Reproduce “Latent Diffusion Models for Controllable RNA Sequence Generation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kaixuan Huang, Yukang Yang, Kaidi Fu, Yanyi Chu, Le Cong, Mengdi Wang
RNAdiffusion generates variable-length RNA sequences by compressing them into fixed-size latent representations and steering diffusion with a trained predictor. For 5′-UTRs, the authors fine-tune the diffusion model and guide generation toward translation-efficiency (TE) or mean-ribosome-loading (MRL) targets. On sequences over 30 bp, a separate-seed predictor reports higher scores than unguided generation, but these are computational predictions, not measured protein production.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.