RoseTTAFold3
Open-source all-atom foundation model for structure prediction and generative design.
RosettaFold-3 (RF3) is a unified biomolecular foundation model developed using the AtomWorks framework. It is designed to bridge the gap between open-source models and AlphaFold 3, offering state-of-the-art accuracy in predicting arbitrary biomolecular complexes, including proteins, nucleic acids, small molecules, and mixed L/D peptides. RF3 distinguishes itself with improved handling of chirality through geometric conditioning and the ability to accept arbitrary atom-level constraints for tasks like docking and conformer templating.
Estimated resource cost: 0.001178
Categories: Structure Prediction & Folding
Tags: Co-Folding Nucleotides Protein Folding Proteins Protein–Ligand Docking Protein–Protein Docking Small Molecules
Key Capabilities
- Built on AtomWorks, a modular framework for rapid prototyping and high-quality data processing.
- Explicit geometric features for chirality ensure 88% accuracy on ligand chiral centers.
- Arbitrary atom-level conditioning allows user-specified distance constraints and ligand conformers.
- Unified architecture capable of structure prediction, generative design, and fixed-backbone design.
- Trained on novel distillation datasets for nucleic acids, RNA, and disordered protein regions.
- Demonstrates high accuracy on mixed L/D peptides and antibody-antigen complexes.
- Performance competitive with AlphaFold 3 and exceeding Boltz-1/Boltz-2 on multiple benchmarks.
Runtime Statistics
| Metric | Value |
|---|---|
| runtime_mean | 247 |
| runtime_median | 192 |
| runtime_std | 221 |
| runtime_90th_percentile | 535 |
| runtime_max | 1108 |
Similar Tools
- Boltz-1 (AlphaFold3)
- Boltz-2 (AlphaFold3)
- Chai-1 (AlphaFold3)
- IntelliFold (AlphaFold3)
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: 0.001178
Invite-only, limited-time access. Please contact ztang@getantibody.com.
Invite-only, limited-time access. Please contact ztang@getantibody.com.