine-tuning framework that enables diffusion models to optimize for arbitrary reward functions.<n>Our off-policy formulation, combined with KL divergence minimization, enhances training stability and sample efficiency compared to existing RL-based methods.
  arXiv  Detail & Related papers  (2025-07-01T05:55:28Z)
• Differentiable Folding for Nearest Neighbor Model Optimization [0.6291443816903801]
  The Nearest Neighbor model is the $textitde facto$ thermodynamic model of RNA secondary structure formation.<n>Here, we leverage recent advances in $textitdifferentiable folding$ to devise an efficient, scalable, and flexible means of parameter optimization.<n>Our method yields a significantly improved parameter set that outperforms existing baselines on all metrics.
  arXiv  Detail & Related papers  (2025-03-12T05:36:12Z)
• Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design [56.957070405026194]
  We propose an algorithm that enables direct backpropagation of rewards through entire trajectories generated by diffusion models.<n>DRAKES can generate sequences that are both natural-like and yield high rewards.
  arXiv  Detail & Related papers  (2024-10-17T15:10:13Z)
• Latent Diffusion Models for Controllable RNA Sequence Generation [33.38594748558547]
  RNA is a key intermediary between DNA and protein, exhibiting high sequence diversity and complex three-dimensional structures. We develop a latent diffusion model for generating and optimizing discrete RNA sequences of variable lengths. Empirical results confirm that RNAdiffusion generates non-coding RNAs that align with natural distributions across various biological metrics.
  arXiv  Detail & Related papers  (2024-09-15T19:04:50Z)
• Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review [63.31328039424469]
  This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. We explain the application of various RL algorithms, including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
  arXiv  Detail & Related papers  (2024-07-18T17:35:32Z)
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
  DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model. We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
  arXiv  Detail & Related papers  (2024-03-07T02:53:40Z)
• Scalable Deep Learning for RNA Secondary Structure Prediction [38.46798525594529]
  We present the RNAformer, a lean deep learning model using axial attention and recycling in the latent space. Our approach achieves state-of-the-art performance on the popular TS0 benchmark dataset. We show experimentally that the RNAformer can learn a biophysical model of the RNA folding process.
  arXiv  Detail & Related papers  (2023-07-14T12:54:56Z)
• Protein Design with Guided Discrete Diffusion [67.06148688398677]
  A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling. We propose diffusioN Optimized Sampling (NOS), a guidance method for discrete diffusion models. NOS makes it possible to perform design directly in sequence space, circumventing significant limitations of structure-based methods.
  arXiv  Detail & Related papers  (2023-05-31T16:31:24Z)
• RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design [65.41144149958208]
  This study aims to systematically construct a data-driven RNA design pipeline. We crafted a benchmark dataset and designed a comprehensive structural modeling approach to represent the complex RNA tertiary structure. We incorporated extracted secondary structures with base pairs as prior knowledge to facilitate the RNA design process.
  arXiv  Detail & Related papers  (2023-01-25T17:19:49Z)
• Accurate RNA 3D structure prediction using a language model-based deep learning approach [50.193512039121984]
  RhoFold+ is an RNA language model-based deep learning method that accurately predicts 3D structures of single-chain RNAs from sequences.<n>RhoFold+ offers a fully automated end-to-end pipeline for RNA 3D structure prediction.
  arXiv  Detail & Related papers  (2022-07-04T17:15:35Z)

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.