MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design

Key points

• Structure-conditioned RNA inverse design seeks nucleotide sequences compatible with a target three-dimensional backbone, yet existing reinforcement learning approaches either optimize a separate policy for each target backbone or rely on offline preference optimization, leaving online post-training of a reusable backbone-conditioned model largely unexplored.1
• MORAD combines backbone-conditioned group sampling, group-relative reward normalization, and a forward-process diffusion objective.1
• Beyond existing RL rewards that primarily target tertiary structural quality, MORAD jointly optimizes six measurements spanning tertiary geometry, base pairing, ensemble behavior, and sequence composition.1
• On the test set, MORAD outperforms RiboDiffusion, gRNAde, and RDesign across tertiary structural accuracy, secondary-structure pairing, and thermodynamic quality, establishing a new state of the art in structure-conditioned RNA inverse design.1

Sources (1)

• [1]MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 09:50 AM

  We introduce MORAD, an online reinforcement learning framework for backbone-conditioned RNA diffusion models that trains a single shared policy across diverse target backbones.

  Structure-conditioned RNA inverse design seeks nucleotide sequences compatible with a target three-dimensional backbone, yet existing reinforcement learning approaches either optimize a separate policy for each target backbone or rely on offline preference optimization, leaving online post-training of a reusable backbone-conditioned model largely unexplored.

Extractive summary: sentences quoted from the sources.