RhoDesign RNA Inverse Folding
Generates RNA sequences with precise structural fidelity and functional diversity for targeted applications
RhoDesign is a deep learning platform for the generative design of RNA sequences informed by 3D structural data. By leveraging a combination of geometric vector perceptrons (GVPs) to encode RNA tertiary structures and transformer architectures to process structural and sequence relationships, it generates RNA sequences predicted to match specific structural backbones. The platform has been successfully applied to design fluorescent RNA aptamers, which demonstrated structural fidelity and novel sequence diversity while maintaining functionality. Benchmark evaluations highlighted its superior performance compared to other models, making it a powerful tool for resource-efficient and targeted RNA design.
Estimated resource cost: 0.000248
Categories: Structure Prediction & Folding
Tags: Inverse Folding Nucleotides
Key Capabilities
- Generates RNA sequences matching specified 3D structural backbones.
- Encodes tertiary structural features using geometric vector perceptrons.
- Utilizes transformer architectures to capture long-range structural dependencies.
- Achieved superior performance in benchmarks for structural fidelity and sequence recovery.
Runtime Statistics
| Metric | Value |
|---|---|
| runtime_mean | 1380 |
| runtime_median | 1423 |
| runtime_std | 837 |
| runtime_90th_percentile | 2673 |
| runtime_max | 3023 |
Similar Tools
- Boltz-1 (AlphaFold3)
- Boltz-2 (AlphaFold3)
- Chai-1 (AlphaFold3)
- CryoSAMU
Ready to submit your job?
Review your configuration, then confirm the estimated credit cost before you run the job. Note that credit estimates are not guaranteed and runtime can vary depending on inputs and settings.
Estimated Credits: 0.000248
Invite-only, limited-time access. Please contact ztang@getantibody.com.
Invite-only, limited-time access. Please contact ztang@getantibody.com.