# RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics

arXiv: https://arxiv.org/abs/2510.24736 · HTML: https://mlsanity.com/paper/2510.24736/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 88 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [Neural SDEs as Infinite-Dimensional GANs](https://mlsanity.com/paper/2102.03657/) (2021)
- [Protein Design with Guided Discrete Diffusion](https://mlsanity.com/paper/2305.20009/) (2023)
- [Manifold Preserving Guided Diffusion](https://mlsanity.com/paper/2311.16424/) (2023)
- [Generalized Denoising Auto-Encoders as Generative Models](https://mlsanity.com/paper/1305.6663/) (2013)
- [Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders](https://mlsanity.com/paper/2203.12742/) (2022)
- [Metric Flow Matching for Smooth Interpolations on the Data Manifold](https://mlsanity.com/paper/2405.14780/) (2024)
- [Graph Denoising Diffusion for Inverse Protein Folding](https://mlsanity.com/paper/2306.16819/) (2023)
- [Protein sequence design with deep generative models](https://mlsanity.com/paper/2104.04457/) (2021)
- [Accurate RNA 3D structure prediction using a language model-based deep learning approach](https://mlsanity.com/paper/2207.01586/) (2022)
- [Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition](https://mlsanity.com/paper/2301.06083/) (2022)
- [Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy](https://mlsanity.com/paper/2312.04823/) (2023)
- [Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds](https://mlsanity.com/paper/2410.12779/) (2024)
- [Geometry-Based Data Generation](https://mlsanity.com/paper/1802.04927/) (2018)
- [Fast differentiable DNA and protein sequence optimization for molecular design](https://mlsanity.com/paper/2005.11275/) (2020)
- [Variational auto-encoding of protein sequences](https://mlsanity.com/paper/1712.03346/) (2017)
- [CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation](https://mlsanity.com/paper/2209.11359/) (2022)
- [DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images](https://mlsanity.com/paper/2410.03058/) (2024)

## Abstract (arXiv)

Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains challenging due to limited data, complex sequence-function relationships, and the narrow space of biologically viable sequences. Generative methods that drift away from the data manifold can yield sequences that fail to fold, translate poorly, or are otherwise nonfunctional. We present RNAGenScape, a property-guided manifold Langevin dynamics framework for mRNA sequence generation that operates on a learned manifold of real data. By performing iterative local optimization constrained to this manifold, RNAGenScape preserves favorable computational viability proxies, accesses reliable guidance, and discourages excursions into regions poorly supported by the training data. The framework integrates three components: (1) an autoencoder jointly trained with a property predictor to learn a property-organized latent manifold, (2) a denoising autoencoder that projects updates back onto the manifold, and (3) a property-guided Langevin dynamics procedure that performs optimization along the manifold. Across three real-world mRNA datasets spanning two orders of magnitude in size, RNAGenScape increases median oracle-predicted property gain by up to 267% and success rate by up to 31%, while maintaining good biological viability proxy measures and achieving competitive inference efficiency compared to existing generative approaches.