---
title: README
emoji: 🧬
colorFrom: green
colorTo: blue
sdk: static
pinned: false
short_description: Organization card for MORAD
---

# MORAD

**Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design**

MORAD post-trains a single backbone-conditioned RNA diffusion policy online with
a six-objective reward covering tertiary geometry, base pairing, ensemble
behavior and sequence composition. The trained policy designs sequences for a
new target backbone directly, with no per-target optimization.

| | |
|---|---|
| 🧬 [**MORAD-RIDE**](https://huggingface.co/MORAD-RNA/MORAD-RIDE) | the released model, post-trained from pretrained RIDE |
| 📦 [**MORAD-Targets**](https://huggingface.co/datasets/MORAD-RNA/MORAD-Targets) | 527 training and 153 test RNA backbone targets |
| 💻 [**Code**](https://github.com/Gabrile166/MORAD) | training, evaluation and reproduction scripts |
| 🌐 [**Project page**](https://gabrile166.github.io/MORAD/) | overview, method and results |