analiza aiqbench
The paper applies generative ML to mRNA design. It builds a learned latent manifold with an autoencoder and property predictor, then uses denoising and Langevin-style updates to optimize sequences while staying near real data. The reported gains are measured on oracle-predicted properties and on proxy viability metrics, not wet-lab validation, so readers should treat the 267% and 31% figures as in-silico results. The manifold-constrained approach to avoiding out-of-distribution outputs may be the more transferable idea for other constrained biological sequence generation tasks.
RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics
arXiv:2510.24736v4 Announce Type: replace-cross Abstract: 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.
Authors:Danqi Liao, Chen Liu, Xingzhi Sun, Dié Tang, Haochen Wang, Scott Youlten, Srikar Krishna Gopinath, Haejeong Lee, Ethan C. Strayer, Antonio J. Giraldez, Smita Krishnaswamy
Abstract: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.
Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Biomolecules (q-bio.BM)
arXiv:2510.24736 [q-bio.QM]
(or arXiv:2510.24736v4 [q-bio.QM] for this version)
Text integral sub licența deschisă a publicației · 238 cuvinte
Subiecte conexe
Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression
arXiv · 6 oct. 2026
Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation
arXiv · 22 iul. 2026
Informe de riesgos de la IA de frontera (febrero–marzo de 2026)
METR · 19 mai 2026
Frontier AI Risk Report (February–March 2026)
METR · 19 mai 2026